PyTorchKR Papers

최신 논문

총 5,358편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2007.13666공식 코드 · Papers with Code

3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised Learning

3D human shape and pose estimation from monocular images has been an active area of research in computer vision, having a substantial impact on the development of new applications, from activity recognition to creating virtual avatars. Existing deep learning methods for 3D human shape and pose estimation rely on relatively high-resolution input images; however, high-resolution visual content is not always available in several practical scenarios such as video surveillance and sports broadcasting. Low-resolution images in real scenarios can vary in a wide range of sizes, and a model trained in one resolution does not typically degrade gracefully across resolutions. Two common approaches to solve the problem of low-resolution input are applying super-resolution techniques to the input images which may result in visual artifacts, or simply training one model for each resolution, which is impractical in many realistic applications. To address the above issues, this paper proposes a novel algorithm called RSC-Net, which consists of a Resolution-aware network, a Self-supervision loss, and a Contrastive learning scheme. The proposed network is able to learn the 3D body shape and pose across different resolutions with a single model. The self-supervision loss encourages scale-consistency of the output, and the contrastive learning scheme enforces scale-consistency of the deep features. We show that both these new training losses provide robustness when learning 3D shape and pose in a weakly-supervised manner. Extensive experiments demonstrate that the RSC-Net can achieve consistently better results than the state-of-the-art methods for challenging low-resolution images.

arXiv:2007.12368

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 focus on object shapes, learning concepts like spatial orientation and part correlation, while acting as a regularizer for the classification task over multiple visual domains. 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.

arXiv:2007.12494공식 코드 · Papers with Code

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 https://github.com/jiaxiangshang/MGCNet.

arXiv:2007.11866공식 코드 · Papers with Code

Reliable Label Bootstrapping for Semi-Supervised Learning

Reducing the amount of labels required to train convolutional neural networks without performance degradation is key to effectively reduce human annotation efforts. We propose Reliable Label Bootstrapping (ReLaB), an unsupervised preprossessing algorithm which improves the performance of semi-supervised algorithms in extremely low supervision settings. Given a dataset with few labeled samples, we first learn meaningful self-supervised, latent features for the data. Second, a label propagation algorithm propagates the known labels on the unsupervised features, effectively labeling the full dataset in an automatic fashion. Third, we select a subset of correctly labeled (reliable) samples using a label noise detection algorithm. Finally, we train a semi-supervised algorithm on the extended subset. We show that the selection of the network architecture and the self-supervised algorithm are important factors to achieve successful label propagation and demonstrate that ReLaB substantially improves semi-supervised learning in scenarios of very limited supervision on CIFAR-10, CIFAR-100 and mini-ImageNet. We reach average error rates of $\boldsymbol{22.34}$ with 1 random labeled sample per class on CIFAR-10 and lower this error to $\boldsymbol{8.46}$ when the labeled sample in each class is highly representative. Our work is fully reproducible: https://github.com/PaulAlbert31/ReLaB.

arXiv:2007.11450

4S-DT: Self Supervised Super Sample Decomposition for Transfer learning with application to COVID-19 detection

Due to the high availability of large-scale annotated image datasets, knowledge transfer from pre-trained models showed outstanding performance in medical image classification. However, building a robust image classification model for datasets with data irregularity or imbalanced classes can be a very challenging task, especially in the medical imaging domain. In this paper, we propose a novel deep convolutional neural network, we called Self Supervised Super Sample Decomposition for Transfer learning (4S-DT) model. 4S-DT encourages a coarse-to-fine transfer learning from large-scale image recognition tasks to a specific chest X-ray image classification task using a generic self-supervised sample decomposition approach. Our main contribution is a novel self-supervised learning mechanism guided by a super sample decomposition of unlabelled chest X-ray images. 4S-DT helps in improving the robustness of knowledge transformation via a downstream learning strategy with a class-decomposition layer to simplify the local structure of the data. 4S-DT can deal with any irregularities in the image dataset by investigating its class boundaries using a downstream class-decomposition mechanism. We used 50,000 unlabelled chest X-ray images to achieve our coarse-to-fine transfer learning with an application to COVID-19 detection, as an exemplar. 4S-DT has achieved a high accuracy of 99.8% (95% CI: 99.44%, 99.98%) in the detection of COVID-19 cases on a large dataset and an accuracy of 97.54% (95%$ CI: 96.22%, 98.91%) on an extended test set enriched by augmented images of a small dataset, out of which all real COVID-19 cases were detected, which was the highest accuracy obtained when compared to other methods.

