1.Semantic Segmentation With Multi Scale Spatial Attention For Self Driving Cars ⬇️
In this paper, we present an architecture using multi scale feature fusion at various scales for accurate and efficient semantic image segmentation. We have used dilated convolutional layers in downsampling layers and transposed convolutional layers in the upsampling layers and used concat layers to merge them. We have used skip connections in between alternate blocks which are comprised of convolutional and max pooling layers. We present an in depth theoretical analysis of our network with training and optimization details. We evaluated our network on the Camvid dataset using mean accuracy per class and Intersection Over Union (IOU) as the evaluation metrics on the test set. Our model outperforms previous state of the art on semantic segmentation achieving mean IOU value of 74.12 while running at >100 FPS.
2.MiCo: Mixup Co-Training for Semi-Supervised Domain Adaptation ⬇️
Semi-supervised domain adaptation (SSDA) aims to adapt models from a labeled source domain to a different but related target domain, from which unlabeled data and a small set of labeled data are provided. In this paper we propose a new approach for SSDA, which is to explicitly decompose SSDA into two sub-problems: a semi-supervised learning (SSL) problem in the target domain and an unsupervised domain adaptation (UDA) problem across domains. We show that these two sub-problems yield very different classifiers, which we leverage with our algorithm MixUp Co-training (MiCo). MiCo applies Mixup to bridge the gap between labeled and unlabeled data of each individual model and employs co-training to exchange the expertise between the two classifiers. MiCo needs no adversarial and minmax training, making it easily implementable and stable. MiCo achieves state-of-the-art results on SSDA datasets, outperforming the prior art by a notable 4% margin on DomainNet.
3.Real-World Multi-Domain Data Applications for Generalizations to Clinical Settings ⬇️
With promising results of machine learning based models in computer vision, applications on medical imaging data have been increasing exponentially. However, generalizations to complex real-world clinical data is a persistent problem. Deep learning models perform well when trained on standardized datasets from artificial settings, such as clinical trials. However, real-world data is different and translations are yielding varying results. The complexity of real-world applications in healthcare could emanate from a mixture of different data distributions across multiple device domains alongside the inevitable noise sourced from varying image resolutions, human errors, and the lack of manual gradings. In addition, healthcare applications not only suffer from the scarcity of labeled data, but also face limited access to unlabeled data due to HIPAA regulations, patient privacy, ambiguity in data ownership, and challenges in collecting data from different sources. These limitations pose additional challenges to applying deep learning algorithms in healthcare and clinical translations. In this paper, we utilize self-supervised representation learning methods, formulated effectively in transfer learning settings, to address limited data availability. Our experiments verify the importance of diverse real-world data for generalization to clinical settings. We show that by employing a self-supervised approach with transfer learning on a multi-domain real-world dataset, we can achieve 16% relative improvement on a standardized dataset over supervised baselines.
4.KPRNet: Improving projection-based LiDAR semantic segmentation ⬇️
Semantic segmentation is an important component in the perception systems of autonomous vehicles. In this work, we adopt recent advances in both image and point cloud segmentation to achieve a better accuracy in the task of segmenting LiDAR scans. KPRNet improves the convolutional neural network architecture of 2D projection methods and utilizes KPConv [11] to replace the commonly used post-processing techniques with a learnable point-wise component which allows us to obtain more accurate 3D labels. With these improvements our model outperforms the current best method on the SemanticKITTI benchmark, reaching an mIoU of 63.1.
5.Real-time Dense Reconstruction of Tissue Surface from Stereo Optical Video ⬇️
We propose an approach to reconstruct dense three-dimensional (3D) model of tissue surface from stereo optical videos in real-time, the basic idea of which is to first extract 3D information from video frames by using stereo matching, and then to mosaic the reconstructed 3D models. To handle the common low texture regions on tissue surfaces, we propose effective post-processing steps for the local stereo matching method to enlarge the radius of constraint, which include outliers removal, hole filling and smoothing. Since the tissue models obtained by stereo matching are limited to the field of view of the imaging modality, we propose a model mosaicking method by using a novel feature-based simultaneously localization and mapping (SLAM) method to align the models. Low texture regions and the varying illumination condition may lead to a large percentage of feature matching outliers. To solve this problem, we propose several algorithms to improve the robustness of SLAM, which mainly include (1) a histogram voting-based method to roughly select possible inliers from the feature matching results, (2) a novel 1-point RANSAC-based P$n$P algorithm called as DynamicR1PP$n$P to track the camera motion and (3) a GPU-based iterative closest points (ICP) and bundle adjustment (BA) method to refine the camera motion estimation results. Experimental results on ex- and in vivo data showed that the reconstructed 3D models have high resolution texture with an accuracy error of less than 2 mm. Most algorithms are highly parallelized for GPU computation, and the average runtime for processing one key frame is 76.3 ms on stereo images with 960x540 resolution.
6.BMBC:Bilateral Motion Estimation with Bilateral Cost Volume for Video Interpolation ⬇️
Video interpolation increases the temporal resolution of a video sequence by synthesizing intermediate frames between two consecutive frames. We propose a novel deep-learning-based video interpolation algorithm based on bilateral motion estimation. First, we develop the bilateral motion network with the bilateral cost volume to estimate bilateral motions accurately. Then, we approximate bi-directional motions to predict a different kind of bilateral motions. We then warp the two input frames using the estimated bilateral motions. Next, we develop the dynamic filter generation network to yield dynamic blending filters. Finally, we combine the warped frames using the dynamic blending filters to generate intermediate frames. Experimental results show that the proposed algorithm outperforms the state-of-the-art video interpolation algorithms on several benchmark datasets.
