PyTorchKR Papers

최신 논문

총 5,358편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2204.05104공식 코드 · Papers with Code

Self-Supervised Graph Neural Network for Multi-Source Domain Adaptation

Domain adaptation (DA) tries to tackle the scenarios when the test data does not fully follow the same distribution of the training data, and multi-source domain adaptation (MSDA) is very attractive for real world applications. By learning from large-scale unlabeled samples, self-supervised learning has now become a new trend in deep learning. It is worth noting that both self-supervised learning and multi-source domain adaptation share a similar goal: they both aim to leverage unlabeled data to learn more expressive representations. Unfortunately, traditional multi-task self-supervised learning faces two challenges: (1) the pretext task may not strongly relate to the downstream task, thus it could be difficult to learn useful knowledge being shared from the pretext task to the target task; (2) when the same feature extractor is shared between the pretext task and the downstream one and only different prediction heads are used, it is ineffective to enable inter-task information exchange and knowledge sharing. To address these issues, we propose a novel \textbf{S}elf-\textbf{S}upervised \textbf{G}raph Neural Network (SSG), where a graph neural network is used as the bridge to enable more effective inter-task information exchange and knowledge sharing. More expressive representation is learned by adopting a mask token strategy to mask some domain information. Our extensive experiments have demonstrated that our proposed SSG method has achieved state-of-the-art results over four multi-source domain adaptation datasets, which have shown the effectiveness of our proposed SSG method from different aspects.

arXiv:2204.05103

Transformer-Based Self-Supervised Learning for Emotion Recognition

In order to exploit representations of time-series signals, such as physiological signals, it is essential that these representations capture relevant information from the whole signal. In this work, we propose to use a Transformer-based model to process electrocardiograms (ECG) for emotion recognition. Attention mechanisms of the Transformer can be used to build contextualized representations for a signal, giving more importance to relevant parts. These representations may then be processed with a fully-connected network to predict emotions. To overcome the relatively small size of datasets with emotional labels, we employ self-supervised learning. We gathered several ECG datasets with no labels of emotion to pre-train our model, which we then fine-tuned for emotion recognition on the AMIGOS dataset. We show that our approach reaches state-of-the-art performances for emotion recognition using ECG signals on AMIGOS. More generally, our experiments show that transformers and pre-training are promising strategies for emotion recognition with physiological signals.

arXiv:2204.05248

Learning Downstream Task by Selectively Capturing Complementary Knowledge from Multiple Self-supervisedly Learning Pretexts

Self-supervised learning (SSL), as a newly emerging unsupervised representation learning paradigm, generally follows a two-stage learning pipeline: 1) learning invariant and discriminative representations with auto-annotation pretext(s), then 2) transferring the representations to assist downstream task(s). Such two stages are usually implemented separately, making the learned representation learned agnostic to the downstream tasks. Currently, most works are devoted to exploring the first stage. Whereas, it is less studied on how to learn downstream tasks with limited labeled data using the already learned representations. Especially, it is crucial and challenging to selectively utilize the complementary representations from diverse pretexts for a downstream task. In this paper, we technically propose a novel solution by leveraging the attention mechanism to adaptively squeeze suitable representations for the tasks. Meanwhile, resorting to information theory, we theoretically prove that gathering representation from diverse pretexts is more effective than a single one. Extensive experiments validate that our scheme significantly exceeds current popular pretext-matching based methods in gathering knowledge and relieving negative transfer in downstream tasks.

arXiv:2204.04874

Augmentation-Free Graph Contrastive Learning with Performance Guarantee

Graph contrastive learning (GCL) is the most representative and prevalent self-supervised learning approach for graph-structured data. Despite its remarkable success, existing GCL methods highly rely on an augmentation scheme to learn the representations invariant across different augmentation views. In this work, we revisit such a convention in GCL through examining the effect of augmentation techniques on graph data via the lens of spectral theory. We found that graph augmentations preserve the low-frequency components and perturb the middle-and high-frequency components of the graph, which contributes to the success of GCL algorithms on homophilic graphs but hinder its application on heterophilic graphs, due to the high-frequency preference of heterophilic data. Motivated by this, we propose a novel, theoretically-principled, and augmentation-free GCL method, named AF-GCL, that (1) leverages the features aggregated by Graph Neural Network to construct the self-supervision signal instead of augmentations and therefore (2) is less sensitive to the graph homophily degree. Theoretically, We present the performance guarantee for AF-GCL as well as an analysis for understanding the efficacy of AF-GCL. Extensive experiments on 14 benchmark datasets with varying degrees of heterophily show that AF-GCL presents competitive or better performance on homophilic graphs and outperforms all existing state-of-the-art GCL methods on heterophilic graphs with significantly less computational overhead.