arXiv:2007.11498공식 코드 · Papers with Code

CrossTransformers: spatially-aware few-shot transfer

Given new tasks with very little data$-$such as new classes in a classification problem or a domain shift in the input$-$performance of modern vision systems degrades remarkably quickly. In this work, we illustrate how the neural network representations which underpin modern vision systems are subject to supervision collapse, whereby they lose any information that is not necessary for performing the training task, including information that may be necessary for transfer to new tasks or domains. We then propose two methods to mitigate this problem. First, we employ self-supervised learning to encourage general-purpose features that transfer better. Second, we propose a novel Transformer based neural network architecture called CrossTransformers, which can take a small number of labeled images and an unlabeled query, find coarse spatial correspondence between the query and the labeled images, and then infer class membership by computing distances between spatially-corresponding features. The result is a classifier that is more robust to task and domain shift, which we demonstrate via state-of-the-art performance on Meta-Dataset, a recent dataset for evaluating transfer from ImageNet to many other vision datasets.

arXiv:2007.11192공식 코드 · Papers with Code

Self-Supervised Learning of Contextual Embeddings for Link Prediction in Heterogeneous Networks

Representation learning methods for heterogeneous networks produce a low-dimensional vector embedding for each node that is typically fixed for all tasks involving the node. Many of the existing methods focus on obtaining a static vector representation for a node in a way that is agnostic to the downstream application where it is being used. In practice, however, downstream tasks such as link prediction require specific contextual information that can be extracted from the subgraphs related to the nodes provided as input to the task. To tackle this challenge, we develop SLiCE, a framework bridging static representation learning methods using global information from the entire graph with localized attention driven mechanisms to learn contextual node representations. We first pre-train our model in a self-supervised manner by introducing higher-order semantic associations and masking nodes, and then fine-tune our model for a specific link prediction task. Instead of training node representations by aggregating information from all semantic neighbors connected via metapaths, we automatically learn the composition of different metapaths that characterize the context for a specific task without the need for any pre-defined metapaths. SLiCE significantly outperforms both static and contextual embedding learning methods on several publicly available benchmark network datasets. We also interpret the semantic association matrix and provide its utility and relevance in making successful link predictions between heterogeneous nodes in the network.

arXiv:2007.11186

Instance-aware Self-supervised Learning for Nuclei Segmentation

Due to the wide existence and large morphological variances of nuclei, accurate nuclei instance segmentation is still one of the most challenging tasks in computational pathology. The annotating of nuclei instances, requiring experienced pathologists to manually draw the contours, is extremely laborious and expensive, which often results in the deficiency of annotated data. The deep learning based segmentation approaches, which highly rely on the quantity of training data, are difficult to fully demonstrate their capacity in this area. In this paper, we propose a novel self-supervised learning framework to deeply exploit the capacity of widely-used convolutional neural networks (CNNs) on the nuclei instance segmentation task. The proposed approach involves two sub-tasks (i.e., scale-wise triplet learning and count ranking), which enable neural networks to implicitly leverage the prior-knowledge of nuclei size and quantity, and accordingly mine the instance-aware feature representations from the raw data. Experimental results on the publicly available MoNuSeg dataset show that the proposed self-supervised learning approach can remarkably boost the segmentation accuracy of nuclei instance---a new state-of-the-art average Aggregated Jaccard Index (AJI) of 70.63%, is achieved by our self-supervised ResUNet-101. To our best knowledge, this is the first work focusing on the self-supervised learning for instance segmentation.