7.Machine-learned Regularization and Polygonization of Building Segmentation Masks ⬇️
We propose a machine learning based approach for automatic regularization and polygonization of building segmentation masks. Taking an image as input, we first predict building segmentation maps exploiting generic fully convolutional network (FCN). A generative adversarial network (GAN) is then involved to perform a regularization of building boundaries to make them more realistic, i.e., having more rectilinear outlines which construct right angles if required. This is achieved through the interplay between the discriminator which gives a probability of input image being true and generator that learns from discriminator's response to create more realistic images. Finally, we train the backbone convolutional neural network (CNN) which is adapted to predict sparse outcomes corresponding to building corners out of regularized building segmentation results. Experiments on three building segmentation datasets demonstrate that the proposed method is not only capable of obtaining accurate results, but also of producing visually pleasing building outlines parameterized as polygons.
8.A Lightweight Neural Network for Monocular View Generation with Occlusion Handling ⬇️
In this article, we present a very lightweight neural network architecture, trained on stereo data pairs, which performs view synthesis from one single image. With the growing success of multi-view formats, this problem is indeed increasingly relevant. The network returns a prediction built from disparity estimation, which fills in wrongly predicted regions using a occlusion handling technique. To do so, during training, the network learns to estimate the left-right consistency structural constraint on the pair of stereo input images, to be able to replicate it at test time from one single image. The method is built upon the idea of blending two predictions: a prediction based on disparity estimation, and a prediction based on direct minimization in occluded regions. The network is also able to identify these occluded areas at training and at test time by checking the pixelwise left-right consistency of the produced disparity maps. At test time, the approach can thus generate a left-side and a right-side view from one input image, as well as a depth map and a pixelwise confidence measure in the prediction. The work outperforms visually and metric-wise state-of-the-art approaches on the challenging KITTI dataset, all while reducing by a very significant order of magnitude (5 or 10 times) the required number of parameters (6.5 M).
9.The Surprising Effectiveness of Linear Unsupervised Image-to-Image Translation ⬇️
Unsupervised image-to-image translation is an inherently ill-posed problem. Recent methods based on deep encoder-decoder architectures have shown impressive results, but we show that they only succeed due to a strong locality bias, and they fail to learn very simple nonlocal transformations (e.g. mapping upside down faces to upright faces). When the locality bias is removed, the methods are too powerful and may fail to learn simple local transformations. In this paper we introduce linear encoder-decoder architectures for unsupervised image to image translation. We show that learning is much easier and faster with these architectures and yet the results are surprisingly effective. In particular, we show a number of local problems for which the results of the linear methods are comparable to those of state-of-the-art architectures but with a fraction of the training time, and a number of nonlocal problems for which the state-of-the-art fails while linear methods succeed.
10.Hallucinating Saliency Maps for Fine-Grained Image Classification for Limited Data Domains ⬇️
Most of the saliency methods are evaluated on their ability to generate saliency maps, and not on their functionality in a complete vision pipeline, like for instance, image classification. In the current paper, we propose an approach which does not require explicit saliency maps to improve image classification, but they are learned implicitely, during the training of an end-to-end image classification task. We show that our approach obtains similar results as the case when the saliency maps are provided explicitely. Combining RGB data with saliency maps represents a significant advantage for object recognition, especially for the case when training data is limited. We validate our method on several datasets for fine-grained classification tasks (Flowers, Birds and Cars). In addition, we show that our saliency estimation method, which is trained without any saliency groundtruth data, obtains competitive results on real image saliency benchmark (Toronto), and outperforms deep saliency models with synthetic images (SID4VAM).
11.Style Transfer for Co-Speech Gesture Animation: A Multi-Speaker Conditional-Mixture Approach ⬇️
How can we teach robots or virtual assistants to gesture naturally? Can we go further and adapt the gesturing style to follow a specific speaker? Gestures that are naturally timed with corresponding speech during human communication are called co-speech gestures. A key challenge, called gesture style transfer, is to learn a model that generates these gestures for a speaking agent 'A' in the gesturing style of a target speaker 'B'. A secondary goal is to simultaneously learn to generate co-speech gestures for multiple speakers while remembering what is unique about each speaker. We call this challenge style preservation. In this paper, we propose a new model, named Mix-StAGE, which trains a single model for multiple speakers while learning unique style embeddings for each speaker's gestures in an end-to-end manner. A novelty of Mix-StAGE is to learn a mixture of generative models which allows for conditioning on the unique gesture style of each speaker. As Mix-StAGE disentangles style and content of gestures, gesturing styles for the same input speech can be altered by simply switching the style embeddings. Mix-StAGE also allows for style preservation when learning simultaneously from multiple speakers. We also introduce a new dataset, Pose-Audio-Transcript-Style (PATS), designed to study gesture generation and style transfer. Our proposed Mix-StAGE model significantly outperforms the previous state-of-the-art approach for gesture generation and provides a path towards performing gesture style transfer across multiple speakers. Link to code, data, and videos: this http URL
12.Reparameterizing Convolutions for Incremental Multi-Task Learning without Task Interference ⬇️
Multi-task networks are commonly utilized to alleviate the need for a large number of highly specialized single-task networks. However, two common challenges in developing multi-task models are often overlooked in literature. First, enabling the model to be inherently incremental, continuously incorporating information from new tasks without forgetting the previously learned ones (incremental learning). Second, eliminating adverse interactions amongst tasks, which has been shown to significantly degrade the single-task performance in a multi-task setup (task interference). In this paper, we show that both can be achieved simply by reparameterizing the convolutions of standard neural network architectures into a non-trainable shared part (filter bank) and task-specific parts (modulators), where each modulator has a fraction of the filter bank parameters. Thus, our reparameterization enables the model to learn new tasks without adversely affecting the performance of existing ones. The results of our ablation study attest the efficacy of the proposed reparameterization. Moreover, our method achieves state-of-the-art on two challenging multi-task learning benchmarks, PASCAL-Context and NYUD, and also demonstrates superior incremental learning capability as compared to its close competitors.
