1.VGGSound: A Large-scale Audio-Visual Dataset ⬇️
Our goal is to collect a large-scale audio-visual dataset with low label noise from videos in the wild using computer vision techniques. The resulting dataset can be used for training and evaluating audio recognition models. We make three contributions. First, we propose a scalable pipeline based on computer vision techniques to create an audio dataset from open-source media. Our pipeline involves obtaining videos from YouTube; using image classification algorithms to localize audio-visual correspondence; and filtering out ambient noise using audio verification. Second, we use this pipeline to curate the VGGSound dataset consisting of more than 210k videos for 310 audio classes. Third, we investigate various Convolutional Neural Network~(CNN) architectures and aggregation approaches to establish audio recognition baselines for our new dataset. Compared to existing audio datasets, VGGSound ensures audio-visual correspondence and is collected under unconstrained conditions. Code and the dataset are available at this http URL
2.Editing in Style: Uncovering the Local Semantics of GANs ⬇️
While the quality of GAN image synthesis has improved tremendously in recent years, our ability to control and condition the output is still limited. Focusing on StyleGAN, we introduce a simple and effective method for making local, semantically-aware edits to a target output image. This is accomplished by borrowing elements from a source image, also a GAN output, via a novel manipulation of style vectors. Our method requires neither supervision from an external model, nor involves complex spatial morphing operations. Instead, it relies on the emergent disentanglement of semantic objects that is learned by StyleGAN during its training. Semantic editing is demonstrated on GANs producing human faces, indoor scenes, cats, and cars. We measure the locality and photorealism of the edits produced by our method, and find that it accomplishes both.
3.Smart Attendance System Usign CNN ⬇️
The research on the attendance system has been going for a very long time, numerous arrangements have been proposed in the last decade to make this system efficient and less time consuming, but all those systems have several flaws. In this paper, we are introducing a smart and efficient system for attendance using face detection and face recognition. This system can be used to take attendance in colleges or offices using real-time face recognition with the help of the Convolution Neural Network(CNN). The conventional methods like Eigenfaces and Fisher faces are sensitive to lighting, noise, posture, obstruction, illumination etc. Hence, we have used CNN to recognize the face and overcome such difficulties. The attendance records will be updated automatically and stored in an excel sheet as well as in a database. We have used MongoDB as a backend database for attendance records.
4.Tensor train rank minimization with nonlocal self-similarity for tensor completion ⬇️
The tensor train (TT) rank has received increasing attention in tensor completion due to its ability to capture the global correlation of high-order tensors (
$\textrm{order} >3$ ). For third order visual data, direct TT rank minimization has not exploited the potential of TT rank for high-order tensors. The TT rank minimization accompany with \emph{ket augmentation}, which transforms a lower-order tensor (e.g., visual data) into a higher-order tensor, suffers from serious block-artifacts. To tackle this issue, we suggest the TT rank minimization with nonlocal self-similarity for tensor completion by simultaneously exploring the spatial, temporal/spectral, and nonlocal redundancy in visual data. More precisely, the TT rank minimization is performed on a formed higher-order tensor called group by stacking similar cubes, which naturally and fully takes advantage of the ability of TT rank for high-order tensors. Moreover, the perturbation analysis for the TT low-rankness of each group is established. We develop the alternating direction method of multipliers tailored for the specific structure to solve the proposed model. Extensive experiments demonstrate that the proposed method is superior to several existing state-of-the-art methods in terms of both qualitative and quantitative measures.
5.Action Sequence Predictions of Vehicles in Urban Environments using Map and Social Context ⬇️
This work studies the problem of predicting the sequence of future actions for surround vehicles in real-world driving scenarios. To this aim, we make three main contributions. The first contribution is an automatic method to convert the trajectories recorded in real-world driving scenarios to action sequences with the help of HD maps. The method enables automatic dataset creation for this task from large-scale driving data. Our second contribution lies in applying the method to the well-known traffic agent tracking and prediction dataset Argoverse, resulting in 228,000 action sequences. Additionally, 2,245 action sequences were manually annotated for testing. The third contribution is to propose a novel action sequence prediction method by integrating past positions and velocities of the traffic agents, map information and social context into a single end-to-end trainable neural network. Our experiments prove the merit of the data creation method and the value of the created dataset - prediction performance improves consistently with the size of the dataset and shows that our action prediction method outperforms comparing models.