arXiv:2204.04213공식 코드 · Papers with Code

Structure-aware Protein Self-supervised Learning

Protein representation learning methods have shown great potential to yield useful representation for many downstream tasks, especially on protein classification. Moreover, a few recent studies have shown great promise in addressing insufficient labels of proteins with self-supervised learning methods. However, existing protein language models are usually pretrained on protein sequences without considering the important protein structural information. To this end, we propose a novel structure-aware protein self-supervised learning method to effectively capture structural information of proteins. In particular, a well-designed graph neural network (GNN) model is pretrained to preserve the protein structural information with self-supervised tasks from a pairwise residue distance perspective and a dihedral angle perspective, respectively. Furthermore, we propose to leverage the available protein language model pretrained on protein sequences to enhance the self-supervised learning. Specifically, we identify the relation between the sequential information in the protein language model and the structural information in the specially designed GNN model via a novel pseudo bi-level optimization scheme. Experiments on several supervised downstream tasks verify the effectiveness of our proposed method.The code of the proposed method is available in \url{https://github.com/GGchen1997/STEPS_Bioinformatics}.

arXiv:2204.04796

SOS! Self-supervised Learning Over Sets Of Handled Objects In Egocentric Action Recognition

Learning an egocentric action recognition model from video data is challenging due to distractors (e.g., irrelevant objects) in the background. Further integrating object information into an action model is hence beneficial. Existing methods often leverage a generic object detector to identify and represent the objects in the scene. However, several important issues remain. Object class annotations of good quality for the target domain (dataset) are still required for learning good object representation. Besides, previous methods deeply couple the existing action models and need to retrain them jointly with object representation, leading to costly and inflexible integration. To overcome both limitations, we introduce Self-Supervised Learning Over Sets (SOS), an approach to pre-train a generic Objects In Contact (OIC) representation model from video object regions detected by an off-the-shelf hand-object contact detector. Instead of augmenting object regions individually as in conventional self-supervised learning, we view the action process as a means of natural data transformations with unique spatio-temporal continuity and exploit the inherent relationships among per-video object sets. Extensive experiments on two datasets, EPIC-KITCHENS-100 and EGTEA, show that our OIC significantly boosts the performance of multiple state-of-the-art video classification models.

arXiv:2204.04788공식 코드 · Papers with Code

Representation Learning by Detecting Incorrect Location Embeddings

In this paper, we introduce a novel self-supervised learning (SSL) loss for image representation learning. There is a growing belief that generalization in deep neural networks is linked to their ability to discriminate object shapes. Since object shape is related to the location of its parts, we propose to detect those that have been artificially misplaced. We represent object parts with image tokens and train a ViT to detect which token has been combined with an incorrect positional embedding. We then introduce sparsity in the inputs to make the model more robust to occlusions and to speed up the training. We call our method DILEMMA, which stands for Detection of Incorrect Location EMbeddings with MAsked inputs. We apply DILEMMA to MoCoV3, DINO and SimCLR and show an improvement in their performance of respectively 4.41%, 3.97%, and 0.5% under the same training time and with a linear probing transfer on ImageNet-1K. We also show full fine-tuning improvements of MAE combined with our method on ImageNet-100. We evaluate our method via fine-tuning on common SSL benchmarks. Moreover, we show that when downstream tasks are strongly reliant on shape (such as in the YOGA-82 pose dataset), our pre-trained features yield a significant gain over prior work.

arXiv:2204.04716공식 코드 · Papers with Code

TOV: The Original Vision Model for Optical Remote Sensing Image Understanding via Self-supervised Learning