13.A Comprehensive Study on Sign Language Recognition Methods ⬇️
In this paper, a comparative experimental assessment of computer vision-based methods for sign language recognition is conducted. By implementing the most recent deep neural network methods in this field, a thorough evaluation on multiple publicly available datasets is performed. The aim of the present study is to provide insights on sign language recognition, focusing on mapping non-segmented video streams to glosses. For this task, two new sequence training criteria, known from the fields of speech and scene text recognition, are introduced. Furthermore, a plethora of pretraining schemes is thoroughly discussed. Finally, a new RGB+D dataset for the Greek sign language is created. To the best of our knowledge, this is the first sign language dataset where sentence and gloss level annotations are provided for a video capture.
14.HEU Emotion: A Large-scale Database for Multi-modal Emotion Recognition in the Wild ⬇️
The study of affective computing in the wild setting is underpinned by databases. Existing multimodal emotion databases in the real-world conditions are few and small, with a limited number of subjects and expressed in a single language. To meet this requirement, we collected, annotated, and prepared to release a new natural state video database (called HEU Emotion). HEU Emotion contains a total of 19,004 video clips, which is divided into two parts according to the data source. The first part contains videos downloaded from Tumblr, Google, and Giphy, including 10 emotions and two modalities (facial expression and body posture). The second part includes corpus taken manually from movies, TV series, and variety shows, consisting of 10 emotions and three modalities (facial expression, body posture, and emotional speech). HEU Emotion is by far the most extensive multi-modal emotional database with 9,951 subjects. In order to provide a benchmark for emotion recognition, we used many conventional machine learning and deep learning methods to evaluate HEU Emotion. We proposed a Multi-modal Attention module to fuse multi-modal features adaptively. After multi-modal fusion, the recognition accuracies for the two parts increased by 2.19% and 4.01% respectively over those of single-modal facial expression recognition.
15.Deforming the Loss Surface ⬇️
In deep learning, it is usually assumed that the shape of the loss surface is fixed. Differently, a novel concept of deformation operator is first proposed in this paper to deform the loss surface, thereby improving the optimization. Deformation function, as a type of deformation operator, can improve the generalization performance. Moreover, various deformation functions are designed, and their contributions to the loss surface are further provided. Then, the original stochastic gradient descent optimizer is theoretically proved to be a flat minima filter that owns the talent to filter out the sharp minima. Furthermore, the flatter minima could be obtained by exploiting the proposed deformation functions, which is verified on CIFAR-100, with visualizations of loss landscapes near the critical points obtained by both the original optimizer and optimizer enhanced by deformation functions. The experimental results show that deformation functions do find flatter regions. Moreover, on ImageNet, CIFAR-10, and CIFAR-100, popular convolutional neural networks enhanced by deformation functions are compared with the corresponding original models, where significant improvements are observed on all of the involved models equipped with deformation functions. For example, the top-1 test accuracy of ResNet-20 on CIFAR-100 increases by 1.46%, with insignificant additional computational overhead.
16.Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry Consistency ⬇️
Recent learning-based approaches, in which models are trained by single-view images have shown promising results for monocular 3D face reconstruction, but they suffer from the ill-posed face pose and depth ambiguity issue. In contrast to previous works that only enforce 2D feature constraints, we propose a self-supervised training architecture by leveraging the multi-view geometry consistency, which provides reliable constraints on face pose and depth estimation. We first propose an occlusion-aware view synthesis method to apply multi-view geometry consistency to self-supervised learning. Then we design three novel loss functions for multi-view consistency, including the pixel consistency loss, the depth consistency loss, and the facial landmark-based epipolar loss. Our method is accurate and robust, especially under large variations of expressions, poses, and illumination conditions. Comprehensive experiments on the face alignment and 3D face reconstruction benchmarks have demonstrated superiority over state-of-the-art methods. Our code and model are released in this https URL.
17.Map-Repair: Deep Cadastre Maps Alignment and Temporal Inconsistencies Fix in Satellite Images ⬇️
In the fast developing countries it is hard to trace new buildings construction or old structures destruction and, as a result, to keep the up-to-date cadastre maps. Moreover, due to the complexity of urban regions or inconsistency of data used for cadastre maps extraction, the errors in form of misalignment is a common problem. In this work, we propose an end-to-end deep learning approach which is able to solve inconsistencies between the input intensity image and the available building footprints by correcting label noises and, at the same time, misalignments if needed. The obtained results demonstrate the robustness of the proposed method to even severely misaligned examples that makes it potentially suitable for real applications, like OpenStreetMap correction.
18.Multi-view adaptive graph convolutions for graph classification ⬇️
In this paper, a novel multi-view methodology for graph-based neural networks is proposed. A systematic and methodological adaptation of the key concepts of classical deep learning methods such as convolution, pooling and multi-view architectures is developed for the context of non-Euclidean manifolds. The aim of the proposed work is to present a novel multi-view graph convolution layer, as well as a new view pooling layer making use of: a) a new hybrid Laplacian that is adjusted based on feature distance metric learning, b) multiple trainable representations of a feature matrix of a graph, using trainable distance matrices, adapting the notion of views to graphs and c) a multi-view graph aggregation scheme called graph view pooling, in order to synthesise information from the multiple generated views. The aforementioned layers are used in an end-to-end graph neural network architecture for graph classification and show competitive results to other state-of-the-art methods.
19.Learning Crisp Edge Detector Using Logical Refinement Network ⬇️
Edge detection is a fundamental problem in different computer vision tasks. Recently, edge detection algorithms achieve satisfying improvement built upon deep learning. Although most of them report favorable evaluation scores, they often fail to accurately localize edges and give thick and blurry boundaries. In addition, most of them focus on 2D images and the challenging 3D edge detection is still under-explored. In this work, we propose a novel logical refinement network for crisp edge detection, which is motivated by the logical relationship between segmentation and edge maps and can be applied to both 2D and 3D images. The network consists of a joint object and edge detection network and a crisp edge refinement network, which predicts more accurate, clearer and thinner high quality binary edge maps without any post-processing. Extensive experiments are conducted on the 2D nuclei images from Kaggle 2018 Data Science Bowl and a private 3D microscopy images of a monkey brain, which show outstanding performance compared with state-of-the-art methods.