6.Image Captioning through Image Transformer ⬇️
Automatic captioning of images is a task that combines the challenges of image analysis and text generation. One important aspect in captioning is the notion of attention: How to decide what to describe and in which order. Inspired by the successes in text analysis and translation, previous work have proposed the \textit{transformer} architecture for image captioning. However, the structure between the \textit{semantic units} in images (usually the detected regions from object detection model) and sentences (each single word) is different. Limited work has been done to adapt the transformer's internal architecture to images. In this work, we introduce the \textbf{\textit{image transformer}}, which consists of a modified encoding transformer and an implicit decoding transformer, motivated by the relative spatial relationship between image regions. Our design widen the original transformer layer's inner architecture to adapt to the structure of images. With only regions feature as inputs, our model achieves new state-of-the-art performance on both MSCOCO offline and online testing benchmarks.
7.Deepfake Video Forensics based on Transfer Learning ⬇️
Deeplearning has been used to solve complex problems in various domains. As it advances, it also creates applications which become a major threat to our privacy, security and even to our Democracy. Such an application which is being developed recently is the "Deepfake". Deepfake models can create fake images and videos that humans cannot differentiate them from the genuine ones. Therefore, the counter application to automatically detect and analyze the digital visual media is necessary in today world. This paper details retraining the image classification models to apprehend the features from each deepfake video frames. After feeding different sets of deepfake clips of video fringes through a pretrained layer of bottleneck in the neural network is made for every video frame, already stated layer contains condense data for all images and exposes artificial manipulations in Deepfake videos. When checking Deepfake videos, this technique received more than 87 per cent accuracy. This technique has been tested on the Face Forensics dataset and obtained good accuracy in detection.
8.Assessing Car Damage using Mask R-CNN ⬇️
Picture based vehicle protection handling is a significant region with enormous degree for mechanization. In this paper we consider the issue of vehicle harm characterization, where a portion of the classifications can be fine-granular. We investigate profound learning based procedures for this reason. At first, we attempt legitimately preparing a CNN. In any case, because of little arrangement of marked information, it doesn't function admirably. At that point, we investigate the impact of space explicit pre-preparing followed by tweaking. At last, we explore different avenues regarding move learning and outfit learning. Trial results show that move learning works superior to space explicit tweaking. We accomplish precision of 89.5% with blend of move and gathering learning.
9.Zero-Shot Learning and its Applications from Autonomous Vehicles to COVID-19 Diagnosis: A Review ⬇️
The challenge of learning a new concept without receiving any examples beforehand is called zero-shot learning (ZSL). One of the major issues in deep learning based methodologies is the requirement of feeding a vast amount of annotated and labelled images by a human to train the network model. ZSL is known for having minimal human intervention by relying only on previously known concepts and auxiliary information. It is an ever-growing research area since it has human-like characteristics in learning new concepts, which makes it applicable in many real-world scenarios, from autonomous vehicles to surveillance systems to medical imaging and COVID-19 CT scan-based diagnosis. In this paper, we present the definition of the problem, we review over fundamentals, and the challenging steps of Zero-shot learning, including recent categories of solutions, motivations behind each approach, and their advantages over other categories. Inspired from different settings and extensions, we have a broaden solution called one/few-shot learning. We then review thorough datasets, the variety of splits, and the evaluation protocols proposed so far. Finally, we discuss the recent applications and possible future directions of ZSL. We aim to convey a useful intuition through this paper towards the goal of handling computer vision learning tasks more similar to the way humans learn.
10.Minimal Rolling Shutter Absolute Pose with Unknown Focal Length and Radial Distortion ⬇️
The internal geometry of most modern consumer cameras is not adequately described by the perspective projection. Almost all cameras exhibit some radial lens distortion and are equipped with an electronic rolling shutter that induces distortions when the camera moves during the image capture. When focal length has not been calibrated offline, the parameters that describe the radial and rolling shutter distortions are usually unknown. While for global shutter cameras, minimal solvers for the absolute camera pose and unknown focal length and radial distortion are available, solvers for the rolling shutter were missing. We present the first minimal solutions for the absolute pose of a rolling shutter camera with unknown rolling shutter parameters, focal length, and radial distortion. Our new minimal solvers combine iterative schemes designed for calibrated rolling shutter cameras with fast generalized eigenvalue and Groebner basis solvers. In a series of experiments, with both synthetic and real data, we show that our new solvers provide accurate estimates of the camera pose, rolling shutter parameters, focal length, and radial distortion parameters.
11.Single-Side Domain Generalization for Face Anti-Spoofing ⬇️
Existing domain generalization methods for face anti-spoofing endeavor to extract common differentiation features to improve the generalization. However, due to large distribution discrepancies among fake faces of different domains, it is difficult to seek a compact and generalized feature space for the fake faces. In this work, we propose an end-to-end single-side domain generalization framework (SSDG) to improve the generalization ability of face anti-spoofing. The main idea is to learn a generalized feature space, where the feature distribution of the real faces is compact while that of the fake ones is dispersed among domains but compact within each domain. Specifically, a feature generator is trained to make only the real faces from different domains undistinguishable, but not for the fake ones, thus forming a single-side adversarial learning. Moreover, an asymmetric triplet loss is designed to constrain the fake faces of different domains separated while the real ones aggregated. The above two points are integrated into a unified framework in an end-to-end training manner, resulting in a more generalized class boundary, especially good for samples from novel domains. Feature and weight normalization is incorporated to further improve the generalization ability. Extensive experiments show that our proposed approach is effective and outperforms the state-of-the-art methods on four public databases.
