Contrastive language-audio pre-training (CLAP) enables zero-shot (ZS) inference of audio and exhibits promising performance in several classification tasks. However, conventional audio representations are still crucial for many tasks where ZS is not applicable (e.g., regression problems). Here, we explore a new representation, a general-purpose audio-language representation, that performs well in both ZS and transfer learning. To do so, we propose a new method, M2D-CLAP, which combines self-supervised learning Masked Modeling Duo (M2D) and CLAP. M2D learns an effective representation to model audio signals, and CLAP aligns the representation with text embedding. As a result, M2D-CLAP learns a versatile representation that allows for both ZS and transfer learning. Experiments show that M2D-CLAP performs well on linear evaluation, fine-tuning, and ZS classification with a GTZAN state-of-the-art of 75.17%, thus achieving a general-purpose audio-language representation.
We investigate the construction of latent spaces through self-supervised learning to support semantically meaningful operations. Analogous to operational amplifiers, these "operational latent spaces" (OpLaS) not only demonstrate semantic structure such as clustering but also support common transformational operations with inherent semantic meaning. Some operational latent spaces are found to have arisen "unintentionally" in the progress toward some (other) self-supervised learning objective, in which unintended but still useful properties are discovered among the relationships of points in the space. Other spaces may be constructed "intentionally" by developers stipulating certain kinds of clustering or transformations intended to produce the desired structure. We focus on the intentional creation of operational latent spaces via self-supervised learning, including the introduction of rotation operators via a novel "FiLMR" layer, which can be used to enable ring-like symmetries found in some musical constructions.
Self-supervised learning (SSL), which aims to learn meaningful prior representations from unlabeled data, has been proven effective for skeleton-based action understanding. Different from the image domain, skeleton data possesses sparser spatial structures and diverse representation forms, with the absence of background clues and the additional temporal dimension, presenting new challenges for spatial-temporal motion pretext task design. Recently, many endeavors have been made for skeleton-based SSL, achieving remarkable progress. However, a systematic and thorough review is still lacking. In this paper, we conduct, for the first time, a comprehensive survey on self-supervised skeleton-based action representation learning. Following the taxonomy of context-based, generative learning, and contrastive learning approaches, we make a thorough review and benchmark of existing works and shed light on the future possible directions. Remarkably, our investigation demonstrates that most SSL works rely on the single paradigm, learning representations of a single level, and are evaluated on the action recognition task solely, which leaves the generalization power of skeleton SSL models under-explored. To this end, a novel and effective SSL method for skeleton is further proposed, which integrates versatile representation learning objectives of different granularity, substantially boosting the generalization capacity for multiple skeleton downstream tasks. Extensive experiments under three large-scale datasets demonstrate our method achieves superior generalization performance on various downstream tasks, including recognition, retrieval, detection, and few-shot learning.
Depth maps produced by consumer-grade sensors suffer from inaccurate measurements and missing data from either system or scene-specific sources. Data-driven denoising algorithms can mitigate such problems. However, they require vast amounts of ground truth depth data. Recent research has tackled this limitation using self-supervised learning techniques, but it requires multiple RGB-D sensors. Moreover, most existing approaches focus on denoising single isolated depth maps or specific subjects of interest, highlighting a need for methods to effectively denoise depth maps in real-time dynamic environments. This paper extends state-of-the-art approaches for depth-denoising commodity depth devices, proposing SelfReDepth, a self-supervised deep learning technique for depth restoration, via denoising and hole-filling by inpainting full-depth maps captured with RGB-D sensors. The algorithm targets depth data in video streams, utilizing multiple sequential depth frames coupled with color data to achieve high-quality depth videos with temporal coherence. Finally, SelfReDepth is designed to be compatible with various RGB-D sensors and usable in real-time scenarios as a pre-processing step before applying other depth-dependent algorithms. Our results demonstrate our approach's real-time performance on real-world datasets. They show that it outperforms state-of-the-art denoising and restoration performance at over 30fps on Commercial Depth Cameras, with potential benefits for augmented and mixed-reality applications.