20.Micro-expression spotting: A new benchmark ⬇️
Micro-expressions (MEs) are brief and involuntary facial expressions that occur when people are trying to hide their true feelings or conceal their emotions. Based on psychology research, MEs play an important role in understanding genuine emotions, which leads to many potential applications. Therefore, ME analysis has been becoming an attractive topic for various research areas, such as psychology, law enforcement, and psychotherapy. In the computer vision field, the study of MEs can be divided into two main tasks: spotting and recognition, which are to identify positions of MEs in videos and determine the emotion category of detected MEs, respectively. Recently, although much research has been done, the construction of a fully automatic system for analyzing MEs is still far away from practice. This is because of two main reasons: most of the research in MEs only focuses on the recognition part while abandons the spotting task; current public datasets for ME spotting are not challenging enough to support developing a robust spotting algorithm. Our contributions in this paper are three folds: (1) We introduce an extension of the SMIC-E database, namely SMIC-E-Long database, which is a new challenging benchmark for ME spotting. (2) We suggest a new evaluation protocol that standardizes the comparison of various ME spotting techniques. (3) Extensive experiments with handcrafted and deep learning-based approaches on the SMIC-E-Long database are performed for baseline evaluation.
21.Visual Compositional Learning for Human-Object Interaction Detection ⬇️
Human-Object interaction (HOI) detection aims to localize and infer relationships between human and objects in an image. It is challenging because an enormous number of possible combinations of objects and verbs types forms a long-tail distribution. We devise a deep Visual Compositional Learning (VCL) framework, which is a simple yet efficient framework to effectively address this problem. VCL first decomposes an HOI representation into object and verb specific features, and then composes new interaction samples in the feature space via stitching the decomposed features. The integration of decomposition and composition enables VCL to share object and verb features among different HOI samples and images, and to generate new interaction samples and new types of HOI, and thus largely alleviates the long-tail distribution problem and benefits low-shot or zero-shot HOI detection. Extensive experiments demonstrate that the proposed VCL can effectively improve the generalization of HOI detection on HICO-DET and V-COCO and outperforms the recent state-of-the-art methods on HICO-DET. Code is available at this https URL.
22.Fully Convolutional Networks for Continuous Sign Language Recognition ⬇️
Continuous sign language recognition (SLR) is a challenging task that requires learning on both spatial and temporal dimensions of signing frame sequences. Most recent work accomplishes this by using CNN and RNN hybrid networks. However, training these networks is generally non-trivial, and most of them fail in learning unseen sequence patterns, causing an unsatisfactory performance for online recognition. In this paper, we propose a fully convolutional network (FCN) for online SLR to concurrently learn spatial and temporal features from weakly annotated video sequences with only sentence-level annotations given. A gloss feature enhancement (GFE) module is introduced in the proposed network to enforce better sequence alignment learning. The proposed network is end-to-end trainable without any pre-training. We conduct experiments on two large scale SLR datasets. Experiments show that our method for continuous SLR is effective and performs well in online recognition.
23.An LSTM Approach to Temporal 3D Object Detection in LiDAR Point Clouds ⬇️
Detecting objects in 3D LiDAR data is a core technology for autonomous driving and other robotics applications. Although LiDAR data is acquired over time, most of the 3D object detection algorithms propose object bounding boxes independently for each frame and neglect the useful information available in the temporal domain. To address this problem, in this paper we propose a sparse LSTM-based multi-frame 3d object detection algorithm. We use a U-Net style 3D sparse convolution network to extract features for each frame's LiDAR point-cloud. These features are fed to the LSTM module together with the hidden and memory features from last frame to predict the 3d objects in the current frame as well as hidden and memory features that are passed to the next frame. Experiments on the Waymo Open Dataset show that our algorithm outperforms the traditional frame by frame approach by 7.5% mAP@0.7 and other multi-frame approaches by 1.2% while using less memory and computation per frame. To the best of our knowledge, this is the first work to use an LSTM for 3D object detection in sparse point clouds.
24.Artificial Intelligence in the Creative Industries: A Review ⬇️
This paper reviews the current state of the art in Artificial Intelligence (AI) technologies and applications in the context of the creative industries. A brief background of AI, and specifically Machine Learning (ML) algorithms, is provided including Convolutional Neural Network (CNNs), Generative Adversarial Networks (GANs), Recurrent Neural Networks (RNNs) and Deep Reinforcement Learning (DRL). We categorise creative applications into five groups related to how AI technologies are used: i) content creation, ii) information analysis, iii) content enhancement and post production workflows, iv) information extraction and enhancement, and v) data compression. We critically examine the successes and limitations of this rapidly advancing technology in each of these areas. We further differentiate between the use of AI as a creative tool and its potential as a creator in its own right. We foresee that, in the near future, machine learning-based AI will be adopted widely as a tool or collaborative assistant for creativity. In contrast, we observe that the successes of machine learning in domains with fewer constraints, where AI is the `creator', remain modest. The potential of AI (or its developers) to win awards for its original creations in competition with human creatives is also limited, based on contemporary technologies. We therefore conclude that, in the context of creative industries, maximum benefit from AI will be derived where its focus is human centric -- where it is designed to augment, rather than replace, human creativity.
25.Commonality-Parsing Network across Shape and Appearance for Partially Supervised Instance Segmentation ⬇️
Partially supervised instance segmentation aims to perform learning on limited mask-annotated categories of data thus eliminating expensive and exhaustive mask annotation. The learned models are expected to be generalizable to novel categories. Existing methods either learn a transfer function from detection to segmentation, or cluster shape priors for segmenting novel categories. We propose to learn the underlying class-agnostic commonalities that can be generalized from mask-annotated categories to novel categories. Specifically, we parse two types of commonalities: 1) shape commonalities which are learned by performing supervised learning on instance boundary prediction; and 2) appearance commonalities which are captured by modeling pairwise affinities among pixels of feature maps to optimize the separability between instance and the background. Incorporating both the shape and appearance commonalities, our model significantly outperforms the state-of-the-art methods on both partially supervised setting and few-shot setting for instance segmentation on COCO dataset.
