20210611.md

ArXiv cs.CV --Fri, 11 Jun 2021

1.Dynamics-Regulated Kinematic Policy for Egocentric Pose Estimation ⬇️

We propose a method for object-aware 3D egocentric pose estimation that tightly integrates kinematics modeling, dynamics modeling, and scene object information. Unlike prior kinematics or dynamics-based approaches where the two components are used disjointly, we synergize the two approaches via dynamics-regulated training. At each timestep, a kinematic model is used to provide a target pose using video evidence and simulation state. Then, a prelearned dynamics model attempts to mimic the kinematic pose in a physics simulator. By comparing the pose instructed by the kinematic model against the pose generated by the dynamics model, we can use their misalignment to further improve the kinematic model. By factoring in the 6DoF pose of objects (e.g., chairs, boxes) in the scene, we demonstrate for the first time, the ability to estimate physically-plausible 3D human-object interactions using a single wearable camera. We evaluate our egocentric pose estimation method in both controlled laboratory settings and real-world scenarios.

2.Space-time Mixing Attention for Video Transformer ⬇️

This paper is on video recognition using Transformers. Very recent attempts in this area have demonstrated promising results in terms of recognition accuracy, yet they have been also shown to induce, in many cases, significant computational overheads due to the additional modelling of the temporal information. In this work, we propose a Video Transformer model the complexity of which scales linearly with the number of frames in the video sequence and hence induces \textit{no overhead} compared to an image-based Transformer model. To achieve this, our model makes two approximations to the full space-time attention used in Video Transformers: (a) It restricts time attention to a local temporal window and capitalizes on the Transformer's depth to obtain full temporal coverage of the video sequence. (b) It uses efficient space-time mixing to attend \textit{jointly} spatial and temporal locations without inducing any additional cost on top of a spatial-only attention model. We also show how to integrate 2 very lightweight mechanisms for global temporal-only attention which provide additional accuracy improvements at minimal computational cost. We demonstrate that our model produces very high recognition accuracy on the most popular video recognition datasets while at the same time being significantly more efficient than other Video Transformer models. Code will be made available.

3.Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations ⬇️

Contrastive self-supervised learning has outperformed supervised pretraining on many downstream tasks like segmentation and object detection. However, current methods are still primarily applied to curated datasets like ImageNet. In this paper, we first study how biases in the dataset affect existing methods. Our results show that current contrastive approaches work surprisingly well across: (i) object- versus scene-centric, (ii) uniform versus long-tailed and (iii) general versus domain-specific datasets. Second, given the generality of the approach, we try to realize further gains with minor modifications. We show that learning additional invariances -- through the use of multi-scale cropping, stronger augmentations and nearest neighbors -- improves the representations. Finally, we observe that MoCo learns spatially structured representations when trained with a multi-crop strategy. The representations can be used for semantic segment retrieval and video instance segmentation without finetuning. Moreover, the results are on par with specialized models. We hope this work will serve as a useful study for other researchers. The code and models will be available at this https URL.

4.Learning by Watching ⬇️

When in a new situation or geographical location, human drivers have an extraordinary ability to watch others and learn maneuvers that they themselves may have never performed. In contrast, existing techniques for learning to drive preclude such a possibility as they assume direct access to an instrumented ego-vehicle with fully known observations and expert driver actions. However, such measurements cannot be directly accessed for the non-ego vehicles when learning by watching others. Therefore, in an application where data is regarded as a highly valuable asset, current approaches completely discard the vast portion of the training data that can be potentially obtained through indirect observation of surrounding vehicles. Motivated by this key insight, we propose the Learning by Watching (LbW) framework which enables learning a driving policy without requiring full knowledge of neither the state nor expert actions. To increase its data, i.e., with new perspectives and maneuvers, LbW makes use of the demonstrations of other vehicles in a given scene by (1) transforming the ego-vehicle's observations to their points of view, and (2) inferring their expert actions. Our LbW agent learns more robust driving policies while enabling data-efficient learning, including quick adaptation of the policy to rare and novel scenarios. In particular, LbW drives robustly even with a fraction of available driving data required by existing methods, achieving an average success rate of 92% on the original CARLA benchmark with only 30 minutes of total driving data and 82% with only 10 minutes.

5.Implicit-PDF: Non-Parametric Representation of Probability Distributions on the Rotation Manifold ⬇️

Single image pose estimation is a fundamental problem in many vision and robotics tasks, and existing deep learning approaches suffer by not completely modeling and handling: i) uncertainty about the predictions, and ii) symmetric objects with multiple (sometimes infinite) correct poses. To this end, we introduce a method to estimate arbitrary, non-parametric distributions on SO(3). Our key idea is to represent the distributions implicitly, with a neural network that estimates the probability given the input image and a candidate pose. Grid sampling or gradient ascent can be used to find the most likely pose, but it is also possible to evaluate the probability at any pose, enabling reasoning about symmetries and uncertainty. This is the most general way of representing distributions on manifolds, and to showcase the rich expressive power, we introduce a dataset of challenging symmetric and nearly-symmetric objects. We require no supervision on pose uncertainty -- the model trains only with a single pose per example. Nonetheless, our implicit model is highly expressive to handle complex distributions over 3D poses, while still obtaining accurate pose estimation on standard non-ambiguous environments, achieving state-of-the-art performance on Pascal3D+ and ModelNet10-SO(3) benchmarks.

6.Learning to See by Looking at Noise ⬇️

Current vision systems are trained on huge datasets, and these datasets come with costs: curation is expensive, they inherit human biases, and there are concerns over privacy and usage rights. To counter these costs, interest has surged in learning from cheaper data sources, such as unlabeled images. In this paper we go a step further and ask if we can do away with real image datasets entirely, instead learning from noise processes. We investigate a suite of image generation models that produce images from simple random processes. These are then used as training data for a visual representation learner with a contrastive loss. We study two types of noise processes, statistical image models and deep generative models under different random initializations. Our findings show that it is important for the noise to capture certain structural properties of real data but that good performance can be achieved even with processes that are far from realistic. We also find that diversity is a key property to learn good representations. Datasets, models, and code are available at this https URL.

7.What Does Rotation Prediction Tell Us about Classifier Accuracy under Varying Testing Environments? ⬇️

Understanding classifier decision under novel environments is central to the community, and a common practice is evaluating it on labeled test sets. However, in real-world testing, image annotations are difficult and expensive to obtain, especially when the test environment is changing. A natural question then arises: given a trained classifier, can we evaluate its accuracy on varying unlabeled test sets? In this work, we train semantic classification and rotation prediction in a multi-task way. On a series of datasets, we report an interesting finding, i.e., the semantic classification accuracy exhibits a strong linear relationship with the accuracy of the rotation prediction task (Pearson's Correlation r > 0.88). This finding allows us to utilize linear regression to estimate classifier performance from the accuracy of rotation prediction which can be obtained on the test set through the freely generated rotation labels.

8.Adversarial Motion Modelling helps Semi-supervised Hand Pose Estimation ⬇️

Hand pose estimation is difficult due to different environmental conditions, object- and self-occlusion as well as diversity in hand shape and appearance. Exhaustively covering this wide range of factors in fully annotated datasets has remained impractical, posing significant challenges for generalization of supervised methods. Embracing this challenge, we propose to combine ideas from adversarial training and motion modelling to tap into unlabeled videos. To this end we propose what to the best of our knowledge is the first motion model for hands and show that an adversarial formulation leads to better generalization properties of the hand pose estimator via semi-supervised training on unlabeled video sequences. In this setting, the pose predictor must produce a valid sequence of hand poses, as determined by a discriminative adversary. This adversary reasons both on the structural as well as temporal domain, effectively exploiting the spatio-temporal structure in the task. The main advantage of our approach is that we can make use of unpaired videos and joint sequence data both of which are much easier to attain than paired training data. We perform extensive evaluation, investigating essential components needed for the proposed framework and empirically demonstrate in two challenging settings that the proposed approach leads to significant improvements in pose estimation accuracy. In the lowest label setting, we attain an improvement of $40%$ in absolute mean joint error.

9.Self-Supervised 3D Hand Pose Estimation from monocular RGB via Contrastive Learning ⬇️

Acquiring accurate 3D annotated data for hand pose estimation is a notoriously difficult problem. This typically requires complex multi-camera setups and controlled conditions, which in turn creates a domain gap that is hard to bridge to fully unconstrained settings. Encouraged by the success of contrastive learning on image classification tasks, we propose a new self-supervised method for the structured regression task of 3D hand pose estimation. Contrastive learning makes use of unlabeled data for the purpose of representation learning via a loss formulation that encourages the learned feature representations to be invariant under any image transformation. For 3D hand pose estimation, it too is desirable to have invariance to appearance transformation such as color jitter. However, the task requires equivariance under affine transformations, such as rotation and translation. To address this issue, we propose an equivariant contrastive objective and demonstrate its effectiveness in the context of 3D hand pose estimation. We experimentally investigate the impact of invariant and equivariant contrastive objectives and show that learning equivariant features leads to better representations for the task of 3D hand pose estimation. Furthermore, we show that a standard ResNet-152, trained on additional unlabeled data, attains an improvement of $7.6%$ in PA-EPE on FreiHAND and thus achieves state-of-the-art performance without any task specific, specialized architectures.