12.Counting of Grapevine Berries in Images via Semantic Segmentation using Convolutional Neural Networks ⬇️
The extraction of phenotypic traits is often very time and labour intensive. Especially the investigation in viticulture is restricted to an on-site analysis due to the perennial nature of grapevine. Traditionally skilled experts examine small samples and extrapolate the results to a whole plot. Thereby different grapevine varieties and training systems, e.g. vertical shoot positioning (VSP) and semi minimal pruned hedges (SMPH) pose different challenges. In this paper we present an objective framework based on automatic image analysis which works on two different training systems. The images are collected semi automatic by a camera system which is installed in a modified grape harvester. The system produces overlapping images from the sides of the plants. Our framework uses a convolutional neural network to detect single berries in images by performing a semantic segmentation. Each berry is then counted with a connected component algorithm. We compare our results with the Mask-RCNN, a state-of-the-art network for instance segmentation and with a regression approach for counting. The experiments presented in this paper show that we are able to detect green berries in images despite of different training systems. We achieve an accuracy for the berry detection of 94.0% in the VSP and 85.6% in the SMPH.
13.Retinal vessel segmentation by probing adaptive to lighting variations ⬇️
We introduce a novel method to extract the vessels in eye fun-dus images which is adaptive to lighting variations. In the Logarithmic Image Processing framework, a 3-segment probe detects the vessels by probing the topographic surface of an image from below. A map of contrasts between the probe and the image allows to detect the vessels by a threshold. In a lowly contrasted image, results show that our method better extract the vessels than another state-of the-art method. In a highly contrasted image database (DRIVE) with a reference , ours has an accuracy of 0.9454 which is similar or better than three state-of-the-art methods and below three others. The three best methods have a higher accuracy than a manual segmentation by another expert. Importantly, our method automatically adapts to the lighting conditions of the image acquisition.
14.Motion Guided 3D Pose Estimation from Videos ⬇️
We propose a new loss function, called motion loss, for the problem of monocular 3D Human pose estimation from 2D pose. In computing motion loss, a simple yet effective representation for keypoint motion, called pairwise motion encoding, is introduced. We design a new graph convolutional network architecture, U-shaped GCN (UGCN). It captures both short-term and long-term motion information to fully leverage the additional supervision from the motion loss. We experiment training UGCN with the motion loss on two large scale benchmarks: Human3.6M and MPI-INF-3DHP. Our model surpasses other state-of-the-art models by a large margin. It also demonstrates strong capacity in producing smooth 3D sequences and recovering keypoint motion.
15.Skeleton Focused Human Activity Recognition in RGB Video ⬇️
The data-driven approach that learns an optimal representation of vision features like skeleton frames or RGB videos is currently a dominant paradigm for activity recognition. While great improvements have been achieved from existing single modal approaches with increasingly larger datasets, the fusion of various data modalities at the feature level has seldom been attempted. In this paper, we propose a multimodal feature fusion model that utilizes both skeleton and RGB modalities to infer human activity. The objective is to improve the activity recognition accuracy by effectively utilizing the mutual complemental information among different data modalities. For the skeleton modality, we propose to use a graph convolutional subnetwork to learn the skeleton representation. Whereas for the RGB modality, we will use the spatial-temporal region of interest from RGB videos and take the attention features from the skeleton modality to guide the learning process. The model could be either individually or uniformly trained by the back-propagation algorithm in an end-to-end manner. The experimental results for the NTU-RGB+D and Northwestern-UCLA Multiview datasets achieved state-of-the-art performance, which indicates that the proposed skeleton-driven attention mechanism for the RGB modality increases the mutual communication between different data modalities and brings more discriminative features for inferring human activities.
16.Effective Human Activity Recognition Based on Small Datasets ⬇️
Most recent work on vision-based human activity recognition (HAR) focuses on designing complex deep learning models for the task. In so doing, there is a requirement for large datasets to be collected. As acquiring and processing large training datasets are usually very expensive, the problem of how dataset size can be reduced without affecting recognition accuracy has to be tackled. To do so, we propose a HAR method that consists of three steps: (i) data transformation involving the generation of new features based on transforming of raw data, (ii) feature extraction involving the learning of a classifier based on the AdaBoost algorithm and the use of training data consisting of the transformed features, and (iii) parameter determination and pattern recognition involving the determination of parameters based on the features generated in (ii) and the use of the parameters as training data for deep learning algorithms to be used to recognize human activities. Compared to existing approaches, this proposed approach has the advantageous characteristics that it is simple and robust. The proposed approach has been tested with a number of experiments performed on a relatively small real dataset. The experimental results indicate that using the proposed method, human activities can be more accurately recognized even with smaller training data size.