Do we on the right way for remote sensing image understanding (RSIU) by training models via supervised data-dependent and task-dependent way, instead of human vision in a label-free and task-independent way? We argue that a more desirable RSIU model should be trained with intrinsic structure from data rather that extrinsic human labels to realize generalizability across a wide range of RSIU tasks. According to this hypothesis, we proposed \textbf{T}he \textbf{O}riginal \textbf{V}ision model (TOV) in remote sensing filed. Trained by massive unlabeled optical data along a human-like self-supervised learning (SSL) path that is from general knowledge to specialized knowledge, TOV model can be easily adapted to various RSIU tasks, including scene classification, object detection, and semantic segmentation, and outperforms dominant ImageNet supervised pretrained method as well as two recently proposed SSL pretrained methods on majority of 12 publicly available benchmarks. Moreover, we analyze the influences of two key factors on the performance of building TOV model for RSIU, including the influence of using different data sampling methods and the selection of learning paths during self-supervised optimization. We believe that a general model which is trained by a label-free and task-independent way may be the next paradigm for RSIU and hope the insights distilled from this study can help to foster the development of an original vision model for RSIU.

arXiv:2204.04607

Self-Supervised Video Representation Learning with Motion-Contrastive Perception

Visual-only self-supervised learning has achieved significant improvement in video representation learning. Existing related methods encourage models to learn video representations by utilizing contrastive learning or designing specific pretext tasks. However, some models are likely to focus on the background, which is unimportant for learning video representations. To alleviate this problem, we propose a new view called long-range residual frame to obtain more motion-specific information. Based on this, we propose the Motion-Contrastive Perception Network (MCPNet), which consists of two branches, namely, Motion Information Perception (MIP) and Contrastive Instance Perception (CIP), to learn generic video representations by focusing on the changing areas in videos. Specifically, the MIP branch aims to learn fine-grained motion features, and the CIP branch performs contrastive learning to learn overall semantics information for each instance. Experiments on two benchmark datasets UCF-101 and HMDB-51 show that our method outperforms current state-of-the-art visual-only self-supervised approaches.

arXiv:2204.04385공식 코드 · Papers with Code

Divergence-aware Federated Self-Supervised Learning

Self-supervised learning (SSL) is capable of learning remarkable representations from centrally available data. Recent works further implement federated learning with SSL to learn from rapidly growing decentralized unlabeled images (e.g., from cameras and phones), often resulted from privacy constraints. Extensive attention has been paid to SSL approaches based on Siamese networks. However, such an effort has not yet revealed deep insights into various fundamental building blocks for the federated self-supervised learning (FedSSL) architecture. We aim to fill in this gap via in-depth empirical study and propose a new method to tackle the non-independently and identically distributed (non-IID) data problem of decentralized data. Firstly, we introduce a generalized FedSSL framework that embraces existing SSL methods based on Siamese networks and presents flexibility catering to future methods. In this framework, a server coordinates multiple clients to conduct SSL training and periodically updates local models of clients with the aggregated global model. Using the framework, our study uncovers unique insights of FedSSL: 1) stop-gradient operation, previously reported to be essential, is not always necessary in FedSSL; 2) retaining local knowledge of clients in FedSSL is particularly beneficial for non-IID data. Inspired by the insights, we then propose a new approach for model update, Federated Divergence-aware Exponential Moving Average update (FedEMA). FedEMA updates local models of clients adaptively using EMA of the global model, where the decay rate is dynamically measured by model divergence. Extensive experiments demonstrate that FedEMA outperforms existing methods by 3-4% on linear evaluation. We hope that this work will provide useful insights for future research.

arXiv:2204.03865

Frequency Selective Augmentation for Video Representation Learning

Recent self-supervised video representation learning methods focus on maximizing the similarity between multiple augmented views from the same video and largely rely on the quality of generated views. However, most existing methods lack a mechanism to prevent representation learning from bias towards static information in the video. In this paper, we propose frequency augmentation (FreqAug), a spatio-temporal data augmentation method in the frequency domain for video representation learning. FreqAug stochastically removes specific frequency components from the video so that learned representation captures essential features more from the remaining information for various downstream tasks. Specifically, FreqAug pushes the model to focus more on dynamic features rather than static features in the video via dropping spatial or temporal low-frequency components. To verify the generality of the proposed method, we experiment with FreqAug on multiple self-supervised learning frameworks along with standard augmentations. Transferring the improved representation to five video action recognition and two temporal action localization downstream tasks shows consistent improvements over baselines.

arXiv:2204.03863

Automatic Pronunciation Assessment using Self-Supervised Speech Representation Learning