10.Curiously Effective Features for Image Quality Prediction ⬇️

The performance of visual quality prediction models is commonly assumed to be closely tied to their ability to capture perceptually relevant image aspects. Models are thus either based on sophisticated feature extractors carefully designed from extensive domain knowledge or optimized through feature learning. In contrast to this, we find feature extractors constructed from random noise to be sufficient to learn a linear regression model whose quality predictions reach high correlations with human visual quality ratings, on par with a model with learned features. We analyze this curious result and show that besides the quality of feature extractors also their quantity plays a crucial role - with top performances only being achieved in highly overparameterized models.

11.FetReg: Placental Vessel Segmentation and Registration in Fetoscopy Challenge Dataset ⬇️

Fetoscopy laser photocoagulation is a widely used procedure for the treatment of Twin-to-Twin Transfusion Syndrome (TTTS), that occur in mono-chorionic multiple pregnancies due to placental vascular anastomoses. This procedure is particularly challenging due to limited field of view, poor manoeuvrability of the fetoscope, poor visibility due to fluid turbidity, variability in light source, and unusual position of the placenta. This may lead to increased procedural time and incomplete ablation, resulting in persistent TTTS. Computer-assisted intervention may help overcome these challenges by expanding the fetoscopic field of view through video mosaicking and providing better visualization of the vessel network. However, the research and development in this domain remain limited due to unavailability of high-quality data to encode the intra- and inter-procedure variability. Through the Fetoscopic Placental Vessel Segmentation and Registration (FetReg) challenge, we present a large-scale multi-centre dataset for the development of generalized and robust semantic segmentation and video mosaicking algorithms for the fetal environment with a focus on creating drift-free mosaics from long duration fetoscopy videos. In this paper, we provide an overview of the FetReg dataset, challenge tasks, evaluation metrics and baseline methods for both segmentation and registration. Baseline methods results on the FetReg dataset shows that our dataset poses interesting challenges, which can be modelled and competed for through our crowd-sourcing initiative of the FetReg challenge.

12.Implicit Feature Alignment: Learn to Convert Text Recognizer to Text Spotter ⬇️

Text recognition is a popular research subject with many associated challenges. Despite the considerable progress made in recent years, the text recognition task itself is still constrained to solve the problem of reading cropped line text images and serves as a subtask of optical character recognition (OCR) systems. As a result, the final text recognition result is limited by the performance of the text detector. In this paper, we propose a simple, elegant and effective paradigm called Implicit Feature Alignment (IFA), which can be easily integrated into current text recognizers, resulting in a novel inference mechanism called IFAinference. This enables an ordinary text recognizer to process multi-line text such that text detection can be completely freed. Specifically, we integrate IFA into the two most prevailing text recognition streams (attention-based and CTC-based) and propose attention-guided dense prediction (ADP) and Extended CTC (ExCTC). Furthermore, the Wasserstein-based Hollow Aggregation Cross-Entropy (WH-ACE) is proposed to suppress negative predictions to assist in training ADP and ExCTC. We experimentally demonstrate that IFA achieves state-of-the-art performance on end-to-end document recognition tasks while maintaining the fastest speed, and ADP and ExCTC complement each other on the perspective of different application scenarios. Code will be available at this https URL.

13.Anatomy X-Net: A Semi-Supervised Anatomy Aware Convolutional Neural Network for Thoracic Disease Classification ⬇️

Thoracic disease detection from chest radiographs using deep learning methods has been an active area of research in the last decade. Most previous methods attempt to focus on the diseased organs of the image by identifying spatial regions responsible for significant contributions to the model's prediction. In contrast, expert radiologists first locate the prominent anatomical structures before determining if those regions are anomalous. Therefore, integrating anatomical knowledge within deep learning models could bring substantial improvement in automatic disease classification. This work proposes an anatomy-aware attention-based architecture named Anatomy X-Net, that prioritizes the spatial features guided by the pre-identified anatomy regions. We leverage a semi-supervised learning method using the JSRT dataset containing organ-level annotation to obtain the anatomical segmentation masks (for lungs and heart) for the NIH and CheXpert datasets. The proposed Anatomy X-Net uses the pre-trained DenseNet-121 as the backbone network with two corresponding structured modules, the Anatomy Aware Attention (AAA) and Probabilistic Weighted Average Pooling (PWAP), in a cohesive framework for anatomical attention learning. Our proposed method sets new state-of-the-art performance on the official NIH test set with an AUC score of 0.8439, proving the efficacy of utilizing the anatomy segmentation knowledge to improve the thoracic disease classification. Furthermore, the Anatomy X-Net yields an averaged AUC of 0.9020 on the Stanford CheXpert dataset, improving on existing methods that demonstrate the generalizability of the proposed framework.

14.Unsupervised Co-part Segmentation through Assembly ⬇️

Co-part segmentation is an important problem in computer vision for its rich applications. We propose an unsupervised learning approach for co-part segmentation from images. For the training stage, we leverage motion information embedded in videos and explicitly extract latent representations to segment meaningful object parts. More importantly, we introduce a dual procedure of part-assembly to form a closed loop with part-segmentation, enabling an effective self-supervision. We demonstrate the effectiveness of our approach with a host of extensive experiments, ranging from human bodies, hands, quadruped, and robot arms. We show that our approach can achieve meaningful and compact part segmentation, outperforming state-of-the-art approaches on diverse benchmarks.

15.Enforcing Morphological Information in Fully Convolutional Networks to Improve Cell Instance Segmentation in Fluorescence Microscopy Images ⬇️

Cell instance segmentation in fluorescence microscopy images is becoming essential for cancer dynamics and prognosis. Data extracted from cancer dynamics allows to understand and accurately model different metabolic processes such as proliferation. This enables customized and more precise cancer treatments. However, accurate cell instance segmentation, necessary for further cell tracking and behavior analysis, is still challenging in scenarios with high cell concentration and overlapping edges. Within this framework, we propose a novel cell instance segmentation approach based on the well-known U-Net architecture. To enforce the learning of morphological information per pixel, a deep distance transformer (DDT) acts as a back-bone model. The DDT output is subsequently used to train a top-model. The following top-models are considered: a three-class (\emph{e.g.,} foreground, background and cell border) U-net, and a watershed transform. The obtained results suggest a performance boost over traditional U-Net architectures. This opens an interesting research line around the idea of injecting morphological information into a fully convolutional model.

16.CAT: Cross Attention in Vision Transformer ⬇️

Since Transformer has found widespread use in NLP, the potential of Transformer in CV has been realized and has inspired many new approaches. However, the computation required for replacing word tokens with image patches for Transformer after the tokenization of the image is vast(e.g., ViT), which bottlenecks model training and inference. In this paper, we propose a new attention mechanism in Transformer termed Cross Attention, which alternates attention inner the image patch instead of the whole image to capture local information and apply attention between image patches which are divided from single-channel feature maps capture global information. Both operations have less computation than standard self-attention in Transformer. By alternately applying attention inner patch and between patches, we implement cross attention to maintain the performance with lower computational cost and build a hierarchical network called Cross Attention Transformer(CAT) for other vision tasks. Our base model achieves state-of-the-arts on ImageNet-1K, and improves the performance of other methods on COCO and ADE20K, illustrating that our network has the potential to serve as general backbones. The code and models are available at \url{this https URL}.

17.Deep Implicit Surface Point Prediction Networks ⬇️

Deep neural representations of 3D shapes as implicit functions have been shown to produce high fidelity models surpassing the resolution-memory trade-off faced by the explicit representations using meshes and point clouds. However, most such approaches focus on representing closed shapes. Unsigned distance function (UDF) based approaches have been proposed recently as a promising alternative to represent both open and closed shapes. However, since the gradients of UDFs vanish on the surface, it is challenging to estimate local (differential) geometric properties like the normals and tangent planes which are needed for many downstream applications in vision and graphics. There are additional challenges in computing these properties efficiently with a low-memory footprint. This paper presents a novel approach that models such surfaces using a new class of implicit representations called the closest surface-point (CSP) representation. We show that CSP allows us to represent complex surfaces of any topology (open or closed) with high fidelity. It also allows for accurate and efficient computation of local geometric properties. We further demonstrate that it leads to efficient implementation of downstream algorithms like sphere-tracing for rendering the 3D surface as well as to create explicit mesh-based representations. Extensive experimental evaluation on the ShapeNet dataset validate the above contributions with results surpassing the state-of-the-art.

