PyTorchKR Papers

최신 논문

총 5,358편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2110.01805

Self-Supervised Learning of Perceptually Optimized Block Motion Estimates for Video Compression

Block based motion estimation is integral to inter prediction processes performed in hybrid video codecs. Prevalent block matching based methods that are used to compute block motion vectors (MVs) rely on computationally intensive search procedures. They also suffer from the aperture problem, which can worsen as the block size is reduced. Moreover, the block matching criteria used in typical codecs do not account for the resulting levels of perceptual quality of the motion compensated pictures that are created upon decoding. Towards achieving the elusive goal of perceptually optimized motion estimation, we propose a search-free block motion estimation framework using a multi-stage convolutional neural network, which is able to conduct motion estimation on multiple block sizes simultaneously, using a triplet of frames as input. This composite block translation network (CBT-Net) is trained in a self-supervised manner on a large database that we created from publicly available uncompressed video content. We deploy the multi-scale structural similarity (MS-SSIM) loss function to optimize the perceptual quality of the motion compensated predicted frames. Our experimental results highlight the computational efficiency of our proposed model relative to conventional block matching based motion estimation algorithms, for comparable prediction errors. Further, when used to perform inter prediction in AV1, the MV predictions of the perceptually optimized model result in average Bjontegaard-delta rate (BD-rate) improvements of -1.70% and -1.52% with respect to the MS-SSIM and Video Multi-Method Assessment Fusion (VMAF) quality metrics, respectively as compared to the block matching based motion estimation system employed in the SVT-AV1 encoder.

arXiv:2110.01680

How You Move Your Head Tells What You Do: Self-supervised Video Representation Learning with Egocentric Cameras and IMU Sensors

Understanding users' activities from head-mounted cameras is a fundamental task for Augmented and Virtual Reality (AR/VR) applications. A typical approach is to train a classifier in a supervised manner using data labeled by humans. This approach has limitations due to the expensive annotation cost and the closed coverage of activity labels. A potential way to address these limitations is to use self-supervised learning (SSL). Instead of relying on human annotations, SSL leverages intrinsic properties of data to learn representations. We are particularly interested in learning egocentric video representations benefiting from the head-motion generated by users' daily activities, which can be easily obtained from IMU sensors embedded in AR/VR devices. Towards this goal, we propose a simple but effective approach to learn video representation by learning to tell the corresponding pairs of video clip and head-motion. We demonstrate the effectiveness of our learned representation for recognizing egocentric activities of people and dogs.

arXiv:2110.01077

Multi-task Voice Activated Framework using Self-supervised Learning

Self-supervised learning methods such as wav2vec 2.0 have shown promising results in learning speech representations from unlabelled and untranscribed speech data that are useful for speech recognition. Since these representations are learned without any task-specific supervision, they can also be useful for other voice-activated tasks like speaker verification, keyword spotting, emotion classification etc. In our work, we propose a general purpose framework for adapting a pre-trained wav2vec 2.0 model for different voice-activated tasks. We develop downstream network architectures that operate on the contextualized speech representations of wav2vec 2.0 to adapt the representations for solving a given task. Finally, we extend our framework to perform multi-task learning by jointly optimizing the network parameters on multiple voice activated tasks using a shared transformer backbone. Both of our single and multi-task frameworks achieve state-of-the-art results in speaker verification and keyword spotting benchmarks. Our best performing models achieve 1.98% and 3.15% EER on VoxCeleb1 test set when trained on VoxCeleb2 and VoxCeleb1 respectively, and 98.23% accuracy on Google Speech Commands v1.0 keyword spotting dataset.

arXiv:2110.01242

Consistency Regularization Can Improve Robustness to Label Noise

Consistency regularization is a commonly-used technique for semi-supervised and self-supervised learning. It is an auxiliary objective function that encourages the prediction of the network to be similar in the vicinity of the observed training samples. Hendrycks et al. (2020) have recently shown such regularization naturally brings test-time robustness to corrupted data and helps with calibration. This paper empirically studies the relevance of consistency regularization for training-time robustness to noisy labels. First, we make two interesting and useful observations regarding the consistency of networks trained with the standard cross entropy loss on noisy datasets which are: (i) networks trained on noisy data have lower consistency than those trained on clean data, and(ii) the consistency reduces more significantly around noisy-labelled training data points than correctly-labelled ones. Then, we show that a simple loss function that encourages consistency improves the robustness of the models to label noise on both synthetic (CIFAR-10, CIFAR-100) and real-world (WebVision) noise as well as different noise rates and types and achieves state-of-the-art results.