17.Deep Transfer Learning For Plant Center Localization ⬇️
Plant phenotyping focuses on the measurement of plant characteristics throughout the growing season, typically with the goal of evaluating genotypes for plant breeding. Estimating plant location is important for identifying genotypes which have low emergence, which is also related to the environment and management practices such as fertilizer applications. The goal of this paper is to investigate methods that estimate plant locations for a field-based crop using RGB aerial images captured using Unmanned Aerial Vehicles (UAVs). Deep learning approaches provide promising capability for locating plants observed in RGB images, but they require large quantities of labeled data (ground truth) for training. Using a deep learning architecture fine-tuned on a single field or a single type of crop on fields in other geographic areas or with other crops may not have good results. The problem of generating ground truth for each new field is labor-intensive and tedious. In this paper, we propose a method for estimating plant centers by transferring an existing model to a new scenario using limited ground truth data. We describe the use of transfer learning using a model fine-tuned for a single field or a single type of plant on a varied set of similar crops and fields. We show that transfer learning provides promising results for detecting plant locations.
18.Video Contents Understanding using Deep Neural Networks ⬇️
We propose a novel application of Transfer Learning to classify video-frame sequences over multiple classes. This is a pre-weighted model that does not require to train a fresh CNN. This representation is achieved with the advent of "deep neural network" (DNN), which is being studied these days by many researchers. We utilize the classical approaches for video classification task using object detection techniques for comparison, such as "Google Video Intelligence API" and this study will run experiments as to how those architectures would perform in foggy or rainy weather conditions. Experimental evaluation on video collections shows that the new proposed classifier achieves superior performance over existing solutions.
19.Deflating Dataset Bias Using Synthetic Data Augmentation ⬇️
Deep Learning has seen an unprecedented increase in vision applications since the publication of large-scale object recognition datasets and introduction of scalable compute hardware. State-of-the-art methods for most vision tasks for Autonomous Vehicles (AVs) rely on supervised learning and often fail to generalize to domain shifts and/or outliers. Dataset diversity is thus key to successful real-world deployment. No matter how big the size of the dataset, capturing long tails of the distribution pertaining to task-specific environmental factors is impractical. The goal of this paper is to investigate the use of targeted synthetic data augmentation - combining the benefits of gaming engine simulations and sim2real style transfer techniques - for filling gaps in real datasets for vision tasks. Empirical studies on three different computer vision tasks of practical use to AVs - parking slot detection, lane detection and monocular depth estimation - consistently show that having synthetic data in the training mix provides a significant boost in cross-dataset generalization performance as compared to training on real data only, for the same size of the training set.
20.Less is More: Sample Selection and Label Conditioning Improve Skin Lesion Segmentation ⬇️
Segmenting skin lesions images is relevant both for itself and for assisting in lesion classification, but suffers from the challenge in obtaining annotated data. In this work, we show that segmentation may improve with less data, by selecting the training samples with best inter-annotator agreement, and conditioning the ground-truth masks to remove excessive detail. We perform an exhaustive experimental design considering several sources of variation, including three different test sets, two different deep-learning architectures, and several replications, for a total of 540 experimental runs. We found that sample selection and detail removal may have impacts corresponding, respectively, to 12% and 16% of the one obtained by picking a better deep-learning model.
21.Boosting Deep Open World Recognition by Clustering ⬇️
While convolutional neural networks have brought significant advances in robot vision, their ability is often limited to closed world scenarios, where the number of semantic concepts to be recognized is determined by the available training set. Since it is practically impossible to capture all possible semantic concepts present in the real world in a single training set, we need to break the closed world assumption, equipping our robot with the capability to act in an open world. To provide such ability, a robot vision system should be able to (i) identify whether an instance does not belong to the set of known categories (i.e. open set recognition), and (ii) extend its knowledge to learn new classes over time (i.e. incremental learning). In this work, we show how we can boost the performance of deep open world recognition algorithms by means of a new loss formulation enforcing a global to local clustering of class-specific features. In particular, a first loss term, i.e. global clustering, forces the network to map samples closer to the class centroid they belong to while the second one, local clustering, shapes the representation space in such a way that samples of the same class get closer in the representation space while pushing away neighbours belonging to other classes. Moreover, we propose a strategy to learn class-specific rejection thresholds, instead of heuristically estimating a single global threshold, as in previous works. Experiments on RGB-D Object and Core50 datasets show the effectiveness of our approach.