Self-supervised learning (SSL) has become the de facto training paradigm of large models, where pre-training is followed by supervised fine-tuning using domain-specific data and labels. Despite demonstrating comparable performance with supervised methods, comprehensive efforts to assess SSL's impact on machine learning fairness (i.e., performing equally on different demographic breakdowns) are lacking. Hypothesizing that SSL models would learn more generic, hence less biased representations, this study explores the impact of pre-training and fine-tuning strategies on fairness. We introduce a fairness assessment framework for SSL, comprising five stages: defining dataset requirements, pre-training, fine-tuning with gradual unfreezing, assessing representation similarity conditioned on demographics, and establishing domain-specific evaluation processes. We evaluate our method's generalizability on three real-world human-centric datasets (i.e., MIMIC, MESA, and GLOBEM) by systematically comparing hundreds of SSL and fine-tuned models on various dimensions spanning from the intermediate representations to appropriate evaluation metrics. Our findings demonstrate that SSL can significantly improve model fairness, while maintaining performance on par with supervised methods-exhibiting up to a 30% increase in fairness with minimal loss in performance through self-supervision. We posit that such differences can be attributed to representation dissimilarities found between the best- and the worst-performing demographics across models-up to x13 greater for protected attributes with larger performance discrepancies between segments.
Recent advancements in Self-Supervised Learning (SSL) have shown promising results in Speaker Verification (SV). However, narrowing the performance gap with supervised systems remains an ongoing challenge. Several studies have observed that speech representations from large-scale ASR models contain valuable speaker information. This work explores the limitations of fine-tuning these models for SV using an SSL contrastive objective in an end-to-end approach. Then, we propose a framework to learn speaker representations in an SSL context by fine-tuning a pre-trained WavLM with a supervised loss using pseudo-labels. Initial pseudo-labels are derived from an SSL DINO-based model and are iteratively refined by clustering the model embeddings. Our method achieves 0.99% EER on VoxCeleb1-O, establishing the new state-of-the-art on self-supervised SV. As this performance is close to our supervised baseline of 0.94% EER, this contribution is a step towards supervised performance on SV with SSL.
Cardiac Magnetic Resonance (CMR) imaging serves as the gold-standard for evaluating cardiac morphology and function. Typically, a multi-view CMR stack, covering short-axis (SA) and 2/3/4-chamber long-axis (LA) views, is acquired for a thorough cardiac assessment. However, efficiently streamlining the complex, high-dimensional 3D+T CMR data and distilling compact, coherent representation remains a challenge. In this work, we introduce a whole-heart self-supervised learning framework that utilizes masked imaging modeling to automatically uncover the correlations between spatial and temporal patches throughout the cardiac stacks. This process facilitates the generation of meaningful and well-clustered heart representations without relying on the traditionally required, and often costly, labeled data. The learned heart representation can be directly used for various downstream tasks. Furthermore, our method demonstrates remarkable robustness, ensuring consistent representations even when certain CMR planes are missing/flawed. We train our model on 14,000 unlabeled CMR data from UK BioBank and evaluate it on 1,000 annotated data. The proposed method demonstrates superior performance to baselines in tasks that demand comprehensive 3D+T cardiac information, e.g. cardiac phenotype (ejection fraction and ventricle volume) prediction and multi-plane/multi-frame CMR segmentation, highlighting its effectiveness in extracting comprehensive cardiac features that are both anatomically and pathologically relevant.
Self-supervised learning (SSL) has potential for effective representation learning in medical imaging, but the choice of data augmentation is critical and domain-specific. It remains uncertain if general augmentation policies suit surgical applications. In this work, we automate the search for suitable augmentation policies through a new method called Dimensionality Driven Augmentation Search (DDA). DDA leverages the local dimensionality of deep representations as a proxy target, and differentiably searches for suitable data augmentation policies in contrastive learning. We demonstrate the effectiveness and efficiency of DDA in navigating a large search space and successfully identifying an appropriate data augmentation policy for laparoscopic surgery. We systematically evaluate DDA across three laparoscopic image classification and segmentation tasks, where it significantly improves over existing baselines. Furthermore, DDA's optimised set of augmentations provides insight into domain-specific dependencies when applying contrastive learning in medical applications. For example, while hue is an effective augmentation for natural images, it is not advantageous for laparoscopic images.