arXiv:2110.00987공식 코드 · Papers with Code

Motif-based Graph Self-Supervised Learning for Molecular Property Prediction

Predicting molecular properties with data-driven methods has drawn much attention in recent years. Particularly, Graph Neural Networks (GNNs) have demonstrated remarkable success in various molecular generation and prediction tasks. In cases where labeled data is scarce, GNNs can be pre-trained on unlabeled molecular data to first learn the general semantic and structural information before being fine-tuned for specific tasks. However, most existing self-supervised pre-training frameworks for GNNs only focus on node-level or graph-level tasks. These approaches cannot capture the rich information in subgraphs or graph motifs. For example, functional groups (frequently-occurred subgraphs in molecular graphs) often carry indicative information about the molecular properties. To bridge this gap, we propose Motif-based Graph Self-supervised Learning (MGSSL) by introducing a novel self-supervised motif generation framework for GNNs. First, for motif extraction from molecular graphs, we design a molecule fragmentation method that leverages a retrosynthesis-based algorithm BRICS and additional rules for controlling the size of motif vocabulary. Second, we design a general motif-based generative pre-training framework in which GNNs are asked to make topological and label predictions. This generative framework can be implemented in two different ways, i.e., breadth-first or depth-first. Finally, to take the multi-scale information in molecular graphs into consideration, we introduce a multi-level self-supervised pre-training. Extensive experiments on various downstream benchmark tasks show that our methods outperform all state-of-the-art baselines.

arXiv:2110.00552

Stochastic Contrastive Learning

While state-of-the-art contrastive Self-Supervised Learning (SSL) models produce results competitive with their supervised counterparts, they lack the ability to infer latent variables. In contrast, prescribed latent variable (LV) models enable attributing uncertainty, inducing task specific compression, and in general allow for more interpretable representations. In this work, we introduce LV approximations to large scale contrastive SSL models. We demonstrate that this addition improves downstream performance (resulting in 96.42% and 77.49% test top-1 fine-tuned performance on CIFAR10 and ImageNet respectively with a ResNet50) as well as producing highly compressed representations (588x reduction) that are useful for interpretability, classification and regression downstream tasks.

arXiv:2110.00538

Evaluating the fairness of fine-tuning strategies in self-supervised learning

In this work we examine how fine-tuning impacts the fairness of contrastive Self-Supervised Learning (SSL) models. Our findings indicate that Batch Normalization (BN) statistics play a crucial role, and that updating only the BN statistics of a pre-trained SSL backbone improves its downstream fairness (36% worst subgroup, 25% mean subgroup gap). This procedure is competitive with supervised learning, while taking 4.4x less time to train and requiring only 0.35% as many parameters to be updated. Finally, inspired by recent work in supervised learning, we find that updating BN statistics and training residual skip connections (12.3% of the parameters) achieves parity with a fully fine-tuned model, while taking 1.33x less time to train.

arXiv:2110.00527공식 코드 · Papers with Code

Consistent Explanations by Contrastive Learning

Post-hoc explanation methods, e.g., Grad-CAM, enable humans to inspect the spatial regions responsible for a particular network decision. However, it is shown that such explanations are not always consistent with human priors, such as consistency across image transformations. Given an interpretation algorithm, e.g., Grad-CAM, we introduce a novel training method to train the model to produce more consistent explanations. Since obtaining the ground truth for a desired model interpretation is not a well-defined task, we adopt ideas from contrastive self-supervised learning, and apply them to the interpretations of the model rather than its embeddings. We show that our method, Contrastive Grad-CAM Consistency (CGC), results in Grad-CAM interpretation heatmaps that are more consistent with human annotations while still achieving comparable classification accuracy. Moreover, our method acts as a regularizer and improves the accuracy on limited-data, fine-grained classification settings. In addition, because our method does not rely on annotations, it allows for the incorporation of unlabeled data into training, which enables better generalization of the model. Our code is available here: https://github.com/UCDvision/CGC

arXiv:2110.00404

Learning of Inter-Label Geometric Relationships Using Self-Supervised Learning: Application To Gleason Grade Segmentation