Self-supervised learning (SSL) approaches such as wav2vec 2.0 and HuBERT models have shown promising results in various downstream tasks in the speech community. In particular, speech representations learned by SSL models have been shown to be effective for encoding various speech-related characteristics. In this context, we propose a novel automatic pronunciation assessment method based on SSL models. First, the proposed method fine-tunes the pre-trained SSL models with connectionist temporal classification to adapt the English pronunciation of English-as-a-second-language (ESL) learners in a data environment. Then, the layer-wise contextual representations are extracted from all across the transformer layers of the SSL models. Finally, the automatic pronunciation score is estimated using bidirectional long short-term memory with the layer-wise contextual representations and the corresponding text. We show that the proposed SSL model-based methods outperform the baselines, in terms of the Pearson correlation coefficient, on datasets of Korean ESL learner children and Speechocean762. Furthermore, we analyze how different representations of transformer layers in the SSL model affect the performance of the pronunciation assessment task.

arXiv:2204.03339공식 코드 · Papers with Code

Boosting Self-Supervised Embeddings for Speech Enhancement

Self-supervised learning (SSL) representation for speech has achieved state-of-the-art (SOTA) performance on several downstream tasks. However, there remains room for improvement in speech enhancement (SE) tasks. In this study, we used a cross-domain feature to solve the problem that SSL embeddings may lack fine-grained information to regenerate speech signals. By integrating the SSL representation and spectrogram, the result can be significantly boosted. We further study the relationship between the noise robustness of SSL representation via clean-noisy distance (CN distance) and the layer importance for SE. Consequently, we found that SSL representations with lower noise robustness are more important. Furthermore, our experiments on the VCTK-DEMAND dataset demonstrated that fine-tuning an SSL representation with an SE model can outperform the SOTA SSL-based SE methods in PESQ, CSIG and COVL without invoking complicated network architectures. In later experiments, the CN distance in SSL embeddings was observed to increase after fine-tuning. These results verify our expectations and may help design SE-related SSL training in the future.

arXiv:2204.03409

MAESTRO: Matched Speech Text Representations through Modality Matching

We present Maestro, a self-supervised training method to unify representations learnt from speech and text modalities. Self-supervised learning from speech signals aims to learn the latent structure inherent in the signal, while self-supervised learning from text attempts to capture lexical information. Learning aligned representations from unpaired speech and text sequences is a challenging task. Previous work either implicitly enforced the representations learnt from these two modalities to be aligned in the latent space through multitasking and parameter sharing or explicitly through conversion of modalities via speech synthesis. While the former suffers from interference between the two modalities, the latter introduces additional complexity. In this paper, we propose Maestro, a novel algorithm to learn unified representations from both these modalities simultaneously that can transfer to diverse downstream tasks such as Automated Speech Recognition (ASR) and Speech Translation (ST). Maestro learns unified representations through sequence alignment, duration prediction and matching embeddings in the learned space through an aligned masked-language model loss. We establish a new state-of-the-art (SOTA) on VoxPopuli multilingual ASR with a 8% relative reduction in Word Error Rate (WER), multidomain SpeechStew ASR (3.7% relative) and 21 languages to English multilingual ST on CoVoST 2 with an improvement of 2.8 BLEU averaged over 21 languages.

arXiv:2204.03219

DDOS: A MOS Prediction Framework utilizing Domain Adaptive Pre-training and Distribution of Opinion Scores

Mean opinion score (MOS) is a typical subjective evaluation metric for speech synthesis systems. Since collecting MOS is time-consuming, it would be desirable if there are accurate MOS prediction models for automatic evaluation. In this work, we propose DDOS, a novel MOS prediction model. DDOS utilizes domain adaptive pre-training to further pre-train self-supervised learning models on synthetic speech. And a proposed module is added to model the opinion score distribution of each utterance. With the proposed components, DDOS outperforms previous works on BVCC dataset. And the zero shot transfer result on BC2019 dataset is significantly improved. DDOS also wins second place in Interspeech 2022 VoiceMOS challenge in terms of system-level score.

arXiv:2204.03421

Self-supervised learning for robust voice cloning

Voice cloning is a difficult task which requires robust and informative features incorporated in a high quality TTS system in order to effectively copy an unseen speaker's voice. In our work, we utilize features learned in a self-supervised framework via the Bootstrap Your Own Latent (BYOL) method, which is shown to produce high quality speech representations when specific audio augmentations are applied to the vanilla algorithm. We further extend the augmentations in the training procedure to aid the resulting features to capture the speaker identity and to make them robust to noise and acoustic conditions. The learned features are used as pre-trained utterance-level embeddings and as inputs to a Non-Attentive Tacotron based architecture, aiming to achieve multispeaker speech synthesis without utilizing additional speaker features. This method enables us to train our model in an unlabeled multispeaker dataset as well as use unseen speaker embeddings to copy a speaker's voice. Subjective and objective evaluations are used to validate the proposed model, as well as the robustness to the acoustic conditions of the target utterance.