22.Pyramid Attention Networks for Image Restoration ⬇️
Self-similarity refers to the image prior widely used in image restoration algorithms that small but similar patterns tend to occur at different locations and scales. However, recent advanced deep convolutional neural network based methods for image restoration do not take full advantage of self-similarities by relying on self-attention neural modules that only process information at the same scale. To solve this problem, we present a novel Pyramid Attention module for image restoration, which captures long-range feature correspondences from a multi-scale feature pyramid. Inspired by the fact that corruptions, such as noise or compression artifacts, drop drastically at coarser image scales, our attention module is designed to be able to borrow clean signals from their "clean" correspondences at the coarser levels. The proposed pyramid attention module is a generic building block that can be flexibly integrated into various neural architectures. Its effectiveness is validated through extensive experiments on multiple image restoration tasks: image denoising, demosaicing, compression artifact reduction, and super resolution. Without any bells and whistles, our PANet (pyramid attention module with simple network backbones) can produce state-of-the-art results with superior accuracy and visual quality.
23.CMRNet++: Map and Camera Agnostic Monocular Visual Localization in LiDAR Maps ⬇️
Localization is a critically essential and crucial enabler of autonomous robots. While deep learning has made significant strides in many computer vision tasks, it is still yet to make a sizeable impact on improving capabilities of metric visual localization. One of the major hindrances has been the inability of existing Convolutional Neural Network (CNN)-based pose regression methods to generalize to previously unseen places. Our recently introduced CMRNet effectively addresses this limitation by enabling map independent monocular localization in LiDAR-maps. In this paper, we now take it a step further by introducing CMRNet++ which is a significantly more robust model that not only generalizes to new places effectively, but is also independent of the camera parameters. We enable this capability by moving any metric reasoning outside of the learning process. Extensive evaluations of our proposed CMRNet++ on three challenging autonomous driving datasets namely, KITTI, Argoverse, and Lyft Level5, demonstrate that our network substantially outperforms CMRNet as well as other baselines by a large margin. More importantly, for the first-time, we demonstrate the ability of a deep learning approach to accurately localize without any retraining or fine-tuning in a completely new environment and independent of the camera parameters.
24.Cross-modal Speaker Verification and Recognition: A Multilingual Perspective ⬇️
Recent years have seen a surge in finding association between faces and voices within a cross-modal biometric application along with speaker recognition. Inspired from this, we introduce a challenging task in establishing association between faces and voices across multiple languages spoken by the same set of persons. The aim of this paper is to answer two closely related questions: \textit{"Is face-voice association language independent?"} and \textit{"Can a speaker be recognised irrespective of the spoken language?"}. These two questions are very important to understand effectiveness and to boost development of multilingual biometric systems. To answer them, we collected a Multilingual Audio-Visual dataset, containing human speech clips of
$154$ identities with$3$ language annotations extracted from various videos uploaded online. Extensive experiments on the three splits of the proposed dataset have been performed to investigate and answer these novel research questions that clearly point out the relevance of the multilingual problem.
25.Beyond Instructional Videos: Probing for More Diverse Visual-Textual Grounding on YouTube ⬇️
Pretraining from unlabelled web videos has quickly become the de-facto means of achieving high performance on many video understanding tasks. Features are learned via prediction of grounded relationships between visual content and automatic speech recognition (ASR) tokens. However, prior pretraining work has been limited to only instructional videos, a domain that, a priori, we expect to be relatively "easy:" speakers in instructional videos will often reference the literal objects/actions being depicted. Because instructional videos make up only a fraction of the web's diverse video content, we ask: can similar models be trained on broader corpora? And, if so, what types of videos are "grounded" and what types are not? We examine the diverse YouTube8M corpus, first verifying that it contains many non-instructional videos via crowd labeling. We pretrain a representative model on YouTube8M and study its success and failure cases. We find that visual-textual grounding is indeed possible across previously unexplored video categories, and that pretraining on a more diverse set still results in representations that generalize to both non-instructional and instructional domains.
26.Seeing voices and hearing voices: learning discriminative embeddings using cross-modal self-supervision ⬇️
The goal of this work is to train discriminative cross-modal embeddings without access to manually annotated data. Recent advances in self-supervised learning have shown that effective representations can be learnt from natural cross-modal synchrony. We build on earlier work to train embeddings that are more discriminative for uni-modal downstream tasks. To this end, we propose a novel training strategy that not only optimises metrics across modalities, but also enforces intra-class feature separation within each of the modalities. The effectiveness of the method is demonstrated on two downstream tasks: lip reading using the features trained on audio-visual synchronisation, and speaker recognition using the features trained for cross-modal biometric matching. The proposed method outperforms state-of-the-art self-supervised baselines by a signficant margin.
