Self-supervised learning (SSL) has led to important breakthroughs in computer vision by allowing learning from large amounts of unlabeled data. As such, it might have a pivotal role to play in biomedicine where annotating data requires a highly specialized expertise. Yet, there are many healthcare domains for which SSL has not been extensively explored. One such domain is endoscopy, minimally invasive procedures which are commonly used to detect and treat infections, chronic inflammatory diseases or cancer. In this work, we study the use of a leading SSL framework, namely Masked Siamese Networks (MSNs), for endoscopic video analysis such as colonoscopy and laparoscopy. To fully exploit the power of SSL, we create sizable unlabeled endoscopic video datasets for training MSNs. These strong image representations serve as a foundation for secondary training with limited annotated datasets, resulting in state-of-the-art performance in endoscopic benchmarks like surgical phase recognition during laparoscopy and colonoscopic polyp characterization. Additionally, we achieve a 50% reduction in annotated data size without sacrificing performance. Thus, our work provides evidence that SSL can dramatically reduce the need of annotated data in endoscopy.
Existing representation-based methods usually conduct industrial anomaly detection in two stages: obtain feature representations with a pre-trained model and perform distance measures for anomaly detection. Among them, K-nearest neighbor (KNN) retrieval-based anomaly detection methods show promising results. However, the features are not fully exploited as these methods ignore domain bias of pre-trained models and the difference of local density in feature space, which limits the detection performance. In this paper, we propose Reducing Biases (REB) in representation by considering the domain bias and building a self-supervised learning task for better domain adaption with a defect generation strategy (DefectMaker) that ensures a strong diversity in the synthetic defects. Additionally, we propose a local-density KNN (LDKNN) to reduce the local density bias in the feature space and obtain effective anomaly detection. The proposed REB method achieves a promising result of 99.5\% Im.AUROC on the widely used MVTec AD, with smaller backbone networks such as Vgg11 and Resnet18. The method also achieves an impressive 88.8\% Im.AUROC on the MVTec LOCO AD dataset and a remarkable 96.0\% on the BTAD dataset, outperforming other representation-based approaches. These results indicate the effectiveness and efficiency of REB for practical industrial applications. Code:https://github.com/ShuaiLYU/REB.
Synthetic Aperture Sonar (SAS) imaging has become a crucial technology for underwater exploration because of its unique ability to maintain resolution at increasing ranges, a characteristic absent in conventional sonar techniques. However, the effective application of deep learning to SAS data processing is often limited due to the scarcity of labeled data. To address this challenge, this paper proposes MoCo-SAS that leverages self-supervised learning (SSL) for SAS data processing, classification, and pattern recognition. The experimental results demonstrate that MoCo-SAS significantly outperforms traditional supervised learning methods, as evidenced by significant improvements observed in terms of the F1-score. These findings highlight the potential of SSL in advancing the state-of-the-art in SAS data processing, offering promising avenues for enhanced underwater object detection and classification.
Spatially dense self-supervised learning is a rapidly growing problem domain with promising applications for unsupervised segmentation and pretraining for dense downstream tasks. Despite the abundance of temporal data in the form of videos, this information-rich source has been largely overlooked. Our paper aims to address this gap by proposing a novel approach that incorporates temporal consistency in dense self-supervised learning. While methods designed solely for images face difficulties in achieving even the same performance on videos, our method improves not only the representation quality for videos-but also images. Our approach, which we call time-tuning, starts from image-pretrained models and fine-tunes them with a novel self-supervised temporal-alignment clustering loss on unlabeled videos. This effectively facilitates the transfer of high-level information from videos to image representations. Time-tuning improves the state-of-the-art by 8-10% for unsupervised semantic segmentation on videos and matches it for images. We believe this method paves the way for further self-supervised scaling by leveraging the abundant availability of videos. The implementation can be found here : https://github.com/SMSD75/Timetuning
Scene Graph Generation (SGG) as a critical task in image understanding, facing the challenge of head-biased prediction caused by the long-tail distribution of predicates. However, current unbiased SGG methods can easily prioritize improving the prediction of tail predicates while ignoring the substantial sacrifice in the prediction of head predicates, leading to a shift from head bias to tail bias. To address this issue, we propose a model-agnostic Head-Tail Collaborative Learning (HTCL) network that includes head-prefer and tail-prefer feature representation branches that collaborate to achieve accurate recognition of both head and tail predicates. We also propose a self-supervised learning approach to enhance the prediction ability of the tail-prefer feature representation branch by constraining tail-prefer predicate features. Specifically, self-supervised learning converges head predicate features to their class centers while dispersing tail predicate features as much as possible through contrast learning and head center loss. We demonstrate the effectiveness of our HTCL by applying it to various SGG models on VG150, Open Images V6 and GQA200 datasets. The results show that our method achieves higher mean Recall with a minimal sacrifice in Recall and achieves a new state-of-the-art overall performance. Our code is available at https://github.com/wanglei0618/HTCL.