논문 ID: document/8964295

SACNN: Self-Attention Convolutional Neural Network for Low-Dose CT Denoising With Self-Supervised Perceptual Loss Network

Computed tomography (CT) is a widely used screening and diagnostic tool that allows clinicians to obtain a high-resolution, volumetric image of internal structures in a non-invasive manner. Increasingly, efforts have been made to improve the image quality of low-dose CT (LDCT) to reduce the cumulative radiation exposure of patients undergoing routine screening exams. The resurgence of deep learning has yielded a new approach for noise reduction by training a deep multi-layer convolutional neural networks (CNN) to map the low-dose to normal-dose CT images. However, CNN-based methods heavily rely on convolutional kernels, which use fixed-size filters to process one local neighborhood within the receptive field at a time. As a result, they are not efficient at retrieving structural information across large regions. In this paper, we propose a novel 3D self-attention convolutional neural network for the LDCT denoising problem. Our 3D self-attention module leverages the 3D volume of CT images to capture a wide range of spatial information both within CT slices and between CT slices. With the help of the 3D self-attention module, CNNs are able to leverage pixels with stronger relationships regardless of their distance and achieve better denoising results. In addition, we propose a self-supervised learning scheme to train a domain-specific autoencoder as the perceptual loss function. We combine these two methods and demonstrate their effectiveness on both CNN-based neural networks and WGAN-based neural networks with comprehensive experiments. Tested on the AAPM-Mayo Clinic Low Dose CT Grand Challenge data set, our experiments demonstrate that self-attention (SA) module and autoencoder (AE) perceptual loss function can efficiently enhance traditional CNNs and can achieve comparable or better results than the state-of-the-art methods.

arXiv:2007.10629공식 코드 · Papers with Code

CSLNSpeech: solving extended speech separation problem with the help of Chinese sign language

Previous audio-visual speech separation methods use the synchronization of the speaker's facial movement and speech in the video to supervise the speech separation in a self-supervised way. In this paper, we propose a model to solve the speech separation problem assisted by both face and sign language, which we call the extended speech separation problem. We design a general deep learning network for learning the combination of three modalities, audio, face, and sign language information, for better solving the speech separation problem. To train the model, we introduce a large-scale dataset named the Chinese Sign Language News Speech (CSLNSpeech) dataset, in which three modalities of audio, face, and sign language coexist. Experiment results show that the proposed model has better performance and robustness than the usual audio-visual system. Besides, sign language modality can also be used alone to supervise speech separation tasks, and the introduction of sign language is helpful for hearing-impaired people to learn and communicate. Last, our model is a general speech separation framework and can achieve very competitive separation performance on two open-source audio-visual datasets. The code is available at https://github.com/iveveive/SLNSpeech

arXiv:2007.10603공식 코드 · Papers with Code

Feature-metric Loss for Self-supervised Learning of Depth and Egomotion

Photometric loss is widely used for self-supervised depth and egomotion estimation. However, the loss landscapes induced by photometric differences are often problematic for optimization, caused by plateau landscapes for pixels in textureless regions or multiple local minima for less discriminative pixels. In this work, feature-metric loss is proposed and defined on feature representation, where the feature representation is also learned in a self-supervised manner and regularized by both first-order and second-order derivatives to constrain the loss landscapes to form proper convergence basins. Comprehensive experiments and detailed analysis via visualization demonstrate the effectiveness of the proposed feature-metric loss. In particular, our method improves state-of-the-art methods on KITTI from 0.885 to 0.925 measured by $\delta_1$ for depth estimation, and significantly outperforms previous method for visual odometry.