18.Multi-resolution Outlier Pooling for Sorghum Classification ⬇️

Automated high throughput plant phenotyping involves leveraging sensors, such as RGB, thermal and hyperspectral cameras (among others), to make large scale and rapid measurements of the physical properties of plants for the purpose of better understanding the difference between crops and facilitating rapid plant breeding programs. One of the most basic phenotyping tasks is to determine the cultivar, or species, in a particular sensor product. This simple phenotype can be used to detect errors in planting and to learn the most differentiating features between cultivars. It is also a challenging visual recognition task, as a large number of highly related crops are grown simultaneously, leading to a classification problem with low inter-class variance. In this paper, we introduce the Sorghum-100 dataset, a large dataset of RGB imagery of sorghum captured by a state-of-the-art gantry system, a multi-resolution network architecture that learns both global and fine-grained features on the crops, and a new global pooling strategy called Dynamic Outlier Pooling which outperforms standard global pooling strategies on this task.

19.The 2021 Hotel-ID to Combat Human Trafficking Competition Dataset ⬇️

Hotel recognition is an important task for human trafficking investigations since victims are often photographed in hotel rooms. Identifying these hotels is vital to trafficking investigations since they can help track down current and future victims who might be taken to the same places. Hotel recognition is a challenging fine grained visual classification task as there can be little similarity between different rooms within the same hotel, and high similarity between rooms from different hotels (especially if they are from the same chain). Hotel recognition to combat human trafficking poses additional challenges as investigative images are often low quality, contain uncommon camera angles and are highly occluded. Here, we present the 2021 Hotel-ID dataset to help raise awareness for this problem and generate novel approaches. The dataset consists of hotel room images that have been crowd-sourced and uploaded through the TraffickCam mobile application. The quality of these images is similar to investigative images and hence models trained on these images have good chances of accurately narrowing down on the correct hotel.

20.Pivotal Tuning for Latent-based Editing of Real Images ⬇️

Recently, a surge of advanced facial editing techniques have been proposed that leverage the generative power of a pre-trained StyleGAN. To successfully edit an image this way, one must first project (or invert) the image into the pre-trained generator's domain. As it turns out, however, StyleGAN's latent space induces an inherent tradeoff between distortion and editability, i.e. between maintaining the original appearance and convincingly altering some of its attributes. Practically, this means it is still challenging to apply ID-preserving facial latent-space editing to faces which are out of the generator's domain. In this paper, we present an approach to bridge this gap. Our technique slightly alters the generator, so that an out-of-domain image is faithfully mapped into an in-domain latent code. The key idea is pivotal tuning - a brief training process that preserves the editing quality of an in-domain latent region, while changing its portrayed identity and appearance. In Pivotal Tuning Inversion (PTI), an initial inverted latent code serves as a pivot, around which the generator is fined-tuned. At the same time, a regularization term keeps nearby identities intact, to locally contain the effect. This surgical training process ends up altering appearance features that represent mostly identity, without affecting editing capabilities. We validate our technique through inversion and editing metrics, and show preferable scores to state-of-the-art methods. We further qualitatively demonstrate our technique by applying advanced edits (such as pose, age, or expression) to numerous images of well-known and recognizable identities. Finally, we demonstrate resilience to harder cases, including heavy make-up, elaborate hairstyles and/or headwear, which otherwise could not have been successfully inverted and edited by state-of-the-art methods.

21.End-to-end lung nodule detection framework with model-based feature projection block ⬇️

This paper proposes novel end-to-end framework for detecting suspicious pulmonary nodules in chest CT scans. The method core idea is a new nodule segmentation architecture with a model-based feature projection block on three-dimensional convolutions. This block acts as a preliminary feature extractor for a two-dimensional U-Net-like convolutional network. Using the proposed approach along with an axial, coronal, and sagittal projection analysis makes it possible to abandon the widely used false positives reduction step. The proposed method achieves SOTA on LUNA2016 with 0.959 average sensitivity, and 0.936 sensitivity if the false-positive level per scan is 0.25. The paper describes the proposed approach and represents the experimental results on LUNA2016 as well as ablation studies.

22.The Medical Segmentation Decathlon ⬇️

International challenges have become the de facto standard for comparative assessment of image analysis algorithms given a specific task. Segmentation is so far the most widely investigated medical image processing task, but the various segmentation challenges have typically been organized in isolation, such that algorithm development was driven by the need to tackle a single specific clinical problem. We hypothesized that a method capable of performing well on multiple tasks will generalize well to a previously unseen task and potentially outperform a custom-designed solution. To investigate the hypothesis, we organized the Medical Segmentation Decathlon (MSD) - a biomedical image analysis challenge, in which algorithms compete in a multitude of both tasks and modalities. The underlying data set was designed to explore the axis of difficulties typically encountered when dealing with medical images, such as small data sets, unbalanced labels, multi-site data and small objects. The MSD challenge confirmed that algorithms with a consistent good performance on a set of tasks preserved their good average performance on a different set of previously unseen tasks. Moreover, by monitoring the MSD winner for two years, we found that this algorithm continued generalizing well to a wide range of other clinical problems, further confirming our hypothesis. Three main conclusions can be drawn from this study: (1) state-of-the-art image segmentation algorithms are mature, accurate, and generalize well when retrained on unseen tasks; (2) consistent algorithmic performance across multiple tasks is a strong surrogate of algorithmic generalizability; (3) the training of accurate AI segmentation models is now commoditized to non AI experts.

23.Face mask detection using convolution neural network ⬇️

In the recent times, the Coronaviruses that are a big family of different viruses have become very common, contagious and dangerous to the whole human kind. It spreads human to human by exhaling the infection breath, which leaves droplets of the virus on different surface which is then inhaled by other person and catches the infection too. So it has become very important to protect ourselves and the people around us from this situation. We can take precautions such as social distancing, washing hands every two hours, using sanitizer, maintaining social distance and the most important wearing a mask. Public use of wearing a masks has become very common everywhere in the whole world now. From that the most affected and devastating condition is of India due to its extreme population in small area. This paper proposes a method to detect the face mask is put on or not for offices, or any other work place with a lot of people coming to work. We have used convolutional neural network for the same. The model is trained on a real world dataset and tested with live video streaming with a good accuracy. Further the accuracy of the model with different hyper parameters and multiple people at different distance and location of the frame is done.

24.Distribution-Aware Semantics-Oriented Pseudo-label for Imbalanced Semi-Supervised Learning ⬇️

The capability of the traditional semi-supervised learning (SSL) methods is far from real-world application since they do not consider (1) class imbalance and (2) class distribution mismatch between labeled and unlabeled data. This paper addresses such a relatively under-explored problem, imbalanced semi-supervised learning, where heavily biased pseudo-labels can harm the model performance. Interestingly, we find that the semantic pseudo-labels from a similarity-based classifier in feature space and the traditional pseudo-labels from the linear classifier show the complementary property. To this end, we propose a general pseudo-labeling framework to address the bias motivated by this observation. The key idea is to class-adaptively blend the semantic pseudo-label to the linear one, depending on the current pseudo-label distribution. Thereby, the increased semantic pseudo-label component suppresses the false positives in the majority classes and vice versa. We term the novel pseudo-labeling framework for imbalanced SSL as Distribution-Aware Semantics-Oriented (DASO) Pseudo-label. Extensive evaluation on CIFAR10/100-LT and STL10-LT shows that DASO consistently outperforms both recently proposed re-balancing methods for label and pseudo-label. Moreover, we demonstrate that typical SSL algorithms can effectively benefit from unlabeled data with DASO, especially when (1) class imbalance and (2) class distribution mismatch exist and even on recent real-world Semi-Aves benchmark.

25.A Dataset And Benchmark Of Underwater Object Detection For Robot Picking ⬇️

Underwater object detection for robot picking has attracted a lot of interest. However, it is still an unsolved problem due to several challenges. We take steps towards making it more realistic by addressing the following challenges. Firstly, the currently available datasets basically lack the test set annotations, causing researchers must compare their method with other SOTAs on a self-divided test set (from the training set). Training other methods lead to an increase in workload and different researchers divide different datasets, resulting there is no unified benchmark to compare the performance of different algorithms. Secondly, these datasets also have other shortcomings, e.g., too many similar images or incomplete labels. Towards these challenges we introduce a dataset, Detecting Underwater Objects (DUO), and a corresponding benchmark, based on the collection and re-annotation of all relevant datasets. DUO contains a collection of diverse underwater images with more rational annotations. The corresponding benchmark provides indicators of both efficiency and accuracy of SOTAs (under the MMDtection framework) for academic research and industrial applications, where JETSON AGX XAVIER is used to assess detector speed to simulate the robot-embedded environment.

26.Adaptive Streaming Perception using Deep Reinforcement Learning ⬇️

Executing computer vision models on streaming visual data, or streaming perception is an emerging problem, with applications in self-driving, embodied agents, and augmented/virtual reality. The development of such systems is largely governed by the accuracy and latency of the processing pipeline. While past work has proposed numerous approximate execution frameworks, their decision functions solely focus on optimizing latency, accuracy, or energy, etc. This results in sub-optimum decisions, affecting the overall system performance. We argue that the streaming perception systems should holistically maximize the overall system performance (i.e., considering both accuracy and latency simultaneously). To this end, we describe a new approach based on deep reinforcement learning to learn these tradeoffs at runtime for streaming perception. This tradeoff optimization is formulated as a novel deep contextual bandit problem and we design a new reward function that holistically integrates latency and accuracy into a single metric. We show that our agent can learn a competitive policy across multiple decision dimensions, which outperforms state-of-the-art policies on public datasets.