26.Self-Supervised Learning Across Domains ⬇️
Human adaptability relies crucially on learning and merging knowledge from both supervised and unsupervised tasks: the parents point out few important concepts, but then the children fill in the gaps on their own. This is particularly effective, because supervised learning can never be exhaustive and thus learning autonomously allows to discover invariances and regularities that help to generalize. In this paper we propose to apply a similar approach to the problem of object recognition across domains: our model learns the semantic labels in a supervised fashion, and broadens its understanding of the data by learning from self-supervised signals on the same images. This secondary task helps the network to learn the concepts like spatial orientation and part correlation, while acting as a regularizer for the classification task. Extensive experiments confirm our intuition and show that our multi-task method combining supervised and self-supervised knowledge shows competitive results with respect to more complex domain generalization and adaptation solutions. It also proves its potential in the novel and challenging predictive and partial domain adaptation scenarios.
27.Performance analysis of weighted low rank model with sparse image histograms for face recognition under lowlevel illumination and occlusion ⬇️
In a broad range of computer vision applications, the purpose of Low-rank matrix approximation (LRMA) models is to recover the underlying low-rank matrix from its degraded observation. The latest LRMA methods - Robust Principal Component Analysis (RPCA) resort to using the nuclear norm minimization (NNM) as a convex relaxation of the non-convex rank minimization. However, NNM tends to over-shrink the rank components and treats the different rank components equally, limiting its flexibility in practical applications. We use a more flexible model, namely the Weighted Schatten p-Norm Minimization (WSNM), to generalize the NNM to the Schatten p-norm minimization with weights assigned to different singular values. The proposed WSNM not only gives a better approximation to the original low-rank assumption but also considers the importance of different rank components. In this paper, a comparison of the low-rank recovery performance of two LRMA algorithms- RPCA and WSNM is brought out on occluded human facial images. The analysis is performed on facial images from the Yale database and over own database , where different facial expressions, spectacles, varying illumination account for the facial occlusions. The paper also discusses the prominent trends observed from the experimental results performed through the application of these algorithms. As low-rank images sometimes might fail to capture the details of a face adequately, we further propose a novel method to use the image-histogram of the sparse images thus obtained to identify the individual in any given image. Extensive experimental results show, both qualitatively and quantitatively, that WSNM surpasses RPCA in its performance more effectively by removing facial occlusions, thus giving recovered low-rank images of higher PSNR and SSIM.
28.On the Effectiveness of Image Rotation for Open Set Domain Adaptation ⬇️
Open Set Domain Adaptation (OSDA) bridges the domain gap between a labeled source domain and an unlabeled target domain, while also rejecting target classes that are not present in the source. To avoid negative transfer, OSDA can be tackled by first separating the known/unknown target samples and then aligning known target samples with the source data. We propose a novel method to addresses both these problems using the self-supervised task of rotation recognition. Moreover, we assess the performance with a new open set metric that properly balances the contribution of recognizing the known classes and rejecting the unknown samples. Comparative experiments with existing OSDA methods on the standard Office-31 and Office-Home benchmarks show that: (i) our method outperforms its competitors, (ii) reproducibility for this field is a crucial issue to tackle, (iii) our metric provides a reliable tool to allow fair open set evaluation.
29.Unsupervised Discovery of 3D Physical Objects from Video ⬇️
We study the problem of unsupervised physical object discovery. Unlike existing frameworks that aim to learn to decompose scenes into 2D segments purely based on each object's appearance, we explore how physics, especially object interactions, facilitates learning to disentangle and segment instances from raw videos, and to infer the 3D geometry and position of each object, all without supervision. Drawing inspiration from developmental psychology, our Physical Object Discovery Network (POD-Net) uses both multi-scale pixel cues and physical motion cues to accurately segment observable and partially occluded objects of varying sizes, and infer properties of those objects. Our model reliably segments objects on both synthetic and real scenes. The discovered object properties can also be used to reason about physical events.
30.CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotations ⬇️
As facial interaction systems are prevalently deployed, security and reliability of these systems become a critical issue, with substantial research efforts devoted. Among them, face anti-spoofing emerges as an important area, whose objective is to identify whether a presented face is live or spoof. Though promising progress has been achieved, existing works still have difficulty in handling complex spoof attacks and generalizing to real-world scenarios. The main reason is that current face anti-spoofing datasets are limited in both quantity and diversity. To overcome these obstacles, we contribute a large-scale face anti-spoofing dataset, CelebA-Spoof, with the following appealing properties: 1) Quantity: CelebA-Spoof comprises of 625,537 pictures of 10,177 subjects, significantly larger than the existing datasets. 2) Diversity: The spoof images are captured from 8 scenes (2 environments * 4 illumination conditions) with more than 10 sensors. 3) Annotation Richness: CelebA-Spoof contains 10 spoof type annotations, as well as the 40 attribute annotations inherited from the original CelebA dataset. Equipped with CelebA-Spoof, we carefully benchmark existing methods in a unified multi-task framework, Auxiliary Information Embedding Network (AENet), and reveal several valuable observations.
31.Locality-Aware Rotated Ship Detection in High-Resolution Remote Sensing Imagery Based on Multi-Scale Convolutional Network ⬇️
Ship detection has been an active and vital topic in the field of remote sensing for a decade, but it is still a challenging problem due to the large scale variations, the high aspect ratios, the intensive arrangement, and the background clutter disturbance. In this letter, we propose a locality-aware rotated ship detection (LARSD) framework based on a multi-scale convolutional neural network (CNN) to tackle these issues. The proposed framework applies a UNet-like multi-scale CNN to generate multi-scale feature maps with high-level semantic information in high resolution. Then, a rotated anchor-based regression is applied for directly predicting the probability, the edge distances, and the angle of ships. Finally, a locality-aware score alignment is proposed to fix the mismatch between classification results and location results caused by the independence of each subnet. Furthermore, to enlarge the datasets of ship detection, we build a new high-resolution ship detection (HRSD) dataset, where 2499 images and 9269 instances were collected from Google Earth with different resolutions. Experiments based on public dataset HRSC2016 and our HRSD dataset demonstrate that our detection method achieves state-of-the-art performance.