arXiv:2204.03310

MTI-Net: A Multi-Target Speech Intelligibility Prediction Model

Recently, deep learning (DL)-based non-intrusive speech assessment models have attracted great attention. Many studies report that these DL-based models yield satisfactory assessment performance and good flexibility, but their performance in unseen environments remains a challenge. Furthermore, compared to quality scores, fewer studies elaborate deep learning models to estimate intelligibility scores. This study proposes a multi-task speech intelligibility prediction model, called MTI-Net, for simultaneously predicting human and machine intelligibility measures. Specifically, given a speech utterance, MTI-Net is designed to predict human subjective listening test results and word error rate (WER) scores. We also investigate several methods that can improve the prediction performance of MTI-Net. First, we compare different features (including low-level features and embeddings from self-supervised learning (SSL) models) and prediction targets of MTI-Net. Second, we explore the effect of transfer learning and multi-tasking learning on training MTI-Net. Finally, we examine the potential advantages of fine-tuning SSL embeddings. Experimental results demonstrate the effectiveness of using cross-domain features, multi-task learning, and fine-tuning SSL embeddings. Furthermore, it is confirmed that the intelligibility and WER scores predicted by MTI-Net are highly correlated with the ground-truth scores.

arXiv:2204.03017

Learning from Untrimmed Videos: Self-Supervised Video Representation Learning with Hierarchical Consistency

Natural videos provide rich visual contents for self-supervised learning. Yet most existing approaches for learning spatio-temporal representations rely on manually trimmed videos, leading to limited diversity in visual patterns and limited performance gain. In this work, we aim to learn representations by leveraging more abundant information in untrimmed videos. To this end, we propose to learn a hierarchy of consistencies in videos, i.e., visual consistency and topical consistency, corresponding respectively to clip pairs that tend to be visually similar when separated by a short time span and share similar topics when separated by a long time span. Specifically, a hierarchical consistency learning framework HiCo is presented, where the visually consistent pairs are encouraged to have the same representation through contrastive learning, while the topically consistent pairs are coupled through a topical classifier that distinguishes whether they are topic related. Further, we impose a gradual sampling algorithm for proposed hierarchical consistency learning, and demonstrate its theoretical superiority. Empirically, we show that not only HiCo can generate stronger representations on untrimmed videos, it also improves the representation quality when applied to trimmed videos. This is in contrast to standard contrastive learning that fails to learn appropriate representations from untrimmed videos.

arXiv:2204.02804

Federated Self-supervised Speech Representations: Are We There Yet?

The ubiquity of microphone-enabled devices has lead to large amounts of unlabelled audio data being produced at the edge. The integration of self-supervised learning (SSL) and federated learning (FL) into one coherent system can potentially offer data privacy guarantees while also advancing the quality and robustness of speech representations. In this paper, we provide a first-of-its-kind systematic study of the feasibility and complexities for training speech SSL models under FL scenarios from the perspective of algorithms, hardware, and systems limits. Despite the high potential of their combination, we find existing system constraints and algorithmic behaviour make SSL and FL systems nearly impossible to build today. Yet critically, our results indicate specific performance bottlenecks and research opportunities that would allow this situation to be reversed. While our analysis suggests that, given existing trends in hardware, hybrid SSL and FL speech systems will not be viable until 2027. We believe this study can act as a roadmap to accelerate work towards reaching this milestone much earlier.

arXiv:2204.02697공식 코드 · Papers with Code

VNIbCReg: VICReg with Neighboring-Invariance and better-Covariance Evaluated on Non-stationary Seismic Signal Time Series

One of the latest self-supervised learning (SSL) methods, VICReg, showed a great performance both in the linear evaluation and the fine-tuning evaluation. However, VICReg is proposed in computer vision and it learns by pulling representations of random crops of an image while maintaining the representation space by the variance and covariance loss. However, VICReg would be ineffective on non-stationary time series where different parts/crops of input should be differently encoded to consider the non-stationarity. Another recent SSL proposal, Temporal Neighborhood Coding (TNC) is effective for encoding non-stationary time series. This study shows that a combination of a VICReg-style method and TNC is very effective for SSL on non-stationary time series, where a non-stationary seismic signal time series is used as an evaluation dataset.