27.To The Point: Correspondence-driven monocular 3D category reconstruction ⬇️

We present To The Point (TTP), a method for reconstructing 3D objects from a single image using 2D to 3D correspondences learned from weak supervision. We recover a 3D shape from a 2D image by first regressing the 2D positions corresponding to the 3D template vertices and then jointly estimating a rigid camera transform and non-rigid template deformation that optimally explain the 2D positions through the 3D shape projection. By relying on 3D-2D correspondences we use a simple per-sample optimization problem to replace CNN-based regression of camera pose and non-rigid deformation and thereby obtain substantially more accurate 3D reconstructions. We treat this optimization as a differentiable layer and train the whole system in an end-to-end manner. We report systematic quantitative improvements on multiple categories and provide qualitative results comprising diverse shape, pose and texture prediction examples. Project website: this https URL.

28.Deep neural network loses attention to adversarial images ⬇️

Adversarial algorithms have shown to be effective against neural networks for a variety of tasks. Some adversarial algorithms perturb all the pixels in the image minimally for the image classification task in image classification. In contrast, some algorithms perturb few pixels strongly. However, very little information is available regarding why these adversarial samples so diverse from each other exist. Recently, Vargas et al. showed that the existence of these adversarial samples might be due to conflicting saliency within the neural network. We test this hypothesis of conflicting saliency by analysing the Saliency Maps (SM) and Gradient-weighted Class Activation Maps (Grad-CAM) of original and few different types of adversarial samples. We also analyse how different adversarial samples distort the attention of the neural network compared to original samples. We show that in the case of Pixel Attack, perturbed pixels either calls the network attention to themselves or divert the attention from them. Simultaneously, the Projected Gradient Descent Attack perturbs pixels so that intermediate layers inside the neural network lose attention for the correct class. We also show that both attacks affect the saliency map and activation maps differently. Thus, shedding light on why some defences successful against some attacks remain vulnerable against other attacks. We hope that this analysis will improve understanding of the existence and the effect of adversarial samples and enable the community to develop more robust neural networks.

29.MST: Masked Self-Supervised Transformer for Visual Representation ⬇️

Transformer has been widely used for self-supervised pre-training in Natural Language Processing (NLP) and achieved great success. However, it has not been fully explored in visual self-supervised learning. Meanwhile, previous methods only consider the high-level feature and learning representation from a global perspective, which may fail to transfer to the downstream dense prediction tasks focusing on local features. In this paper, we present a novel Masked Self-supervised Transformer approach named MST, which can explicitly capture the local context of an image while preserving the global semantic information. Specifically, inspired by the Masked Language Modeling (MLM) in NLP, we propose a masked token strategy based on the multi-head self-attention map, which dynamically masks some tokens of local patches without damaging the crucial structure for self-supervised learning. More importantly, the masked tokens together with the remaining tokens are further recovered by a global image decoder, which preserves the spatial information of the image and is more friendly to the downstream dense prediction tasks. The experiments on multiple datasets demonstrate the effectiveness and generality of the proposed method. For instance, MST achieves Top-1 accuracy of 76.9% with DeiT-S only using 300-epoch pre-training by linear evaluation, which outperforms supervised methods with the same epoch by 0.4% and its comparable variant DINO by 1.0%. For dense prediction tasks, MST also achieves 42.7% mAP on MS COCO object detection and 74.04% mIoU on Cityscapes segmentation only with 100-epoch pre-training.

30.Date Estimation in the Wild of Scanned Historical Photos: An Image Retrieval Approach ⬇️

This paper presents a novel method for date estimation of historical photographs from archival sources. The main contribution is to formulate the date estimation as a retrieval task, where given a query, the retrieved images are ranked in terms of the estimated date similarity. The closer are their embedded representations the closer are their dates. Contrary to the traditional models that design a neural network that learns a classifier or a regressor, we propose a learning objective based on the nDCG ranking metric. We have experimentally evaluated the performance of the method in two different tasks: date estimation and date-sensitive image retrieval, using the DEW public database, overcoming the baseline methods.

31.SVMA: A GAN-based model for Monocular 3D Human Pose Estimation ⬇️

Recovering 3D human pose from 2D joints is a highly unconstrained problem, especially without any video or multi-view information. We present an unsupervised GAN-based model to recover 3D human pose from 2D joint locations extracted from a single image. Our model uses a GAN to learn the mapping of distribution from 2D poses to 3D poses, not the simple 2D-3D correspondence. Considering the reprojection constraint, our model can estimate the camera so that we can reproject the estimated 3D pose to the original 2D pose. Based on this reprojection method, we can rotate and reproject the generated pose to get our "new" 2D pose and then use a weight sharing generator to estimate the "new" 3D pose and a "new" camera. Through the above estimation process, we can define the single-view-multi-angle consistency loss during training to simulate multi-view consistency, which means the 3D poses and cameras estimated from two angles of a single view should be able to be mixed to generate rich 2D reprojections, and the 2D reprojections reprojected from the same 3D pose should be consistent. The experimental results on Human3.6M show that our method outperforms all the state-of-the-art methods, and results on MPI-INF-3DHP show that our method outperforms state-of-the-art by approximately 15.0%.

32.Context-Free TextSpotter for Real-Time and Mobile End-to-End Text Detection and Recognition ⬇️

In the deployment of scene-text spotting systems on mobile platforms, lightweight models with low computation are preferable. In concept, end-to-end (E2E) text spotting is suitable for such purposes because it performs text detection and recognition in a single model. However, current state-of-the-art E2E methods rely on heavy feature extractors, recurrent sequence modellings, and complex shape aligners to pursue accuracy, which means their computations are still heavy. We explore the opposite direction: How far can we go without bells and whistles in E2E text spotting? To this end, we propose a text-spotting method that consists of simple convolutions and a few post-processes, named Context-Free TextSpotter. Experiments using standard benchmarks show that Context-Free TextSpotter achieves real-time text spotting on a GPU with only three million parameters, which is the smallest and fastest among existing deep text spotters, with an acceptable transcription quality degradation compared to heavier ones. Further, we demonstrate that our text spotter can run on a smartphone with affordable latency, which is valuable for building stand-alone OCR applications.

33.Spatially Invariant Unsupervised 3D Object Segmentation with Graph Neural Networks ⬇️

In this paper, we tackle the problem of unsupervised 3D object segmentation from a point cloud without RGB information. In particular, we propose a framework,{\bf SPAIR3D}, to model a point cloud as a spatial mixture model and jointly learn the multiple-object representation and segmentation in 3D via Variational Autoencoders (VAE). Inspired by SPAIR, we adopt an object-specification scheme that describes each object's location relative to its local voxel grid cell rather than the point cloud as a whole. To model the spatial mixture model on point clouds, we derive the\emph{Chamfer Likelihood}, which fits naturally into the variational training pipeline. We further design a new spatially invariant graph neural network to generate a varying number of 3D points as a decoder within our VAE.Experimental results demonstrate that{\bf SPAIR3D} is capable of detecting and segmenting variable number of objects without appearance information across diverse scenes.

34.MiDeCon: Unsupervised and Accurate Fingerprint and Minutia Quality Assessment based on Minutia Detection Confidence ⬇️

An essential factor to achieve high accuracies in fingerprint recognition systems is the quality of its samples. Previous works mainly proposed supervised solutions based on image properties that neglects the minutiae extraction process, despite that most fingerprint recognition techniques are based on detected minutiae. Consequently, a fingerprint image might be assigned a high quality even if the utilized minutia extractor produces unreliable information. In this work, we propose a novel concept of assessing minutia and fingerprint quality based on minutia detection confidence (MiDeCon). MiDeCon can be applied to an arbitrary deep learning based minutia extractor and does not require quality labels for learning. We propose using the detection reliability of the extracted minutia as its quality indicator. By combining the highest minutia qualities, MiDeCon also accurately determines the quality of a full fingerprint. Experiments are conducted on the publicly available databases of the FVC 2006 and compared against several baselines, such as NIST's widely-used fingerprint image quality software NFIQ1 and NFIQ2. The results demonstrate a significantly stronger quality assessment performance of the proposed MiDeCon-qualities as related works on both, minutia- and fingerprint-level. The implementation is publicly available.

35.Supervising the Transfer of Reasoning Patterns in VQA ⬇️

Methods for Visual Question Anwering (VQA) are notorious for leveraging dataset biases rather than performing reasoning, hindering generalization. It has been recently shown that better reasoning patterns emerge in attention layers of a state-of-the-art VQA model when they are trained on perfect (oracle) visual inputs. This provides evidence that deep neural networks can learn to reason when training conditions are favorable enough. However, transferring this learned knowledge to deployable models is a challenge, as much of it is lost during the transfer. We propose a method for knowledge transfer based on a regularization term in our loss function, supervising the sequence of required reasoning operations. We provide a theoretical analysis based on PAC-learning, showing that such program prediction can lead to decreased sample complexity under mild hypotheses. We also demonstrate the effectiveness of this approach experimentally on the GQA dataset and show its complementarity to BERT-like self-supervised pre-training.