27.A Wearable Social Interaction Aid for Children with Autism ⬇️
With most recent estimates giving an incidence rate of 1 in 68 children in the United States, the autism spectrum disorder (ASD) is a growing public health crisis. Many of these children struggle to make eye contact, recognize facial expressions, and engage in social interactions. Today the standard for treatment of the core autism-related deficits focuses on a form of behavior training known as Applied Behavioral Analysis. To address perceived deficits in expression recognition, ABA approaches routinely involve the use of prompts such as flash cards for repetitive emotion recognition training via memorization. These techniques must be administered by trained practitioners and often at clinical centers that are far outnumbered by and out of reach from the many children and families in need of attention. Waitlists for access are up to 18 months long, and this wait may lead to children regressing down a path of isolation that worsens their long-term prognosis. There is an urgent need to innovate new methods of care delivery that can appropriately empower caregivers of children at risk or with a diagnosis of autism, and that capitalize on mobile tools and wearable devices for use outside of clinical settings.
28.A Fast 3D CNN for Hyperspectral Image Classification ⬇️
Hyperspectral imaging (HSI) has been extensively utilized for a number of real-world applications. HSI classification (HSIC) is a challenging task due to high inter-class similarity, high intra-class variability, overlapping, and nested regions. A 2D Convolutional Neural Network (CNN) is a viable approach whereby HSIC highly depends on both Spectral-Spatial information, therefore, 3D CNN can be an alternative but highly computational complex due to the volume and spectral dimensions. Furthermore, these models do not extract quality feature maps and may underperform over the regions having similar textures. Therefore, this work proposed a 3D CNN model that utilizes both spatial-spectral feature maps to attain good performance. In order to achieve the said performance, the HSI cube is first divided into small overlapping 3D patches. Later these patches are processed to generate 3D feature maps using a 3D kernel function over multiple contiguous bands that persevere the spectral information as well. Benchmark HSI datasets (Pavia University, Salinas and Indian Pines) are considered to validate the performance of our proposed method. The results are further compared with several state-of-the-art methods.
29.Inf-Net: Automatic COVID-19 Lung Infection Segmentation from CT Scans ⬇️
Coronavirus Disease 2019 (COVID-19) spread globally in early 2020, causing the world to face an existential health crisis. Automated detection of lung infections from computed tomography (CT) images offers a great potential to augment the traditional healthcare strategy for tackling COVID-19. However, segmenting infected regions from CT scans faces several challenges, including high variation in infection characteristics, and low intensity contrast between infections and normal tissues. Further, collecting a large amount of data is impractical within a short time period, inhibiting the training of a deep model. To address these challenges, a novel COVID-19 Lung Infection Segmentation Deep Network (Inf-Net) is proposed to automatically identify infected regions from chest CT scans. In our Inf-Net, a parallel partial decoder is used to aggregate the high-level features and generate a global map. Then, the implicit reverse attention and explicit edge-attention are utilized to model the boundaries and enhance the representations. Moreover, to alleviate the shortage of labeled data, we present a semi-supervised segmentation framework based on a randomly selected propagation strategy, which only requires a few labeled images and leverages primarily unlabeled data. Our semi-supervised framework can improve the learning ability and achieve a higher performance. Extensive experiments on a COVID-19 infection dataset demonstrate that the proposed COVID-SemiSeg outperforms most cutting-edge segmentation models and advances the state-of-the-art performance.
30.Informative Scene Decomposition for Crowd Analysis, Comparison and Simulation Guidance ⬇️
Crowd simulation is a central topic in several fields including graphics. To achieve high-fidelity simulations, data has been increasingly relied upon for analysis and simulation guidance. However, the information in real-world data is often noisy, mixed and unstructured, making it difficult for effective analysis, therefore has not been fully utilized. With the fast-growing volume of crowd data, such a bottleneck needs to be addressed. In this paper, we propose a new framework which comprehensively tackles this problem. It centers at an unsupervised method for analysis. The method takes as input raw and noisy data with highly mixed multi-dimensional (space, time and dynamics) information, and automatically structure it by learning the correlations among these dimensions. The dimensions together with their correlations fully describe the scene semantics which consists of recurring activity patterns in a scene, manifested as space flows with temporal and dynamics profiles. The effectiveness and robustness of the analysis have been tested on datasets with great variations in volume, duration, environment and crowd dynamics. Based on the analysis, new methods for data visualization, simulation evaluation and simulation guidance are also proposed. Together, our framework establishes a highly automated pipeline from raw data to crowd analysis, comparison and simulation guidance. Extensive experiments and evaluations have been conducted to show the flexibility, versatility and intuitiveness of our framework.