We design a system that learns how to edit visual programs. Our edit network consumes a complete input program and a visual target. From this input, we task our network with predicting a local edit operation that could be applied to the input program to improve its similarity to the target. In order to apply this scheme for domains that lack program annotations, we develop a self-supervised learning approach that integrates this edit network into a bootstrapped finetuning loop along with a network that predicts entire programs in one-shot. Our joint finetuning scheme, when coupled with an inference procedure that initializes a population from the one-shot model and evolves members of this population with the edit network, helps to infer more accurate visual programs. Over multiple domains, we experimentally compare our method against the alternative of using only the one-shot model, and find that even under equal search-time budgets, our editing-based paradigm provides significant advantages.
Recommender systems help users navigate information overload by providing personalized recommendations aligned with their preferences. Collaborative Filtering (CF) is a widely adopted approach, but while advanced techniques like graph neural networks (GNNs) and self-supervised learning (SSL) have enhanced CF models for better user representations, they often lack the ability to provide explanations for the recommended items. Explainable recommendations aim to address this gap by offering transparency and insights into the recommendation decision-making process, enhancing users' understanding. This work leverages the language capabilities of Large Language Models (LLMs) to push the boundaries of explainable recommender systems. We introduce a model-agnostic framework called XRec, which enables LLMs to provide comprehensive explanations for user behaviors in recommender systems. By integrating collaborative signals and designing a lightweight collaborative adaptor, the framework empowers LLMs to understand complex patterns in user-item interactions and gain a deeper understanding of user preferences. Our extensive experiments demonstrate the effectiveness of XRec, showcasing its ability to generate comprehensive and meaningful explanations that outperform baseline approaches in explainable recommender systems. We open-source our model implementation at https://github.com/HKUDS/XRec.
The utilization of deep learning on electrocardiogram (ECG) analysis has brought the advanced accuracy and efficiency of cardiac healthcare diagnostics. By leveraging the capabilities of deep learning in semantic understanding, especially in feature extraction and representation learning, this study introduces a new multimodal contrastive pretaining framework that aims to improve the quality and robustness of learned representations of 12-lead ECG signals. Our framework comprises two key components, including Cardio Query Assistant (CQA) and ECG Semantics Integrator(ESI). CQA integrates a retrieval-augmented generation (RAG) pipeline to leverage large language models (LLMs) and external medical knowledge to generate detailed textual descriptions of ECGs. The generated text is enriched with information about demographics and waveform patterns. ESI integrates both contrastive and captioning loss to pretrain ECG encoders for enhanced representations. We validate our approach through various downstream tasks, including arrhythmia detection and ECG-based subject identification. Our experimental results demonstrate substantial improvements over strong baselines in these tasks. These baselines encompass supervised and self-supervised learning methods, as well as prior multimodal pretraining approaches.
Severe data imbalance naturally exists among web-scale vision-language datasets. Despite this, we find CLIP pre-trained thereupon exhibits notable robustness to the data imbalance compared to supervised learning, and demonstrates significant effectiveness in learning generalizable representations. With an aim to investigate the reasons behind this finding, we conduct controlled experiments to study various underlying factors, and reveal that CLIP's pretext task forms a dynamic classification problem wherein only a subset of classes is present in training. This isolates the bias from dominant classes and implicitly balances the learning signal. Furthermore, the robustness and discriminability of CLIP improve with more descriptive language supervision, larger data scale, and broader open-world concepts, which are inaccessible to supervised learning. Our study not only uncovers the mechanisms behind CLIP's generalizability beyond data imbalance but also provides transferable insights for the research community. The findings are validated in both supervised and self-supervised learning, enabling models trained on imbalanced data to achieve CLIP-level performance on diverse recognition tasks. Code and data are available at: https://github.com/CVMI-Lab/clip-beyond-tail.