36.Multi-Dataset Benchmarks for Masked Identification using Contrastive Representation Learning ⬇️

The COVID-19 pandemic has drastically changed accepted norms globally. Within the past year, masks have been used as a public health response to limit the spread of the virus. This sudden change has rendered many face recognition based access control, authentication and surveillance systems ineffective. Official documents such as passports, driving license and national identity cards are enrolled with fully uncovered face images. However, in the current global situation, face matching systems should be able to match these reference images with masked face images. As an example, in an airport or security checkpoint it is safer to match the unmasked image of the identifying document to the masked person rather than asking them to remove the mask. We find that current facial recognition techniques are not robust to this form of occlusion.
To address this unique requirement presented due to the current circumstance, we propose a set of re-purposed datasets and a benchmark for researchers to use. We also propose a contrastive visual representation learning based pre-training workflow which is specialized to masked vs unmasked face matching. We ensure that our method learns robust features to differentiate people across varying data collection scenarios. We achieve this by training over many different datasets and validating our result by testing on various holdout datasets. The specialized weights trained by our method outperform standard face recognition features for masked to unmasked face matching. We believe the provided synthetic mask generating code, our novel training approach and the trained weights from the masked face models will help in adopting existing face recognition systems to operate in the current global environment. We open-source all contributions for broader use by the research community.

37.Progressive Stage-wise Learning for Unsupervised Feature Representation Enhancement ⬇️

Unsupervised learning methods have recently shown their competitiveness against supervised training. Typically, these methods use a single objective to train the entire network. But one distinct advantage of unsupervised over supervised learning is that the former possesses more variety and freedom in designing the objective. In this work, we explore new dimensions of unsupervised learning by proposing the Progressive Stage-wise Learning (PSL) framework. For a given unsupervised task, we design multilevel tasks and define different learning stages for the deep network. Early learning stages are forced to focus on lowlevel tasks while late stages are guided to extract deeper information through harder tasks. We discover that by progressive stage-wise learning, unsupervised feature representation can be effectively enhanced. Our extensive experiments show that PSL consistently improves results for the leading unsupervised learning methods.

38.Validation of Simulation-Based Testing: Bypassing Domain Shift with Label-to-Image Synthesis ⬇️

Many machine learning applications can benefit from simulated data for systematic validation - in particular if real-life data is difficult to obtain or annotate. However, since simulations are prone to domain shift w.r.t. real-life data, it is crucial to verify the transferability of the obtained results. We propose a novel framework consisting of a generative label-to-image synthesis model together with different transferability measures to inspect to what extent we can transfer testing results of semantic segmentation models from synthetic data to equivalent real-life data. With slight modifications, our approach is extendable to, e.g., general multi-class classification tasks. Grounded on the transferability analysis, our approach additionally allows for extensive testing by incorporating controlled simulations. We validate our approach empirically on a semantic segmentation task on driving scenes. Transferability is tested using correlation analysis of IoU and a learned discriminator. Although the latter can distinguish between real-life and synthetic tests, in the former we observe surprisingly strong correlations of 0.7 for both cars and pedestrians.

39.Super-Resolution Image Reconstruction Based on Self-Calibrated Convolutional GAN ⬇️

With the effective application of deep learning in computer vision, breakthroughs have been made in the research of super-resolution images reconstruction. However, many researches have pointed out that the insufficiency of the neural network extraction on image features may bring the deteriorating of newly reconstructed image. On the other hand, the generated pictures are sometimes too artificial because of over-smoothing. In order to solve the above problems, we propose a novel self-calibrated convolutional generative adversarial networks. The generator consists of feature extraction and image reconstruction. Feature extraction uses self-calibrated convolutions, which contains four portions, and each portion has specific functions. It can not only expand the range of receptive fields, but also obtain long-range spatial and inter-channel dependencies. Then image reconstruction is performed, and finally a super-resolution image is reconstructed. We have conducted thorough experiments on different datasets including set5, set14 and BSD100 under the SSIM evaluation method. The experimental results prove the effectiveness of the proposed network.

40.DUET: Detection Utilizing Enhancement for Text in Scanned or Captured Documents ⬇️

We present a novel deep neural model for text detection in document images. For robust text detection in noisy scanned documents, the advantages of multi-task learning are adopted by adding an auxiliary task of text enhancement. Namely, our proposed model is designed to perform noise reduction and text region enhancement as well as text detection. Moreover, we enrich the training data for the model with synthesized document images that are fully labeled for text detection and enhancement, thus overcome the insufficiency of labeled document image data. For the effective exploitation of the synthetic and real data, the training process is separated in two phases. The first phase is training only synthetic data in a fully-supervised manner. Then real data with only detection labels are added in the second phase. The enhancement task for the real data is weakly-supervised with information from their detection labels. Our methods are demonstrated in a real document dataset with performances exceeding those of other text detection methods. Moreover, ablations are conducted and the results confirm the effectiveness of the synthetic data, auxiliary task, and weak-supervision. Whereas the existing text detection studies mostly focus on the text in scenes, our proposed method is optimized to the applications for the text in scanned documents.

41.Cross-domain Contrastive Learning for Unsupervised Domain Adaptation ⬇️

Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a fully-labeled source domain to a different unlabeled target domain. Most existing UDA methods learn domain-invariant feature representations by minimizing feature distances across domains. In this work, we build upon contrastive self-supervised learning to align features so as to reduce the domain discrepancy between training and testing sets. Exploring the same set of categories shared by both domains, we introduce a simple yet effective framework CDCL, for domain alignment. In particular, given an anchor image from one domain, we minimize its distances to cross-domain samples from the same class relative to those from different categories. Since target labels are unavailable, we use a clustering-based approach with carefully initialized centers to produce pseudo labels. In addition, we demonstrate that CDCL is a general framework and can be adapted to the data-free setting, where the source data are unavailable during training, with minimal modification. We conduct experiments on two widely used domain adaptation benchmarks, i.e., Office-31 and VisDA-2017, and demonstrate that CDCL achieves state-of-the-art performance on both datasets.

42.Consistent Instance False Positive Improves Fairness in Face Recognition ⬇️

Demographic bias is a significant challenge in practical face recognition systems. Existing methods heavily rely on accurate demographic annotations. However, such annotations are usually unavailable in real scenarios. Moreover, these methods are typically designed for a specific demographic group and are not general enough. In this paper, we propose a false positive rate penalty loss, which mitigates face recognition bias by increasing the consistency of instance False Positive Rate (FPR). Specifically, we first define the instance FPR as the ratio between the number of the non-target similarities above a unified threshold and the total number of the non-target similarities. The unified threshold is estimated for a given total FPR. Then, an additional penalty term, which is in proportion to the ratio of instance FPR overall FPR, is introduced into the denominator of the softmax-based loss. The larger the instance FPR, the larger the penalty. By such unequal penalties, the instance FPRs are supposed to be consistent. Compared with the previous debiasing methods, our method requires no demographic annotations. Thus, it can mitigate the bias among demographic groups divided by various attributes, and these attributes are not needed to be previously predefined during training. Extensive experimental results on popular benchmarks demonstrate the superiority of our method over state-of-the-art competitors. Code and trained models are available at this https URL.

43.Learning to Affiliate: Mutual Centralized Learning for Few-shot Classification ⬇️

Few-shot learning (FSL) aims to learn a classifier that can be easily adapted to accommodate new tasks not seen during training, given only a few examples. To handle the limited-data problem in few-shot regimes, recent methods tend to collectively use a set of local features to densely represent an image instead of using a mixed global feature. They generally explore a unidirectional query-to-support paradigm in FSL, e.g., find the nearest/optimal support feature for each query feature and aggregate these local matches for a joint classification. In this paper, we propose a new method Mutual Centralized Learning (MCL) to fully affiliate the two disjoint sets of dense features in a bidirectional paradigm. We associate each local feature with a particle that can bidirectionally random walk in a discrete feature space by the affiliations. To estimate the class probability, we propose the features' accessibility that measures the expected number of visits to the support features of that class in a Markov process. We relate our method to learning a centrality on an affiliation network and demonstrate its capability to be plugged in existing methods by highlighting centralized local features. Experiments show that our method achieves the state-of-the-art on both miniImageNet and tieredImageNet.

44.AFAN: Augmented Feature Alignment Network for Cross-Domain Object Detection ⬇️

Unsupervised domain adaptation for object detection is a challenging problem with many real-world applications. Unfortunately, it has received much less attention than supervised object detection. Models that try to address this task tend to suffer from a shortage of annotated training samples. Moreover, existing methods of feature alignments are not sufficient to learn domain-invariant representations. To address these limitations, we propose a novel augmented feature alignment network (AFAN) which integrates intermediate domain image generation and domain-adversarial training into a unified framework. An intermediate domain image generator is proposed to enhance feature alignments by domain-adversarial training with automatically generated soft domain labels. The synthetic intermediate domain images progressively bridge the domain divergence and augment the annotated source domain training data. A feature pyramid alignment is designed and the corresponding feature discriminator is used to align multi-scale convolutional features of different semantic levels. Last but not least, we introduce a region feature alignment and an instance discriminator to learn domain-invariant features for object proposals. Our approach significantly outperforms the state-of-the-art methods on standard benchmarks for both similar and dissimilar domain adaptations. Further extensive experiments verify the effectiveness of each component and demonstrate that the proposed network can learn domain-invariant representations.