32.Body2Hands: Learning to Infer 3D Hands from Conversational Gesture Body Dynamics ⬇️
We propose a novel learned deep prior of body motion for 3D hand shape synthesis and estimation in the domain of conversational gestures. Our model builds upon the insight that body motion and hand gestures are strongly correlated in non-verbal communication settings. We formulate the learning of this prior as a prediction task of 3D hand shape over time given body motion input alone. Trained with 3D pose estimations obtained from a large-scale dataset of internet videos, our hand prediction model produces convincing 3D hand gestures given only the 3D motion of the speaker's arms as input. We demonstrate the efficacy of our method on hand gesture synthesis from body motion input, and as a strong body prior for single-view image-based 3D hand pose estimation. We demonstrate that our method outperforms previous state-of-the-art approaches and can generalize beyond the monologue-based training data to multi-person conversations. Video results are available at this http URL.
33.Towards Recognizing Unseen Categories in Unseen Domains ⬇️
Current deep visual recognition systems suffer from severe performance degradation when they encounter new images from classes and scenarios unseen during training. Hence, the core challenge of Zero-Shot Learning (ZSL) is to cope with the semantic-shift whereas the main challenge of Domain Adaptation and Domain Generalization (DG) is the domain-shift. While historically ZSL and DG tasks are tackled in isolation, this work develops with the ambitious goal of solving them jointly,i.e. by recognizing unseen visual concepts in unseen domains. We presentCuMix (CurriculumMixup for recognizing unseen categories in unseen domains), a holistic algorithm to tackle ZSL, DG and ZSL+DG. The key idea of CuMix is to simulate the test-time domain and semantic shift using images and features from unseen domains and categories generated by mixing up the multiple source domains and categories available during training. Moreover, a curriculum-based mixing policy is devised to generate increasingly complex training samples. Results on standard SL and DG datasets and on ZSL+DG using the DomainNet benchmark demonstrate the effectiveness of our approach.
34.SeismoGlow -- Data augmentation for the class imbalance problem ⬇️
In several application areas, such as medical diagnosis, spam filtering, fraud detection, and seismic data analysis, it is very usual to find relevant classification tasks where some class occurrences are rare. This is the so called class imbalance problem, which is a challenge in machine learning. In this work, we propose the SeismoGlow a flow-based generative model to create synthetic samples, aiming to address the class imbalance. Inspired by the Glow model, it uses interpolation on the learned latent space to produce synthetic samples for one rare class. We apply our approach to the development of a seismogram signal quality classifier. We introduce a dataset composed of5.223seismograms that are distributed between the good, medium, and bad classes and with their respective frequencies of 66.68%,31.54%, and 1.76%. Our methodology is evaluated on a stratified 10-fold cross-validation setting, using the Miniceptionmodel as a baseline, and assessing the effects of adding the generated samples on the training set of each iteration. In our experiments, we achieve an improvement of 13.9% on the rare class F1-score, while not hurting the metric value for the other classes and thus observing the overall accuracy improvement. Our empirical findings indicate that our method can generate high-quality synthetic seismograms with realistic looking and sufficient plurality to help the Miniception model to overcome the class imbalance problem. We believe that our results are a step forward in solving both the task of seismogram signal quality classification and class imbalance.
35.ZSCRGAN: A GAN-based Expectation Maximization Model for Zero-Shot Retrieval of Images from Textual Descriptions ⬇️
Most existing algorithms for cross-modal Information Retrieval are based on a supervised train-test setup, where a model learns to align the mode of the query (e.g., text) to the mode of the documents (e.g., images) from a given training set. Such a setup assumes that the training set contains an exhaustive representation of all possible classes of queries. In reality, a retrieval model may need to be deployed on previously unseen classes, which implies a zero-shot IR setup. In this paper, we propose a novel GAN-based model for zero-shot text to image retrieval. When given a textual description as the query, our model can retrieve relevant images in a zero-shot setup. The proposed model is trained using an Expectation-Maximization framework. Experiments on multiple benchmark datasets show that our proposed model comfortably outperforms several state-of-the-art zero-shot text to image retrieval models, as well as zero-shot classification and hashing models suitably used for retrieval.
36.Learning Noise-Aware Encoder-Decoder from Noisy Labels by Alternating Back-Propagation for Saliency Detection ⬇️
In this paper, we propose a noise-aware encoder-decoder framework to disentangle a clean saliency predictor from noisy training examples, where the noisy labels are generated by unsupervised handcrafted feature-based methods. The proposed model consists of two sub-models parameterized by neural networks: (1) a saliency predictor that maps input images to clean saliency maps, and (2) a noise generator, which is a latent variable model that produces noises from Gaussian latent vectors. The whole model that represents noisy labels is a sum of the two sub-models. The goal of training the model is to estimate the parameters of both sub-models, and simultaneously infer the corresponding latent vector of each noisy label. We propose to train the model by using an alternating back-propagation (ABP) algorithm, which alternates the following two steps: (1) learning back-propagation for estimating the parameters of two sub-models by gradient ascent, and (2) inferential back-propagation for inferring the latent vectors of training noisy examples by Langevin Dynamics. To prevent the network from converging to trivial solutions, we utilize an edge-aware smoothness loss to regularize hidden saliency maps to have similar structures as their corresponding images. Experimental results on several benchmark datasets indicate the effectiveness of the proposed model.