arXiv:2007.10983

Learning Monocular Visual Odometry via Self-Supervised Long-Term Modeling

Monocular visual odometry (VO) suffers severely from error accumulation during frame-to-frame pose estimation. In this paper, we present a self-supervised learning method for VO with special consideration for consistency over longer sequences. To this end, we model the long-term dependency in pose prediction using a pose network that features a two-layer convolutional LSTM module. We train the networks with purely self-supervised losses, including a cycle consistency loss that mimics the loop closure module in geometric VO. Inspired by prior geometric systems, we allow the networks to see beyond a small temporal window during training, through a novel a loss that incorporates temporally distant (e.g., O(100)) frames. Given GPU memory constraints, we propose a stage-wise training mechanism, where the first stage operates in a local time window and the second stage refines the poses with a "global" loss given the first stage features. We demonstrate competitive results on several standard VO datasets, including KITTI and TUM RGB-D.

arXiv:2007.10730

Video Representation Learning by Recognizing Temporal Transformations

We introduce a novel self-supervised learning approach to learn representations of videos that are responsive to changes in the motion dynamics. Our representations can be learned from data without human annotation and provide a substantial boost to the training of neural networks on small labeled data sets for tasks such as action recognition, which require to accurately distinguish the motion of objects. We promote an accurate learning of motion without human annotation by training a neural network to discriminate a video sequence from its temporally transformed versions. To learn to distinguish non-trivial motions, the design of the transformations is based on two principles: 1) To define clusters of motions based on time warps of different magnitude; 2) To ensure that the discrimination is feasible only by observing and analyzing as many image frames as possible. Thus, we introduce the following transformations: forward-backward playback, random frame skipping, and uniform frame skipping. Our experiments show that networks trained with the proposed method yield representations with improved transfer performance for action recognition on UCF101 and HMDB51.

arXiv:2007.09300

An Open-World Simulated Environment for Developmental Robotics

As the current trend of artificial intelligence is shifting towards self-supervised learning, conventional norms such as highly curated domain-specific data, application-specific learning models, extrinsic reward based learning policies etc. might not provide with the suitable ground for such developments. In this paper, we introduce SEDRo, a Simulated Environment for Developmental Robotics which allows a learning agent to have similar experiences that a human infant goes through from the fetus stage up to 12 months. A series of simulated tests based on developmental psychology will be used to evaluate the progress of a learning model.

arXiv:2007.09162

Improving Object Detection with Selective Self-supervised Self-training

We study how to leverage Web images to augment human-curated object detection datasets. Our approach is two-pronged. On the one hand, we retrieve Web images by image-to-image search, which incurs less domain shift from the curated data than other search methods. The Web images are diverse, supplying a wide variety of object poses, appearances, their interactions with the context, etc. On the other hand, we propose a novel learning method motivated by two parallel lines of work that explore unlabeled data for image classification: self-training and self-supervised learning. They fail to improve object detectors in their vanilla forms due to the domain gap between the Web images and curated datasets. To tackle this challenge, we propose a selective net to rectify the supervision signals in Web images. It not only identifies positive bounding boxes but also creates a safe zone for mining hard negative boxes. We report state-of-the-art results on detecting backpacks and chairs from everyday scenes, along with other challenging object classes.

arXiv:2007.10321

Hierarchical Contrastive Motion Learning for Video Action Recognition

One central question for video action recognition is how to model motion. In this paper, we present hierarchical contrastive motion learning, a new self-supervised learning framework to extract effective motion representations from raw video frames. Our approach progressively learns a hierarchy of motion features that correspond to different abstraction levels in a network. This hierarchical design bridges the semantic gap between low-level motion cues and high-level recognition tasks, and promotes the fusion of appearance and motion information at multiple levels. At each level, an explicit motion self-supervision is provided via contrastive learning to enforce the motion features at the current level to predict the future ones at the previous level. Thus, the motion features at higher levels are trained to gradually capture semantic dynamics and evolve more discriminative for action recognition. Our motion learning module is lightweight and flexible to be embedded into various backbone networks. Extensive experiments on four benchmarks show that the proposed approach consistently achieves superior results.