Segmentation of Prostate Cancer (PCa) tissues from Gleason graded histopathology images is vital for accurate diagnosis. Although deep learning (DL) based segmentation methods achieve state-of-the-art accuracy, they rely on large datasets with manual annotations. We propose a method to synthesize for PCa histopathology images by learning the geometrical relationship between different disease labels using self-supervised learning. We use a weakly supervised segmentation approach that uses Gleason score to segment the diseased regions and the resulting segmentation map is used to train a Shape Restoration Network (ShaRe-Net) to predict missing mask segments in a self-supervised manner. Using DenseUNet as the backbone generator architecture we incorporate latent variable sampling to inject diversity in the image generation process and thus improve robustness. Experiments on multiple histopathology datasets demonstrate the superiority of our method over competing image synthesis methods for segmentation tasks. Ablation studies show the benefits of integrating geometry and diversity in generating high-quality images, and our self-supervised approach with limited class-labeled data achieves similar performance as fully supervised learning.

arXiv:2110.00155

Incremental Layer-wise Self-Supervised Learning for Efficient Speech Domain Adaptation On Device

Streaming end-to-end speech recognition models have been widely applied to mobile devices and show significant improvement in efficiency. These models are typically trained on the server using transcribed speech data. However, the server data distribution can be very different from the data distribution on user devices, which could affect the model performance. There are two main challenges for on device training, limited reliable labels and limited training memory. While self-supervised learning algorithms can mitigate the mismatch between domains using unlabeled data, they are not applicable on mobile devices directly because of the memory constraint. In this paper, we propose an incremental layer-wise self-supervised learning algorithm for efficient speech domain adaptation on mobile devices, in which only one layer is updated at a time. Extensive experimental results demonstrate that the proposed algorithm obtains a Word Error Rate (WER) on the target domain $24.2\%$ better than supervised baseline and costs $89.7\%$ less training memory than the end-to-end self-supervised learning algorithm.

arXiv:2110.00075공식 코드 · Papers with Code

Noise2Recon: Enabling Joint MRI Reconstruction and Denoising with Semi-Supervised and Self-Supervised Learning

Deep learning (DL) has shown promise for faster, high quality accelerated MRI reconstruction. However, supervised DL methods depend on extensive amounts of fully-sampled (labeled) data and are sensitive to out-of-distribution (OOD) shifts, particularly low signal-to-noise ratio (SNR) acquisitions. To alleviate this challenge, we propose Noise2Recon, a model-agnostic, consistency training method for joint MRI reconstruction and denoising that can use both fully-sampled (labeled) and undersampled (unlabeled) scans in semi-supervised and self-supervised settings. With limited or no labeled training data, Noise2Recon outperforms compressed sensing and deep learning baselines, including supervised networks, augmentation-based training, fine-tuned denoisers, and self-supervised methods, and matches performance of supervised models, which were trained with 14x more fully-sampled scans. Noise2Recon also outperforms all baselines, including state-of-the-art fine-tuning and augmentation techniques, among low-SNR scans and when generalizing to other OOD factors, such as changes in acceleration factors and different datasets. Augmentation extent and loss weighting hyperparameters had negligible impact on Noise2Recon compared to supervised methods, which may indicate increased training stability. Our code is available at https://github.com/ad12/meddlr.

arXiv:2110.00023공식 코드 · Papers with Code

Mining for Strong Gravitational Lenses with Self-supervised Learning

We employ self-supervised representation learning to distill information from 76 million galaxy images from the Dark Energy Spectroscopic Instrument Legacy Imaging Surveys' Data Release 9. Targeting the identification of new strong gravitational lens candidates, we first create a rapid similarity search tool to discover new strong lenses given only a single labelled example. We then show how training a simple linear classifier on the self-supervised representations, requiring only a few minutes on a CPU, can automatically classify strong lenses with great efficiency. We present 1192 new strong lens candidates that we identified through a brief visual identification campaign, and release an interactive web-based similarity search tool and the top network predictions to facilitate crowd-sourcing rapid discovery of additional strong gravitational lenses and other rare objects: https://github.com/georgestein/ssl-legacysurvey.