37.Accelerated Stochastic Gradient-free and Projection-free Methods ⬇️
In the paper, we propose a class of accelerated stochastic gradient-free and projection-free (a.k.a., zeroth-order Frank-Wolfe) methods to solve the constrained stochastic and finite-sum nonconvex optimization. Specifically, we propose an accelerated stochastic zeroth-order Frank-Wolfe (Acc-SZOFW) method based on the variance reduced technique of SPIDER/SpiderBoost and a novel momentum accelerated technique. Moreover, under some mild conditions, we prove that the Acc-SZOFW has the function query complexity of
$O(d\sqrt{n}\epsilon^{-2})$ for finding an$\epsilon$ -stationary point in the finite-sum problem, which improves the exiting best result by a factor of$O(\sqrt{n}\epsilon^{-2})$ , and has the function query complexity of$O(d\epsilon^{-3})$ in the stochastic problem, which improves the exiting best result by a factor of$O(\epsilon^{-1})$ . To relax the large batches required in the Acc-SZOFW, we further propose a novel accelerated stochastic zeroth-order Frank-Wolfe (Acc-SZOFW*) based on a new variance reduced technique of STORM, which still reaches the function query complexity of$O(d\epsilon^{-3})$ in the stochastic problem without relying on any large batches. In particular, we present an accelerated framework of the Frank-Wolfe methods based on the proposed momentum accelerated technique. The extensive experimental results on black-box adversarial attack and robust black-box classification demonstrate the efficiency of our algorithms.
38.Channel-Level Variable Quantization Network for Deep Image Compression ⬇️
Deep image compression systems mainly contain four components: encoder, quantizer, entropy model, and decoder. To optimize these four components, a joint rate-distortion framework was proposed, and many deep neural network-based methods achieved great success in image compression. However, almost all convolutional neural network-based methods treat channel-wise feature maps equally, reducing the flexibility in handling different types of information. In this paper, we propose a channel-level variable quantization network to dynamically allocate more bitrates for significant channels and withdraw bitrates for negligible channels. Specifically, we propose a variable quantization controller. It consists of two key components: the channel importance module, which can dynamically learn the importance of channels during training, and the splitting-merging module, which can allocate different bitrates for different channels. We also formulate the quantizer into a Gaussian mixture model manner. Quantitative and qualitative experiments verify the effectiveness of the proposed model and demonstrate that our method achieves superior performance and can produce much better visual reconstructions.
39.Stain Style Transfer of Histopathology Images Via Structure-Preserved Generative Learning ⬇️
Computational histopathology image diagnosis becomes increasingly popular and important, where images are segmented or classified for disease diagnosis by computers. While pathologists do not struggle with color variations in slides, computational solutions usually suffer from this critical issue. To address the issue of color variations in histopathology images, this study proposes two stain style transfer models, SSIM-GAN and DSCSI-GAN, based on the generative adversarial networks. By cooperating structural preservation metrics and feedback of an auxiliary diagnosis net in learning, medical-relevant information presented by image texture, structure, and chroma-contrast features is preserved in color-normalized images. Particularly, the smart treat of chromatic image content in our DSCSI-GAN model helps to achieve noticeable normalization improvement in image regions where stains mix due to histological substances co-localization. Extensive experimentation on public histopathology image sets indicates that our methods outperform prior arts in terms of generating more stain-consistent images, better preserving histological information in images, and obtaining significantly higher learning efficiency. Our python implementation is published on this https URL.
40.Study of Different Deep Learning Approach with Explainable AI for Screening Patients with COVID-19 Symptoms: Using CT Scan and Chest X-ray Image Dataset ⬇️
The outbreak of COVID-19 disease caused more than 100,000 deaths so far in the USA alone. It is necessary to conduct an initial screening of patients with the symptoms of COVID-19 disease to control the spread of the disease. However, it is becoming laborious to conduct the tests with the available testing kits due to the growing number of patients. Some studies proposed CT scan or chest X-ray images as an alternative solution. Therefore, it is essential to use every available resource, instead of either a CT scan or chest X-ray to conduct a large number of tests simultaneously. As a result, this study aims to develop a deep learning-based model that can detect COVID-19 patients with better accuracy both on CT scan and chest X-ray image dataset. In this work, eight different deep learning approaches such as VGG16, InceptionResNetV2, ResNet50, DenseNet201, VGG19, MobilenetV2, NasNetMobile, and ResNet15V2 have been tested on two dataset-one dataset includes 400 CT scan images, and another dataset includes 400 chest X-ray images studied. Besides, Local Interpretable Model-agnostic Explanations (LIME) is used to explain the model's interpretability. Using LIME, test results demonstrate that it is conceivable to interpret top features that should have worked to build a trust AI framework to distinguish between patients with COVID-19 symptoms with other patients.
41.Adma: A Flexible Loss Function for Neural Networks ⬇️
Highly increased interest in Artificial Neural Networks (ANNs) have resulted in impressively wide-ranging improvements in its structure. In this work, we come up with the idea that instead of static plugins that the currently available loss functions are, they should by default be flexible in nature. A flexible loss function can be a more insightful navigator for neural networks leading to higher convergence rates and therefore reaching the optimum accuracy more quickly. The insights to help decide the degree of flexibility can be derived from the complexity of ANNs, the data distribution, selection of hyper-parameters and so on. In the wake of this, we introduce a novel flexible loss function for neural networks. The function is shown to characterize a range of fundamentally unique properties from which, much of the properties of other loss functions are only a subset and varying the flexibility parameter in the function allows it to emulate the loss curves and the learning behavior of prevalent static loss functions. The extensive experimentation performed with the loss function demonstrates that it is able to give state-of-the-art performance on selected data sets. Thus, in all the idea of flexibility itself and the proposed function built upon it carry the potential to open to a new interesting chapter in deep learning research.
42.Parkinson's Disease Detection with Ensemble Architectures based on ILSVRC Models ⬇️
In this work, we explore various neural network architectures using Magnetic Resonance (MR) T1 images of the brain to identify Parkinson's Disease (PD), which is one of the most common neurodegenerative and movement disorders. We propose three ensemble architectures combining some winning Convolutional Neural Network models of ImageNet Large Scale Visual Recognition Challenge (ILSVRC). All of our proposed architectures outperform existing approaches to detect PD from MR images, achieving upto 95% detection accuracy. We also find that when we construct our ensemble architecture using models pretrained on the ImageNet dataset unrelated to PD, the detection performance is significantly better compared to models without any prior training. Our finding suggests a promising direction when no or insufficient training data is available.