45.RLCorrector: Reinforced Proofreading for Connectomics Image Segmentation ⬇️

The segmentation of nanoscale electron microscopy (EM) images is crucial but challenging in connectomics. Recent advances in deep learning have demonstrated the significant potential of automatic segmentation for tera-scale EM images. However, none of the existing segmentation methods are error-free, and they require proofreading, which is typically implemented as an interactive, semi-automatic process via manual intervention. Herein, we propose a fully automatic proofreading method based on reinforcement learning. The main idea is to model the human decision process in proofreading using a reinforcement agent to achieve fully automatic proofreading. We systematically design the proposed system by combining multiple reinforcement learning agents in a hierarchical manner, where each agent focuses only on a specific task while preserving dependency between agents. Furthermore, we also demonstrate that the episodic task setting of reinforcement learning can efficiently manage a combination of merge and split errors concurrently presented in the input. We demonstrate the efficacy of the proposed system by comparing it with state-of-the-art proofreading methods using various testing examples.

46.Joint Landmark and Structure Learning for Automatic Evaluation of Developmental Dysplasia of the Hip ⬇️

The ultrasound (US) screening of the infant hip is vital for the early diagnosis of developmental dysplasia of the hip (DDH). The US diagnosis of DDH refers to measuring alpha and beta angles that quantify hip joint development. These two angles are calculated from key anatomical landmarks and structures of the hip. However, this measurement process is not trivial for sonographers and usually requires a thorough understanding of complex anatomical structures. In this study, we propose a multi-task framework to learn the relationships among landmarks and structures jointly and automatically evaluate DDH. Our multi-task networks are equipped with three novel modules. Firstly, we adopt Mask R-CNN as the basic framework to detect and segment key anatomical structures and add one landmark detection branch to form a new multi-task framework. Secondly, we propose a novel shape similarity loss to refine the incomplete anatomical structure prediction robustly and accurately. Thirdly, we further incorporate the landmark-structure consistent prior to ensure the consistency of the bony rim estimated from the segmented structure and the detected landmark. In our experiments, 1,231 US images of the infant hip from 632 patients are collected, of which 247 images from 126 patients are tested. The average errors in alpha and beta angles are 2.221 degrees and 2.899 degrees. About 93% and 85% estimates of alpha and beta angles have errors less than 5 degrees, respectively. Experimental results demonstrate that the proposed method can accurately and robustly realize the automatic evaluation of DDH, showing great potential for clinical application.

47.Improving White-box Robustness of Pre-processing Defenses via Joint Adversarial Training ⬇️

Deep neural networks (DNNs) are vulnerable to adversarial noise. A range of adversarial defense techniques have been proposed to mitigate the interference of adversarial noise, among which the input pre-processing methods are scalable and show great potential to safeguard DNNs. However, pre-processing methods may suffer from the robustness degradation effect, in which the defense reduces rather than improving the adversarial robustness of a target model in a white-box setting. A potential cause of this negative effect is that adversarial training examples are static and independent to the pre-processing model. To solve this problem, we investigate the influence of full adversarial examples which are crafted against the full model, and find they indeed have a positive impact on the robustness of defenses. Furthermore, we find that simply changing the adversarial training examples in pre-processing methods does not completely alleviate the robustness degradation effect. This is due to the adversarial risk of the pre-processed model being neglected, which is another cause of the robustness degradation effect. Motivated by above analyses, we propose a method called Joint Adversarial Training based Pre-processing (JATP) defense. Specifically, we formulate a feature similarity based adversarial risk for the pre-processing model by using full adversarial examples found in a feature space. Unlike standard adversarial training, we only update the pre-processing model, which prompts us to introduce a pixel-wise loss to improve its cross-model transferability. We then conduct a joint adversarial training on the pre-processing model to minimize this overall risk. Empirical results show that our method could effectively mitigate the robustness degradation effect across different target models in comparison to previous state-of-the-art approaches.

48.Unsupervised Video Person Re-identification via Noise and Hard frame Aware Clustering ⬇️

Unsupervised video-based person re-identification (re-ID) methods extract richer features from video tracklets than image-based ones. The state-of-the-art methods utilize clustering to obtain pseudo-labels and train the models iteratively. However, they underestimate the influence of two kinds of frames in the tracklet: 1) noise frames caused by detection errors or heavy occlusions exist in the tracklet, which may be allocated with unreliable labels during clustering; 2) the tracklet also contains hard frames caused by pose changes or partial occlusions, which are difficult to distinguish but informative. This paper proposes a Noise and Hard frame Aware Clustering (NHAC) method. NHAC consists of a graph trimming module and a node re-sampling module. The graph trimming module obtains stable graphs by removing noise frame nodes to improve the clustering accuracy. The node re-sampling module enhances the training of hard frame nodes to learn rich tracklet information. Experiments conducted on two video-based datasets demonstrate the effectiveness of the proposed NHAC under the unsupervised re-ID setting.

49.Cross-Modal Discrete Representation Learning ⬇️

Recent advances in representation learning have demonstrated an ability to represent information from different modalities such as video, text, and audio in a single high-level embedding vector. In this work we present a self-supervised learning framework that is able to learn a representation that captures finer levels of granularity across different modalities such as concepts or events represented by visual objects or spoken words. Our framework relies on a discretized embedding space created via vector quantization that is shared across different modalities. Beyond the shared embedding space, we propose a Cross-Modal Code Matching objective that forces the representations from different views (modalities) to have a similar distribution over the discrete embedding space such that cross-modal objects/actions localization can be performed without direct supervision. In our experiments we show that the proposed discretized multi-modal fine-grained representation (e.g., pixel/word/frame) can complement high-level summary representations (e.g., video/sentence/waveform) for improved performance on cross-modal retrieval tasks. We also observe that the discretized representation uses individual clusters to represent the same semantic concept across modalities.

50.Very Compact Clusters with Structural Regularization via Similarity and Connectivity ⬇️

Clustering algorithms have significantly improved along with Deep Neural Networks which provide effective representation of data. Existing methods are built upon deep autoencoder and self-training process that leverages the distribution of cluster assignments of samples. However, as the fundamental objective of the autoencoder is focused on efficient data reconstruction, the learnt space may be sub-optimal for clustering. Moreover, it requires highly effective codes (i.e., representation) of data, otherwise the initial cluster centers often cause stability issues during self-training. Many state-of-the-art clustering algorithms use convolution operation to extract efficient codes but their applications are limited to image data. In this regard, we propose an end-to-end deep clustering algorithm, i.e., Very Compact Clusters (VCC), for the general datasets, which takes advantage of distributions of local relationships of samples near the boundary of clusters, so that they can be properly separated and pulled to cluster centers to form compact clusters. Experimental results on various datasets illustrate that our proposed approach achieves better clustering performance over most of the state-of-the-art clustering methods, and the data embeddings learned by VCC without convolution for image data are even comparable with specialized convolutional methods.

51.Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers ⬇️

In video transformers, the time dimension is often treated in the same way as the two spatial dimensions. However, in a scene where objects or the camera may move, a physical point imaged at one location in frame $t$ may be entirely unrelated to what is found at that location in frame $t+k$. These temporal correspondences should be modeled to facilitate learning about dynamic scenes. To this end, we propose a new drop-in block for video transformers -- trajectory attention -- that aggregates information along implicitly determined motion paths. We additionally propose a new method to address the quadratic dependence of computation and memory on the input size, which is particularly important for high resolution or long videos. While these ideas are useful in a range of settings, we apply them to the specific task of video action recognition with a transformer model and obtain state-of-the-art results on the Kinetics, Something--Something V2, and Epic-Kitchens datasets. Code and models are available at: this https URL

52.Plan2Scene: Converting Floorplans to 3D Scenes ⬇️

We address the task of converting a floorplan and a set of associated photos of a residence into a textured 3D mesh model, a task which we call Plan2Scene. Our system 1) lifts a floorplan image to a 3D mesh model; 2) synthesizes surface textures based on the input photos; and 3) infers textures for unobserved surfaces using a graph neural network architecture. To train and evaluate our system we create indoor surface texture datasets, and augment a dataset of floorplans and photos from prior work with rectified surface crops and additional annotations. Our approach handles the challenge of producing tileable textures for dominant surfaces such as floors, walls, and ceilings from a sparse set of unaligned photos that only partially cover the residence. Qualitative and quantitative evaluations show that our system produces realistic 3D interior models, outperforming baseline approaches on a suite of texture quality metrics and as measured by a holistic user study.