31.DR-SPAAM: A Spatial-Attention and Auto-regressive Model for Person Detection in 2D Range Data ⬇️
Detecting persons using a 2D LiDAR is a challenging task due to the low information content of 2D range data. To alleviate the problem caused by the sparsity of the LiDAR points, current state-of-the-art methods fuse multiple previous scans and perform detection using the combined scans. The downside of such a backward looking fusion is that all the scans need to be aligned explicitly, and the necessary alignment operation makes the whole pipeline more expensive -- often too expensive for real-world applications. In this paper, we propose a person detection network which uses an alternative strategy to combine scans obtained at different times. Our method, Distance Robust SPatial Attention and Auto-regressive Model (DR-SPAAM), follows a forward looking paradigm. It keeps the intermediate features from the backbone network as a template and recurrently updates the template when a new scan becomes available. The updated feature template is in turn used for detecting persons currently in the scene. On the DROW dataset, our method outperforms the existing state-of-the-art, while being approximately four times faster, running at 87.2 FPS on a laptop with a dedicated GPU and at 22.6 FPS on an NVIDIA Jetson AGX embedded GPU. We release our code in PyTorch and a ROS node including pre-trained models.
32.Image Morphing with Perceptual Constraints and STN Alignment ⬇️
In image morphing, a sequence of plausible frames are synthesized and composited together to form a smooth transformation between given instances. Intermediates must remain faithful to the input, stand on their own as members of the set, and maintain a well-paced visual transition from one to the next. In this paper, we propose a conditional GAN morphing framework operating on a pair of input images. The network is trained to synthesize frames corresponding to temporal samples along the transformation, and learns a proper shape prior that enhances the plausibility of intermediate frames. While individual frame plausibility is boosted by the adversarial setup, a special training protocol producing sequences of frames, combined with a perceptual similarity loss, promote smooth transformation over time. Explicit stating of correspondences is replaced with a grid-based freeform deformation spatial transformer that predicts the geometric warp between the inputs, instituting the smooth geometric effect by bringing the shapes into an initial alignment. We provide comparisons to classic as well as latent space morphing techniques, and demonstrate that, given a set of images for self-supervision, our network learns to generate visually pleasing morphing effects featuring believable in-betweens, with robustness to changes in shape and texture, requiring no correspondence annotation.
33.The International Workshop on Osteoarthritis Imaging Knee MRI Segmentation Challenge: A Multi-Institute Evaluation and Analysis Framework on a Standardized Dataset ⬇️
Purpose: To organize a knee MRI segmentation challenge for characterizing the semantic and clinical efficacy of automatic segmentation methods relevant for monitoring osteoarthritis progression.
Methods: A dataset partition consisting of 3D knee MRI from 88 subjects at two timepoints with ground-truth articular (femoral, tibial, patellar) cartilage and meniscus segmentations was standardized. Challenge submissions and a majority-vote ensemble were evaluated using Dice score, average symmetric surface distance, volumetric overlap error, and coefficient of variation on a hold-out test set. Similarities in network segmentations were evaluated using pairwise Dice correlations. Articular cartilage thickness was computed per-scan and longitudinally. Correlation between thickness error and segmentation metrics was measured using Pearson's coefficient. Two empirical upper bounds for ensemble performance were computed using combinations of model outputs that consolidated true positives and true negatives.
Results: Six teams (T1-T6) submitted entries for the challenge. No significant differences were observed across all segmentation metrics for all tissues (p=1.0) among the four top-performing networks (T2, T3, T4, T6). Dice correlations between network pairs were high (>0.85). Per-scan thickness errors were negligible among T1-T4 (p=0.99) and longitudinal changes showed minimal bias (<0.03mm). Low correlations (<0.41) were observed between segmentation metrics and thickness error. The majority-vote ensemble was comparable to top performing networks (p=1.0). Empirical upper bound performances were similar for both combinations (p=1.0).
Conclusion: Diverse networks learned to segment the knee similarly where high segmentation accuracy did not correlate to cartilage thickness accuracy. Voting ensembles did not outperform individual networks but may help regularize individual models.
34.Span-based Localizing Network for Natural Language Video Localization ⬇️
Given an untrimmed video and a text query, natural language video localization (NLVL) is to locate a matching span from the video that semantically corresponds to the query. Existing solutions formulate NLVL either as a ranking task and apply multimodal matching architecture, or as a regression task to directly regress the target video span. In this work, we address NLVL task with a span-based QA approach by treating the input video as text passage. We propose a video span localizing network (VSLNet), on top of the standard span-based QA framework, to address NLVL. The proposed VSLNet tackles the differences between NLVL and span-based QA through a simple and yet effective query-guided highlighting (QGH) strategy. The QGH guides VSLNet to search for matching video span within a highlighted region. Through extensive experiments on three benchmark datasets, we show that the proposed VSLNet outperforms the state-of-the-art methods; and adopting span-based QA framework is a promising direction to solve NLVL.