arXiv:2110.00175공식 코드 · Papers with Code

DualNet: Continual Learning, Fast and Slow

According to Complementary Learning Systems (CLS) theory~\citep{mcclelland1995there} in neuroscience, humans do effective \emph{continual learning} through two complementary systems: a fast learning system centered on the hippocampus for rapid learning of the specifics and individual experiences, and a slow learning system located in the neocortex for the gradual acquisition of structured knowledge about the environment. Motivated by this theory, we propose a novel continual learning framework named "DualNet", which comprises a fast learning system for supervised learning of pattern-separated representation from specific tasks and a slow learning system for unsupervised representation learning of task-agnostic general representation via a Self-Supervised Learning (SSL) technique. The two fast and slow learning systems are complementary and work seamlessly in a holistic continual learning framework. Our extensive experiments on two challenging continual learning benchmarks of CORE50 and miniImageNet show that DualNet outperforms state-of-the-art continual learning methods by a large margin. We further conduct ablation studies of different SSL objectives to validate DualNet's efficacy, robustness, and scalability. Code will be made available upon acceptance.

arXiv:2110.00269

A Survey of Knowledge Enhanced Pre-trained Models

Pre-trained language models learn informative word representations on a large-scale text corpus through self-supervised learning, which has achieved promising performance in fields of natural language processing (NLP) after fine-tuning. These models, however, suffer from poor robustness and lack of interpretability. We refer to pre-trained language models with knowledge injection as knowledge-enhanced pre-trained language models (KEPLMs). These models demonstrate deep understanding and logical reasoning and introduce interpretability. In this survey, we provide a comprehensive overview of KEPLMs in NLP. We first discuss the advancements in pre-trained language models and knowledge representation learning. Then we systematically categorize existing KEPLMs from three different perspectives. Finally, we outline some potential directions of KEPLMs for future research.

arXiv:2109.15170공식 코드 · Papers with Code

CoSeg: Cognitively Inspired Unsupervised Generic Event Segmentation

Some cognitive research has discovered that humans accomplish event segmentation as a side effect of event anticipation. Inspired by this discovery, we propose a simple yet effective end-to-end self-supervised learning framework for event segmentation/boundary detection. Unlike the mainstream clustering-based methods, our framework exploits a transformer-based feature reconstruction scheme to detect event boundary by reconstruction errors. This is consistent with the fact that humans spot new events by leveraging the deviation between their prediction and what is actually perceived. Thanks to their heterogeneity in semantics, the frames at boundaries are difficult to be reconstructed (generally with large reconstruction errors), which is favorable for event boundary detection. Additionally, since the reconstruction occurs on the semantic feature level instead of pixel level, we develop a temporal contrastive feature embedding module to learn the semantic visual representation for frame feature reconstruction. This procedure is like humans building up experiences with "long-term memory". The goal of our work is to segment generic events rather than localize some specific ones. We focus on achieving accurate event boundaries. As a result, we adopt F1 score (Precision/Recall) as our primary evaluation metric for a fair comparison with previous approaches. Meanwhile, we also calculate the conventional frame-based MoF and IoU metric. We thoroughly benchmark our work on four publicly available datasets and demonstrate much better results.

arXiv:2109.15089공식 코드 · Papers with Code

Biologically Plausible Training Mechanisms for Self-Supervised Learning in Deep Networks

We develop biologically plausible training mechanisms for self-supervised learning (SSL) in deep networks. Specifically, by biological plausible training we mean (i) All updates of weights are based on current activities of pre-synaptic units and current, or activity retrieved from short term memory of post synaptic units, including at the top-most error computing layer, (ii) Complex computations such as normalization, inner products and division are avoided (iii) Asymmetric connections between units, (iv) Most learning is carried out in an unsupervised manner. SSL with a contrastive loss satisfies the third condition as it does not require labelled data and it introduces robustness to observed perturbations of objects, which occur naturally as objects or observer move in 3d and with variable lighting over time. We propose a contrastive hinge based loss whose error involves simple local computations satisfying (ii), as opposed to the standard contrastive losses employed in the literature, which do not lend themselves easily to implementation in a network architecture due to complex computations involving ratios and inner products. Furthermore we show that learning can be performed with one of two more plausible alternatives to backpropagation that satisfy conditions (i) and (ii). The first is difference target propagation (DTP) and the second is layer-wise learning (LL), where each layer is directly connected to a layer computing the loss error. Both methods represent alternatives to the symmetric weight issue of backpropagation. By training convolutional neural networks (CNNs) with SSL and DTP, LL, we find that our proposed framework achieves comparable performance to standard BP learning downstream linear classifier evaluation of the learned embeddings.