arXiv:2007.10284공식 코드 · Papers with Code

Learning High-Level Policies for Model Predictive Control

The combination of policy search and deep neural networks holds the promise of automating a variety of decision-making tasks. Model Predictive Control (MPC) provides robust solutions to robot control tasks by making use of a dynamical model of the system and solving an optimization problem online over a short planning horizon. In this work, we leverage probabilistic decision-making approaches and the generalization capability of artificial neural networks to the powerful online optimization by learning a deep high-level policy for the MPC (High-MPC). Conditioning on robot's local observations, the trained neural network policy is capable of adaptively selecting high-level decision variables for the low-level MPC controller, which then generates optimal control commands for the robot. First, we formulate the search of high-level decision variables for MPC as a policy search problem, specifically, a probabilistic inference problem. The problem can be solved in a closed-form solution. Second, we propose a self-supervised learning algorithm for learning a neural network high-level policy, which is useful for online hyperparameter adaptations in highly dynamic environments. We demonstrate the importance of incorporating the online adaption into autonomous robots by using the proposed method to solve a challenging control problem, where the task is to control a simulated quadrotor to fly through a swinging gate. We show that our approach can handle situations that are difficult for standard MPC.

arXiv:2007.08786

Cross-Identity Motion Transfer for Arbitrary Objects through Pose-Attentive Video Reassembling

We propose an attention-based networks for transferring motions between arbitrary objects. Given a source image(s) and a driving video, our networks animate the subject in the source images according to the motion in the driving video. In our attention mechanism, dense similarities between the learned keypoints in the source and the driving images are computed in order to retrieve the appearance information from the source images. Taking a different approach from the well-studied warping based models, our attention-based model has several advantages. By reassembling non-locally searched pieces from the source contents, our approach can produce more realistic outputs. Furthermore, our system can make use of multiple observations of the source appearance (e.g. front and sides of faces) to make the results more accurate. To reduce the training-testing discrepancy of the self-supervised learning, a novel cross-identity training scheme is additionally introduced. With the training scheme, our networks is trained to transfer motions between different subjects, as in the real testing scenario. Experimental results validate that our method produces visually pleasing results in various object domains, showing better performances compared to previous works.

arXiv:2007.08826

Revisiting Rubik's Cube: Self-supervised Learning with Volume-wise Transformation for 3D Medical Image Segmentation

Deep learning highly relies on the quantity of annotated data. However, the annotations for 3D volumetric medical data require experienced physicians to spend hours or even days for investigation. Self-supervised learning is a potential solution to get rid of the strong requirement of training data by deeply exploiting raw data information. In this paper, we propose a novel self-supervised learning framework for volumetric medical images. Specifically, we propose a context restoration task, i.e., Rubik's cube++, to pre-train 3D neural networks. Different from the existing context-restoration-based approaches, we adopt a volume-wise transformation for context permutation, which encourages network to better exploit the inherent 3D anatomical information of organs. Compared to the strategy of training from scratch, fine-tuning from the Rubik's cube++ pre-trained weight can achieve better performance in various tasks such as pancreas segmentation and brain tissue segmentation. The experimental results show that our self-supervised learning method can significantly improve the accuracy of 3D deep learning networks on volumetric medical datasets without the use of extra data.

arXiv:2007.09060

Self-Supervised Learning of Context-Aware Pitch Prosody Representations

In music and speech, meaning is derived at multiple levels of context. Affect, for example, can be inferred both by a short sound token and by sonic patterns over a longer temporal window such as an entire recording. In this letter, we focus on inferring meaning from this dichotomy of contexts. We show how contextual representations of short sung vocal lines can be implicitly learned from fundamental frequency ($F_0$) and thus be used as a meaningful feature space for downstream Music Information Retrieval (MIR) tasks. We propose three self-supervised deep learning paradigms which leverage pseudotask learning of these two levels of context to produce latent representation spaces. We evaluate the usefulness of these representations by embedding unseen pitch contours into each space and conducting downstream classification tasks. Our results show that contextual representation can enhance downstream classification by as much as 15\% as compared to using traditional statistical contour features.