35.An Auto-Encoder Strategy for Adaptive Image Segmentation ⬇️
Deep neural networks are powerful tools for biomedical image segmentation. These models are often trained with heavy supervision, relying on pairs of images and corresponding voxel-level labels. However, obtaining segmentations of anatomical regions on a large number of cases can be prohibitively expensive. Thus there is a strong need for deep learning-based segmentation tools that do not require heavy supervision and can continuously adapt. In this paper, we propose a novel perspective of segmentation as a discrete representation learning problem, and present a variational autoencoder segmentation strategy that is flexible and adaptive. Our method, called Segmentation Auto-Encoder (SAE), leverages all available unlabeled scans and merely requires a segmentation prior, which can be a single unpaired segmentation image. In experiments, we apply SAE to brain MRI scans. Our results show that SAE can produce good quality segmentations, particularly when the prior is good. We demonstrate that a Markov Random Field prior can yield significantly better results than a spatially independent prior. Our code is freely available at this https URL.
36.Unmanned Aerial Systems for Wildland and Forest Fires: Sensing, Perception, Cooperation and Assistance ⬇️
Wildfires represent an important natural risk causing economic losses, human death and important environmental damage. In recent years, we witness an increase in fire intensity and frequency. Research has been conducted towards the development of dedicated solutions for wildland and forest fire assistance and fighting. Systems were proposed for the remote detection and tracking of fires. These systems have shown improvements in the area of efficient data collection and fire characterization within small scale environments. However, wildfires cover large areas making some of the proposed ground-based systems unsuitable for optimal coverage. To tackle this limitation, Unmanned Aerial Systems (UAS) were proposed. UAS have proven to be useful due to their maneuverability, allowing for the implementation of remote sensing, allocation strategies and task planning. They can provide a low-cost alternative for the prevention, detection and real-time support of firefighting. In this paper we review previous work related to the use of UAS in wildfires. Onboard sensor instruments, fire perception algorithms and coordination strategies are considered. In addition, we present some of the recent frameworks proposing the use of both aerial vehicles and Unmanned Ground Vehicles (UV) for a more efficient wildland firefighting strategy at a larger scale.
37.Histogram-based Auto Segmentation: A Novel Approach to Segmenting Integrated Circuit Structures from SEM Images ⬇️
In the Reverse Engineering and Hardware Assurance domain, a majority of the data acquisition is done through electron microscopy techniques such as Scanning Electron Microscopy (SEM). However, unlike its counterparts in optical imaging, only a limited number of techniques are available to enhance and extract information from the raw SEM images. In this paper, we introduce an algorithm to segment out Integrated Circuit (IC) structures from the SEM image. Unlike existing algorithms discussed in this paper, this algorithm is unsupervised, parameter-free and does not require prior information on the noise model or features in the target image making it effective in low quality image acquisition scenarios as well. Furthermore, the results from the application of the algorithm on various structures and layers in the IC are reported and discussed.
38.Character-level Japanese Text Generation with Attention Mechanism for Chest Radiography Diagnosis ⬇️
Chest radiography is a general method for diagnosing a patient's condition and identifying important information; therefore, radiography is used extensively in routine medical practice in various situations, such as emergency medical care and medical checkup. However, a high level of expertise is required to interpret chest radiographs. Thus, medical specialists spend considerable time in diagnosing such huge numbers of radiographs. In order to solve these problems, methods for generating findings have been proposed. However, the study of generating chest radiograph findings has primarily focused on the English language, and to the best of our knowledge, no studies have studied Japanese data on this subject. There are two challenges involved in generating findings in the Japanese language. The first challenge is that word splitting is difficult because the boundaries of Japanese word are not clear. The second challenge is that there are numerous orthographic variants. For deal with these two challenges, we proposed an end-to-end model that generates Japanese findings at the character-level from chest radiographs. In addition, we introduced the attention mechanism to improve not only the accuracy, but also the interpretation ability of the results. We evaluated the proposed method using a public dataset with Japanese findings. The effectiveness of the proposed method was confirmed using the Bilingual Evaluation Understudy score. And, we were confirmed from the generated findings that the proposed method was able to consider the orthographic variants. Furthermore, we confirmed via visual inspection that the attention mechanism captures the features and positional information of radiographs.
39.Minority Reports Defense: Defending Against Adversarial Patches ⬇️
Deep learning image classification is vulnerable to adversarial attack, even if the attacker changes just a small patch of the image. We propose a defense against patch attacks based on partially occluding the image around each candidate patch location, so that a few occlusions each completely hide the patch. We demonstrate on CIFAR-10, Fashion MNIST, and MNIST that our defense provides certified security against patch attacks of a certain size.