Sign language recognition (SLR) has long been plagued by insufficient model representation capabilities. Although current pre-training approaches have alleviated this dilemma to some extent and yielded promising performance by employing various pretext tasks on sign pose data, these methods still suffer from two primary limitations: 1) Explicit motion information is usually disregarded in previous pretext tasks, leading to partial information loss and limited representation capability. 2) Previous methods focus on the local context of a sign pose sequence, without incorporating the guidance of the global meaning of lexical signs. To this end, we propose a Motion-Aware masked autoencoder with Semantic Alignment (MASA) that integrates rich motion cues and global semantic information in a self-supervised learning paradigm for SLR. Our framework contains two crucial components, i.e., a motion-aware masked autoencoder (MA) and a momentum semantic alignment module (SA). Specifically, in MA, we introduce an autoencoder architecture with a motion-aware masked strategy to reconstruct motion residuals of masked frames, thereby explicitly exploring dynamic motion cues among sign pose sequences. Moreover, in SA, we embed our framework with global semantic awareness by aligning the embeddings of different augmented samples from the input sequence in the shared latent space. In this way, our framework can simultaneously learn local motion cues and global semantic features for comprehensive sign language representation. Furthermore, we conduct extensive experiments to validate the effectiveness of our method, achieving new state-of-the-art performance on four public benchmarks.
Sequential recommendation effectively addresses information overload by modeling users' temporal and sequential interaction patterns. To overcome the limitations of supervision signals, recent approaches have adopted self-supervised learning techniques in recommender systems. However, there are still two critical challenges that remain unsolved. Firstly, existing sequential models primarily focus on long-term modeling of individual interaction sequences, overlooking the valuable short-term collaborative relationships among the behaviors of different users. Secondly, real-world data often contain noise, particularly in users' short-term behaviors, which can arise from temporary intents or misclicks. Such noise negatively impacts the accuracy of both graph and sequence models, further complicating the modeling process. To address these challenges, we propose a novel framework called Self-Supervised Graph Neural Network (SelfGNN) for sequential recommendation. The SelfGNN framework encodes short-term graphs based on time intervals and utilizes Graph Neural Networks (GNNs) to learn short-term collaborative relationships. It captures long-term user and item representations at multiple granularity levels through interval fusion and dynamic behavior modeling. Importantly, our personalized self-augmented learning structure enhances model robustness by mitigating noise in short-term graphs based on long-term user interests and personal stability. Extensive experiments conducted on four real-world datasets demonstrate that SelfGNN outperforms various state-of-the-art baselines. Our model implementation codes are available at https://github.com/HKUDS/SelfGNN.
Skeleton-based action representation learning aims to interpret and understand human behaviors by encoding the skeleton sequences, which can be categorized into two primary training paradigms: supervised learning and self-supervised learning. However, the former one-hot classification requires labor-intensive predefined action categories annotations, while the latter involves skeleton transformations (e.g., cropping) in the pretext tasks that may impair the skeleton structure. To address these challenges, we introduce a novel skeleton-based training framework (C$^2$VL) based on Cross-modal Contrastive learning that uses the progressive distillation to learn task-agnostic human skeleton action representation from the Vision-Language knowledge prompts. Specifically, we establish the vision-language action concept space through vision-language knowledge prompts generated by pre-trained large multimodal models (LMMs), which enrich the fine-grained details that the skeleton action space lacks. Moreover, we propose the intra-modal self-similarity and inter-modal cross-consistency softened targets in the cross-modal representation learning process to progressively control and guide the degree of pulling vision-language knowledge prompts and corresponding skeletons closer. These soft instance discrimination and self-knowledge distillation strategies contribute to the learning of better skeleton-based action representations from the noisy skeleton-vision-language pairs. During the inference phase, our method requires only the skeleton data as the input for action recognition and no longer for vision-language prompts. Extensive experiments on NTU RGB+D 60, NTU RGB+D 120, and PKU-MMD datasets demonstrate that our method outperforms the previous methods and achieves state-of-the-art results. Code is available at: https://github.com/cseeyangchen/C2VL.