arXiv:2109.14288

Self-Supervised Learning for 3D Medical Image Analysis using 3D SimCLR and Monte Carlo Dropout

Self-supervised learning methods can be used to learn meaningful representations from unlabeled data that can be transferred to supervised downstream tasks to reduce the need for labeled data. In this paper, we propose a 3D self-supervised method that is based on the contrastive (SimCLR) method. Additionally, we show that employing Bayesian neural networks (with Monte-Carlo Dropout) during the inference phase can further enhance the results on the downstream tasks. We showcase our models on two medical imaging segmentation tasks: i) Brain Tumor Segmentation from 3D MRI, ii) Pancreas Tumor Segmentation from 3D CT. Our experimental results demonstrate the benefits of our proposed methods in both downstream data-efficiency and performance.

arXiv:2109.14159

Adaptive Multi-layer Contrastive Graph Neural Networks

We present Adaptive Multi-layer Contrastive Graph Neural Networks (AMC-GNN), a self-supervised learning framework for Graph Neural Network, which learns feature representations of sample data without data labels. AMC-GNN generates two graph views by data augmentation and compares different layers' output embeddings of Graph Neural Network encoders to obtain feature representations, which could be used for downstream tasks. AMC-GNN could learn the importance weights of embeddings in different layers adaptively through the attention mechanism, and an auxiliary encoder is introduced to train graph contrastive encoders better. The accuracy is improved by maximizing the representation's consistency of positive pairs in the early layers and the final embedding space. Our experiments show that the results can be consistently improved by using the AMC-GNN framework, across four established graph benchmarks: Cora, Citeseer, Pubmed, DBLP citation network datasets, as well as four newly proposed datasets: Co-author-CS, Co-author-Physics, Amazon-Computers, Amazon-Photo.

arXiv:2109.13392공식 코드 · Papers with Code

The Tensor Brain: A Unified Theory of Perception, Memory and Semantic Decoding

We present a unified computational theory of an agent's perception and memory. In our model, perception, episodic memory, and semantic memory are realized by different operational modes of the oscillating interactions between a symbolic index layer and a subsymbolic representation layer. The two layers form a bilayer tensor network (BTN). Although memory appears to be about the past, its main purpose is to support the agent in the present and the future. Recent episodic memory provides the agent with a sense of the here and now. Remote episodic memory retrieves relevant past experiences to provide information about possible future scenarios. This aids the agent in decision-making. "Future" episodic memory, based on expected future events, guides planning and action. Semantic memory retrieves specific information, which is not delivered by current perception, and defines priors for future observations. We argue that it is important for the agent to encode individual entities, not just classes and attributes. We demonstrate that a form of self-supervised learning can acquire new concepts and refine existing ones. We test our model on a standard benchmark data set, which we expanded to contain richer representations for attributes, classes, and individuals. Our key hypothesis is that obtaining a better understanding of perception and memory is a crucial prerequisite to comprehending human-level intelligence.

arXiv:2109.12502공식 코드 · Papers with Code

Self-Supervised Learning for MRI Reconstruction with a Parallel Network Training Framework

Image reconstruction from undersampled k-space data plays an important role in accelerating the acquisition of MR data, and a lot of deep learning-based methods have been exploited recently. Despite the achieved inspiring results, the optimization of these methods commonly relies on the fully-sampled reference data, which are time-consuming and difficult to collect. To address this issue, we propose a novel self-supervised learning method. Specifically, during model optimization, two subsets are constructed by randomly selecting part of k-space data from the undersampled data and then fed into two parallel reconstruction networks to perform information recovery. Two reconstruction losses are defined on all the scanned data points to enhance the network's capability of recovering the frequency information. Meanwhile, to constrain the learned unscanned data points of the network, a difference loss is designed to enforce consistency between the two parallel networks. In this way, the reconstruction model can be properly trained with only the undersampled data. During the model evaluation, the undersampled data are treated as the inputs and either of the two trained networks is expected to reconstruct the high-quality results. The proposed method is flexible and can be employed in any existing deep learning-based method. The effectiveness of the method is evaluated on an open brain MRI dataset. Experimental results demonstrate that the proposed self-supervised method can achieve competitive reconstruction performance compared to the corresponding supervised learning method at high acceleration rates (4 and 8). The code is publicly available at \url{https://github.com/chenhu96/Self-Supervised-MRI-Reconstruction}.