53.Match What Matters: Generative Implicit Feature Replay for Continual Learning ⬇️

Neural networks are prone to catastrophic forgetting when trained incrementally on different tasks. In order to prevent forgetting, most existing methods retain a small subset of previously seen samples, which in turn can be used for joint training with new tasks. While this is indeed effective, it may not always be possible to store such samples, e.g., due to data protection regulations. In these cases, one can instead employ generative models to create artificial samples or features representing memories from previous tasks. Following a similar direction, we propose GenIFeR (Generative Implicit Feature Replay) for class-incremental learning. The main idea is to train a generative adversarial network (GAN) to generate images that contain realistic features. While the generator creates images at full resolution, the discriminator only sees the corresponding features extracted by the continually trained classifier. Since the classifier compresses raw images into features that are actually relevant for classification, the GAN can match this target distribution more accurately. On the other hand, allowing the generator to create full resolution images has several benefits: In contrast to previous approaches, the feature extractor of the classifier does not have to be frozen. In addition, we can employ augmentations on generated images, which not only boosts classification performance, but also mitigates discriminator overfitting during GAN training. We empirically show that GenIFeR is superior to both conventional generative image and feature replay. In particular, we significantly outperform the state-of-the-art in generative replay for various settings on the CIFAR-100 and CUB-200 datasets.

54.Tensor feature hallucination for few-shot learning ⬇️

Few-shot classification addresses the challenge of classifying examples given not just limited supervision but limited data as well. An attractive solution is synthetic data generation. However, most such methods are overly sophisticated, focusing on high-quality, realistic data in the input space. It is unclear whether adapting them to the few-shot regime and using them for the downstream task of classification is the right approach. Previous works on synthetic data generation for few-shot classification focus on exploiting complex models, e.g. a Wasserstein GAN with multiple regularizers or a network that transfers latent diversities from known to novel classes.
We follow a different approach and investigate how a simple and straightforward synthetic data generation method can be used effectively. We make two contributions, namely we show that: (1) using a simple loss function is more than enough for training a feature generator in the few-shot setting; and (2) learning to generate tensor features instead of vector features is superior. Extensive experiments on miniImagenet, CUB and CIFAR-FS datasets show that our method sets a new state of the art, outperforming more sophisticated few-shot data augmentation methods.

55.Raman spectral analysis of mixtures with one-dimensional convolutional neural network ⬇️

Recently, the combination of robust one-dimensional convolutional neural networks (1-D CNNs) and Raman spectroscopy has shown great promise in rapid identification of unknown substances with good accuracy. Using this technique, researchers can recognize a pure compound and distinguish it from unknown substances in a mixture. The novelty of this approach is that the trained neural network operates automatically without any pre- or post-processing of data. Some studies have attempted to extend this technique to the classification of pure compounds in an unknown mixture. However, the application of 1-D CNNs has typically been restricted to binary classifications of pure compounds. Here we will highlight a new approach in spectral recognition and quantification of chemical components in a multicomponent mixture. Two 1-D CNN models, RaMixNet I and II, have been developed for this purpose. The former is for rapid classification of components in a mixture while the latter is for quantitative determination of those constituents. In the proposed method, there is no limit to the number of compounds in a mixture. A data augmentation method is also introduced by adding random baselines to the Raman spectra. The experimental results revealed that the classification accuracy of RaMixNet I and II is 100% for analysis of unknown test mixtures; at the same time, the RaMixNet II model may achieve a regression accuracy of 88% for the quantification of each component.

56.Visual Sensor Pose Optimisation Using Rendering-based Visibility Models for Robust Cooperative Perception ⬇️

Visual Sensor Networks can be used in a variety of perception applications such as infrastructure support for autonomous driving in complex road segments. The pose of the sensors in such networks directly determines the coverage of the environment and objects therein, which impacts the performance of applications such as object detection and tracking. Existing sensor pose optimisation methods in the literature either maximise the coverage of ground surfaces, or consider the visibility of the target objects as binary variables, which cannot represent various degrees of visibility. Such formulations cannot guarantee the visibility of the target objects as they fail to consider occlusions. This paper proposes two novel sensor pose optimisation methods, based on gradient-ascent and Integer Programming techniques, which maximise the visibility of multiple target objects in cluttered environments. Both methods consider a realistic visibility model based on a rendering engine that provides pixel-level visibility information about the target objects. The proposed methods are evaluated in a complex environment and compared to existing methods in the literature. The evaluation results indicate that explicitly modelling the visibility of target objects is critical to avoid occlusions in cluttered environments. Furthermore, both methods significantly outperform existing methods in terms of object visibility.

57.Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline ⬇️

Processing point cloud data is an important component of many real-world systems. As such, a wide variety of point-based approaches have been proposed, reporting steady benchmark improvements over time. We study the key ingredients of this progress and uncover two critical results. First, we find that auxiliary factors like different evaluation schemes, data augmentation strategies, and loss functions, which are independent of the model architecture, make a large difference in performance. The differences are large enough that they obscure the effect of architecture. When these factors are controlled for, PointNet++, a relatively older network, performs competitively with recent methods. Second, a very simple projection-based method, which we refer to as SimpleView, performs surprisingly well. It achieves on par or better results than sophisticated state-of-the-art methods on ModelNet40 while being half the size of PointNet++. It also outperforms state-of-the-art methods on ScanObjectNN, a real-world point cloud benchmark, and demonstrates better cross-dataset generalization. Code is available at this https URL.

58.ImaginE: An Imagination-Based Automatic Evaluation Metric for Natural Language Generation ⬇️

Automatic evaluations for natural language generation (NLG) conventionally rely on token-level or embedding-level comparisons with the text references. This is different from human language processing, for which visual imaginations often improve comprehension. In this work, we propose ImaginE, an imagination-based automatic evaluation metric for natural language generation. With the help of CLIP and DALL-E, two cross-modal models pre-trained on large-scale image-text pairs, we automatically generate an image as the embodied imagination for the text snippet and compute the imagination similarity using contextual embeddings. Experiments spanning several text generation tasks demonstrate that adding imagination with our ImaginE displays great potential in introducing multi-modal information into NLG evaluation, and improves existing automatic metrics' correlations with human similarity judgments in many circumstances.

59.Beyond BatchNorm: Towards a General Understanding of Normalization in Deep Learning ⬇️

Inspired by BatchNorm, there has been an explosion of normalization layers in deep learning. Recent works have identified a multitude of beneficial properties in BatchNorm to explain its success. However, given the pursuit of alternative normalization techniques, these properties need to be generalized so that any given layer's success/failure can be accurately predicted. In this work, we take a first step towards this goal by extending known properties of BatchNorm in randomly initialized deep neural networks (DNNs) to nine recently proposed normalization layers. Our primary findings follow: (i) Similar to BatchNorm, activations-based normalization layers can avoid exploding activations in ResNets; (ii) Use of GroupNorm ensures rank of activations is at least $\Omega(\sqrt{\frac{\text{width}}{\text{Group Size}}})$, thus explaining why LayerNorm witnesses slow optimization speed; (iii) Small group sizes result in large gradient norm in earlier layers, hence justifying training instability issues in Instance Normalization and illustrating a speed-stability tradeoff in GroupNorm. Overall, our analysis reveals several general mechanisms that explain the success of normalization techniques in deep learning, providing us with a compass to systematically explore the vast design space of DNN normalization layers.

60.Deciphering Implicit Hate: Evaluating Automated Detection Algorithms for Multimodal Hate ⬇️

Accurate detection and classification of online hate is a difficult task. Implicit hate is particularly challenging as such content tends to have unusual syntax, polysemic words, and fewer markers of prejudice (e.g., slurs). This problem is heightened with multimodal content, such as memes (combinations of text and images), as they are often harder to decipher than unimodal content (e.g., text alone). This paper evaluates the role of semantic and multimodal context for detecting implicit and explicit hate. We show that both text- and visual- enrichment improves model performance, with the multimodal model (0.771) outperforming other models' F1 scores (0.544, 0.737, and 0.754). While the unimodal-text context-aware (transformer) model was the most accurate on the subtask of implicit hate detection, the multimodal model outperformed it overall because of a lower propensity towards false positives. We find that all models perform better on content with full annotator agreement and that multimodal models are best at classifying the content where annotators disagree. To conduct these investigations, we undertook high-quality annotation of a sample of 5,000 multimodal entries. Tweets were annotated for primary category, modality, and strategy. We make this corpus, along with the codebook, code, and final model, freely available.

61.CoviLearn: A Machine Learning Integrated Smart X-Ray Device in Healthcare Cyber-Physical System for Automatic Initial Screening of COVID-19 ⬇️

The pandemic of novel Coronavirus Disease 2019 (COVID-19) is widespread all over the world causing serious health problems as well as serious impact on the global economy. Reliable and fast testing of the COVID-19 has been a challenge for researchers and healthcare practitioners. In this work we present a novel machine learning (ML) integrated X-ray device in Healthcare Cyber-Physical System (H-CPS) or smart healthcare framework (called CoviLearn) to allow healthcare practitioners to perform automatic initial screening of COVID-19 patients. We propose convolutional neural network (CNN) models of X-ray images integrated into an X-ray device for automatic COVID-19 detection. The proposed CoviLearn device will be useful in detecting if a person is COVID-19 positive or negative by considering the chest X-ray image of individuals. CoviLearn will be useful tool doctors to detect potential COVID-19 infections instantaneously without taking more intrusive healthcare data samples, such as saliva and blood. COVID-19 attacks the endothelium tissues that support respiratory tract, X-rays images can be used to analyze the health of a patient lungs. As all healthcare centers have X-ray machines, it could be possible to use proposed CoviLearn X-rays to test for COVID-19 without the especial test kits. Our proposed automated analysis system CoviLearn which has 99% accuracy will be able to save valuable time of medical professionals as the X-ray machines come with a drawback as it needed a radiology expert.