Graph neural networks (GNNs) have achieved great success for a variety of tasks such as node classification, graph classification, and link prediction. However, the use of GNNs (and machine learning more generally) to solve combinatorial optimization (CO) problems is much less explored. Here, we introduce GCON, a novel GNN architecture that leverages a complex filter bank and localized attention mechanisms to solve CO problems on graphs. We show how our method differentiates itself from prior GNN-based CO solvers and how it can be effectively applied to the maximum cut, minimum dominating set, and maximum clique problems in a unsupervised learning setting. GCON is competitive across all tasks and consistently outperforms other specialized GNN-based approaches, and is on par with the powerful Gurobi solver on the max-cut problem. We provide an open-source implementation of our work at https://github.com/WenkelF/copt.
Rapid detection and well-timed intervention are essential to mitigate the impacts of wildfires. Leveraging remote sensed data from satellite networks and advanced AI models to automatically detect hotspots (i.e., thermal anomalies caused by active fires) is an effective way to build wildfire monitoring systems. In this work, we propose a novel dataset containing time series of remotely sensed data related to European fire events and a Self-Supervised Learning (SSL)-based model able to analyse multi-temporal data and identify hotspots in potentially near real time. We train and evaluate the performance of our model using our dataset and Thraws, a dataset of thermal anomalies including several fire events, obtaining an F1 score of 63.58.
Contrastive pre-training on image-text pairs, exemplified by CLIP, becomes a standard technique for learning multi-modal visual-language representations. Although CLIP has demonstrated remarkable performance, training it from scratch on noisy web-scale datasets is computationally demanding. On the other hand, mask-then-predict pre-training approaches, like Masked Image Modeling (MIM), offer efficient self-supervised learning for single-modal representations. This paper introduces Unmasked Token Alignment (UTA), a method that leverages existing CLIP models to further enhance its vision-language representations. UTA trains a Vision Transformer (ViT) by aligning unmasked visual tokens to the corresponding image tokens from a frozen CLIP vision encoder, which automatically aligns the ViT model with the CLIP text encoder. The pre-trained ViT can be directly applied for zero-shot evaluation even without training on image-text pairs. Compared to MIM approaches, UTA does not suffer from training-finetuning inconsistency and is much more training-efficient by avoiding using the extra [MASK] tokens. Extensive experimental results demonstrate that UTA can enhance CLIP models and outperform existing MIM methods on various uni- and multi-modal benchmarks. Code and models are available at https://github.com/jihaonew/UTA.
Constructing large-scale labeled datasets for multi-modal perception model training in autonomous driving presents significant challenges. This has motivated the development of self-supervised pretraining strategies. However, existing pretraining methods mainly employ distinct approaches for each modality. In contrast, we focus on LiDAR-Camera 3D perception models and introduce a unified pretraining strategy, NeRF-Supervised Masked Auto Encoder (NS-MAE), which optimizes all modalities through a shared formulation. NS-MAE leverages NeRF's ability to encode both appearance and geometry, enabling efficient masked reconstruction of multi-modal data. Specifically, embeddings are extracted from corrupted LiDAR point clouds and images, conditioned on view directions and locations. Then, these embeddings are rendered into multi-modal feature maps from two crucial viewpoints for 3D driving perception: perspective and bird's-eye views. The original uncorrupted data serve as reconstruction targets for self-supervised learning. Extensive experiments demonstrate the superior transferability of NS-MAE across various 3D perception tasks under different fine-tuning settings. Notably, NS-MAE outperforms prior SOTA pre-training methods that employ separate strategies for each modality in BEV map segmentation under the label-efficient fine-tuning setting. Our code is publicly available at https://github.com/Xiaohao-Xu/Unified-Pretrain-AD/ .
We present SSL-HV: Self-Supervised Learning approaches applied to the task of Handwriting Verification. This task involves determining whether a given pair of handwritten images originate from the same or different writer distribution. We have compared the performance of multiple generative, contrastive SSL approaches against handcrafted feature extractors and supervised learning on CEDAR AND dataset. We show that ResNet based Variational Auto-Encoder (VAE) outperforms other generative approaches achieving 76.3% accuracy, while ResNet-18 fine-tuned using Variance-Invariance-Covariance Regularization (VICReg) outperforms other contrastive approaches achieving 78% accuracy. Using a pre-trained VAE and VICReg for the downstream task of writer verification we observed a relative improvement in accuracy of 6.7% and 9% over ResNet-18 supervised baseline with 10% writer labels.