43.Approximately Optimal Binning for the Piecewise Constant Approximation of the Normalized Unexplained Variance (nUV) Dissimilarity Measure ⬇️
The recently introduced Matching by Tone Mapping (MTM) dissimilarity measure enables template matching under smooth non-linear distortions and also has a well-established mathematical background. MTM operates by binning the template, but the ideal binning for a particular problem is an open question. By pointing out an important analogy between the well known mutual information (MI) and MTM, we introduce the term "normalized unexplained variance" (nUV) for MTM to emphasize its relevance and applicability beyond image processing. Then, we provide theoretical results on the optimal binning technique for the nUV measure and propose algorithms to find approximate solutions. The theoretical findings are supported by numerical experiments. Using the proposed techniques for binning shows 4-13% increase in terms of AUC scores with statistical significance, enabling us to conclude that the proposed binning techniques have the potential to improve the performance of the nUV measure in real applications.
44.What and Where: Learn to Plug Adapters via NAS for Multi-Domain Learning ⬇️
As an important and challenging problem, multi-domain learning (MDL) typically seeks for a set of effective lightweight domain-specific adapter modules plugged into a common domain-agnostic network. Usually, existing ways of adapter plugging and structure design are handcrafted and fixed for all domains before model learning, resulting in the learning inflexibility and computational intensiveness. With this motivation, we propose to learn a data-driven adapter plugging strategy with Neural Architecture Search (NAS), which automatically determines where to plug for those adapter modules. Furthermore, we propose a NAS-adapter module for adapter structure design in a NAS-driven learning scheme, which automatically discovers effective adapter module structures for different domains. Experimental results demonstrate the effectiveness of our MDL model against existing approaches under the conditions of comparable performance. We will release the code, baselines, and training statistics for all models to facilitate future research.
45.Interpreting Spatially Infinite Generative Models ⬇️
Traditional deep generative models of images and other spatial modalities can only generate fixed sized outputs. The generated images have exactly the same resolution as the training images, which is dictated by the number of layers in the underlying neural network. Recent work has shown, however, that feeding spatial noise vectors into a fully convolutional neural network enables both generation of arbitrary resolution output images as well as training on arbitrary resolution training images. While this work has provided impressive empirical results, little theoretical interpretation was provided to explain the underlying generative process. In this paper we provide a firm theoretical interpretation for infinite spatial generation, by drawing connections to spatial stochastic processes. We use the resulting intuition to improve upon existing spatially infinite generative models to enable more efficient training through a model that we call an infinite generative adversarial network, or
$\infty$ -GAN. Experiments on world map generation, panoramic images and texture synthesis verify the ability of$\infty$ -GAN to efficiently generate images of arbitrary size.
46.COVID TV-UNet: Segmenting COVID-19 Chest CT Images Using Connectivity Imposed U-Net ⬇️
The novel corona-virus disease (COVID-19) pandemic has caused a major outbreak in more than 200 countries around the world, leading to a severe impact on the health and life of many people globally. As of mid-July 2020, more than 12 million people were infected, and more than 570,000 death were reported. Computed Tomography (CT) images can be used as an alternative to the time-consuming RT-PCR test, to detect COVID-19. In this work we propose a segmentation framework to detect chest regions in CT images, which are infected by COVID-19. We use an architecture similar to U-Net model, and train it to detect ground glass regions, on pixel level. As the infected regions tend to form a connected component (rather than randomly distributed pixels), we add a suitable regularization term to the loss function, to promote connectivity of the segmentation map for COVID-19 pixels. 2D-anisotropic total-variation is used for this purpose, and therefore the proposed model is called "TV-UNet". Through experimental results on a relatively large-scale CT segmentation dataset of around 900 images, we show that adding this new regularization term leads to 2% gain on overall segmentation performance compared to the U-Net model. Our experimental analysis, ranging from visual evaluation of the predicted segmentation results to quantitative assessment of segmentation performance (precision, recall, Dice score, and mIoU) demonstrated great ability to identify COVID-19 associated regions of the lungs, achieving a mIoU rate of over 99%, and a Dice score of around 86%.
47.Frequency Domain-based Perceptual Loss for Super Resolution ⬇️
We introduce Frequency Domain Perceptual Loss (FDPL), a loss function for single image super resolution (SR). Unlike previous loss functions used to train SR models, which are all calculated in the pixel (spatial) domain, FDPL is computed in the frequency domain. By working in the frequency domain we can encourage a given model to learn a mapping that prioritizes those frequencies most related to human perception. While the goal of FDPL is not to maximize the Peak Signal to Noise Ratio (PSNR), we found that there is a correlation between decreasing FDPL and increasing PSNR. Training a model with FDPL results in a higher average PSRN (30.94), compared to the same model trained with pixel loss (30.59), as measured on the Set5 image dataset. We also show that our method achieves higher qualitative results, which is the goal of a perceptual loss function. However, it is not clear that the improved perceptual quality is due to the slightly higher PSNR or the perceptual nature of FDPL.
48.Are Visual Explanations Useful? A Case Study in Model-in-the-Loop Prediction ⬇️
We present a randomized controlled trial for a model-in-the-loop regression task, with the goal of measuring the extent to which (1) good explanations of model predictions increase human accuracy, and (2) faulty explanations decrease human trust in the model. We study explanations based on visual saliency in an image-based age prediction task for which humans and learned models are individually capable but not highly proficient and frequently disagree. Our experimental design separates model quality from explanation quality, and makes it possible to compare treatments involving a variety of explanations of varying levels of quality. We find that presenting model predictions improves human accuracy. However, visual explanations of various kinds fail to significantly alter human accuracy or trust in the model - regardless of whether explanations characterize an accurate model, an inaccurate one, or are generated randomly and independently of the input image. These findings suggest the need for greater evaluation of explanations in downstream decision making tasks, better design-based tools for presenting explanations to users, and better approaches for generating explanations.