62.SemSegLoss: A python package of loss functions for semantic segmentation ⬇️

Image Segmentation has been an active field of research as it has a wide range of applications, ranging from automated disease detection to self-driving cars. In recent years, various research papers proposed different loss functions used in case of biased data, sparse segmentation, and unbalanced dataset. In this paper, we introduce SemSegLoss, a python package consisting of some of the well-known loss functions widely used for image segmentation. It is developed with the intent to help researchers in the development of novel loss functions and perform an extensive set of experiments on model architectures for various applications. The ease-of-use and flexibility of the presented package have allowed reducing the development time and increased evaluation strategies of machine learning models for semantic segmentation. Furthermore, different applications that use image segmentation can use SemSegLoss because of the generality of its functions. This wide range of applications will lead to the development and growth of AI across all industries.

63.Quantized Conditional COT-GAN for Video Prediction ⬇️

Causal Optimal Transport (COT) results from imposing a temporal causality constraint on classic optimal transport problems, which naturally generates a new concept of distances between distributions on path spaces. The first application of the COT theory for sequential learning was given in Xu et al. (2020), where COT-GAN was introduced as an adversarial algorithm to train implicit generative models optimized for producing sequential data. Relying on Xu et al. (2020), the contribution of the present paper is twofold. First, we develop a conditional version of COT-GAN suitable for sequence prediction. This means that the dataset is now used in order to learn how a sequence will evolve given the observation of its past evolution. Second, we improve on the convergence results by working with modifications of the empirical measures via a specific type of quantization due to Backhoff et al. (2020). The resulting quantized conditional COT-GAN algorithm is illustrated with an application for video prediction.

64.Hierarchical Agglomerative Graph Clustering in Nearly-Linear Time ⬇️

We study the widely used hierarchical agglomerative clustering (HAC) algorithm on edge-weighted graphs. We define an algorithmic framework for hierarchical agglomerative graph clustering that provides the first efficient $\tilde{O}(m)$ time exact algorithms for classic linkage measures, such as complete- and WPGMA-linkage, as well as other measures. Furthermore, for average-linkage, arguably the most popular variant of HAC, we provide an algorithm that runs in $\tilde{O}(n\sqrt{m})$ time. For this variant, this is the first exact algorithm that runs in subquadratic time, as long as $m=n^{2-\epsilon}$ for some constant $\epsilon > 0$. We complement this result with a simple $\epsilon$-close approximation algorithm for average-linkage in our framework that runs in $\tilde{O}(m)$ time. As an application of our algorithms, we consider clustering points in a metric space by first using $k$-NN to generate a graph from the point set, and then running our algorithms on the resulting weighted graph. We validate the performance of our algorithms on publicly available datasets, and show that our approach can speed up clustering of point datasets by a factor of 20.7--76.5x.

65.CALTeC: Content-Adaptive Linear Tensor Completion for Collaborative Intelligence ⬇️

In collaborative intelligence, an artificial intelligence (AI) model is typically split between an edge device and the cloud. Feature tensors produced by the edge sub-model are sent to the cloud via an imperfect communication channel. At the cloud side, parts of the feature tensor may be missing due to packet loss. In this paper we propose a method called Content-Adaptive Linear Tensor Completion (CALTeC) to recover the missing feature data. The proposed method is fast, data-adaptive, does not require pre-training, and produces better results than existing methods for tensor data recovery in collaborative intelligence.

66.3D Semantic Mapping from Arthroscopy using Out-of-distribution Pose and Depth and In-distribution Segmentation Training ⬇️

Minimally invasive surgery (MIS) has many documented advantages, but the surgeon's limited visual contact with the scene can be problematic. Hence, systems that can help surgeons navigate, such as a method that can produce a 3D semantic map, can compensate for the limitation above. In theory, we can borrow 3D semantic mapping techniques developed for robotics, but this requires finding solutions to the following challenges in MIS: 1) semantic segmentation, 2) depth estimation, and 3) pose estimation. In this paper, we propose the first 3D semantic mapping system from knee arthroscopy that solves the three challenges above. Using out-of-distribution non-human datasets, where pose could be labeled, we jointly train depth+pose estimators using selfsupervised and supervised losses. Using an in-distribution human knee dataset, we train a fully-supervised semantic segmentation system to label arthroscopic image pixels into femur, ACL, and meniscus. Taking testing images from human knees, we combine the results from these two systems to automatically create 3D semantic maps of the human knee. The result of this work opens the pathway to the generation of intraoperative 3D semantic mapping, registration with pre-operative data, and robotic-assisted arthroscopy

67.Data augmentation to improve robustness of image captioning solutions ⬇️

In this paper, we study the impact of motion blur, a common quality flaw in real world images, on a state-of-the-art two-stage image captioning solution, and notice a degradation in solution performance as blur intensity increases. We investigate techniques to improve the robustness of the solution to motion blur using training data augmentation at each or both stages of the solution, i.e., object detection and captioning, and observe improved results. In particular, augmenting both the stages reduces the CIDEr-D degradation for high motion blur intensity from 68.7 to 11.7 on MS COCO dataset, and from 22.4 to 6.8 on Vizwiz dataset.

68.An adaptive Origin-Destination flows cluster-detecting method to identify urban mobility trends ⬇️

Origin-Destination (OD) flow, as an abstract representation of the object`s movement or interaction, has been used to reveal the urban mobility and human-land interaction pattern. As an important spatial analysis approach, the clustering methods of point events have been extended to OD flows to identify the dominant trends and spatial structures of urban mobility. However, the existing methods for OD flow cluster-detecting are limited both in specific spatial scale and the uncertain result due to different parameters setting, which is difficult for complicated OD flows clustering under spatial heterogeneity. To address these limitations, in this paper, we proposed a novel OD flows cluster-detecting method based on the OPTICS algorithm which can identify OD flow clusters with various aggregation scales. The method can adaptively determine parameter value from the dataset without prior knowledge and artificial intervention. Experiments indicated that our method outperformed three state-of-the-art methods with more accurate and complete of clusters and less noise. As a case study, our method is applied to identify the potential routes for public transport service settings by detecting OD flow clusters within urban travel data.

69.Optimizing Reusable Knowledge for Continual Learning via Metalearning ⬇️

When learning tasks over time, artificial neural networks suffer from a problem known as Catastrophic Forgetting (CF). This happens when the weights of a network are overwritten during the training of a new task causing forgetting of old information. To address this issue, we propose MetA Reusable Knowledge or MARK, a new method that fosters weight reusability instead of overwriting when learning a new task. Specifically, MARK keeps a set of shared weights among tasks. We envision these shared weights as a common Knowledge Base (KB) that is not only used to learn new tasks, but also enriched with new knowledge as the model learns new tasks. Key components behind MARK are two-fold. On the one hand, a metalearning approach provides the key mechanism to incrementally enrich the KB with new knowledge and to foster weight reusability among tasks. On the other hand, a set of trainable masks provides the key mechanism to selectively choose from the KB relevant weights to solve each task. By using MARK, we achieve state of the art results in several popular benchmarks, surpassing the best performing methods in terms of average accuracy by over 10% on the 20-Split-MiniImageNet dataset, while achieving almost zero forgetfulness using 55% of the number of parameters. Furthermore, an ablation study provides evidence that, indeed, MARK is learning reusable knowledge that is selectively used by each task.

70.Deep Unfolding of Iteratively Reweighted ADMM for Wireless RF Sensing ⬇️

We address the detection of material defects, which are inside a layered material structure using compressive sensing based multiple-output (MIMO) wireless radar. Here, the strong clutter due to the reflection of the layered structure's surface often makes the detection of the defects challenging. Thus, sophisticated signal separation methods are required for improved defect detection. In many scenarios, the number of defects that we are interested in is limited and the signaling response of the layered structure can be modeled as a low-rank structure. Therefore, we propose joint rank and sparsity minimization for defect detection. In particular, we propose a non-convex approach based on the iteratively reweighted nuclear and $\ell_1-$norm (a double-reweighted approach) to obtain a higher accuracy compared to the conventional nuclear norm and $\ell_1-$norm minimization. To this end, an iterative algorithm is designed to estimate the low-rank and sparse contributions. Further, we propose deep learning to learn the parameters of the algorithm (i.e., algorithm unfolding) to improve the accuracy and the speed of convergence of the algorithm. Our numerical results show that the proposed approach outperforms the conventional approaches in terms of mean square errors of the recovered low-rank and sparse components and the speed of convergence.