Self-supervised pretraining (SSP) has emerged as a popular technique in machine learning, enabling the extraction of meaningful feature representations without labelled data. In the realm of computer vision, pretrained vision transformers (ViTs) have played a pivotal role in advancing transfer learning. Nonetheless, the escalating cost of finetuning these large models has posed a challenge due to the explosion of model size. This study endeavours to evaluate the effectiveness of pure self-supervised learning (SSL) techniques in computer vision tasks, obviating the need for finetuning, with the intention of emulating human-like capabilities in generalisation and recognition of unseen objects. To this end, we propose an evaluation protocol for zero-shot segmentation based on a prompting patch. Given a point on the target object as a prompt, the algorithm calculates the similarity map between the selected patch and other patches, upon that, a simple thresholding is applied to segment the target. Another evaluation is intra-object and inter-object similarity to gauge discriminatory ability of SSP ViTs. Insights from zero-shot segmentation from prompting and discriminatory abilities of SSP led to the design of a simple SSP approach, termed MMC. This approaches combines Masked image modelling for encouraging similarity of local features, Momentum based self-distillation for transferring semantics from global to local features, and global Contrast for promoting semantics of global features, to enhance discriminative representations of SSP ViTs. Consequently, our proposed method significantly reduces the overlap of intra-object and inter-object similarities, thereby facilitating effective object segmentation within an image. Our experiments reveal that MMC delivers top-tier results in zero-shot semantic segmentation across various datasets.
Wav2vec2 has achieved success in applying Transformer architecture and self-supervised learning to speech recognition. Recently, these have come to be used not only for speech recognition but also for the entire speech processing. This paper introduces an effective end-to-end speaker identification model applied Transformer-based contextual model. We explored the relationship between the hyper-parameters and the performance in order to discern the structure of an effective model. Furthermore, we propose a pooling method, Temporal Gate Pooling, with powerful learning ability for speaker identification. We applied Conformer as encoder and BEST-RQ for pre-training and conducted an evaluation utilizing the speaker identification of VoxCeleb1. The proposed method has achieved an accuracy of 87.1% with 28.5M parameters, demonstrating comparable precision to wav2vec2 with 317.7M parameters. Code is available at https://github.com/HarunoriKawano/speaker-identification-with-tgp.
Large-scale foundation models, such as CLIP, have demonstrated remarkable success in visual recognition tasks by embedding images in a semantically rich space. Self-supervised learning (SSL) has also shown promise in improving visual recognition by learning invariant features. However, the combination of CLIP with SSL is found to face challenges due to the multi-task framework that blends CLIP's contrastive loss and SSL's loss, including difficulties with loss weighting and inconsistency among different views of images in CLIP's output space. To overcome these challenges, we propose a prompt learning-based model called GOPro, which is a unified framework that ensures similarity between various augmented views of input images in a shared image-text embedding space, using a pair of learnable image and text projectors atop CLIP, to promote invariance and generalizability. To automatically learn such prompts, we leverage the visual content and style primitives extracted from pre-trained CLIP and adapt them to the target task. In addition to CLIP's cross-domain contrastive loss, we introduce a visual contrastive loss and a novel prompt consistency loss, considering the different views of the images. GOPro is trained end-to-end on all three loss objectives, combining the strengths of CLIP and SSL in a principled manner. Empirical evaluations demonstrate that GOPro outperforms the state-of-the-art prompting techniques on three challenging domain generalization tasks across multiple benchmarks by a significant margin. Our code is available at https://github.com/mainaksingha01/GOPro.
The success of supervised deep learning models on cell recognition tasks relies on detailed annotations. Many previous works have managed to reduce the dependency on labels. However, considering the large number of cells contained in a patch, costly and inefficient labeling is still inevitable. To this end, we explored label-free methods for cell recognition. Prior self-activation maps (PSM) are proposed to generate pseudo masks as training targets. To be specific, an activation network is trained with self-supervised learning. The gradient information in the shallow layers of the network is aggregated to generate prior self-activation maps. Afterward, a semantic clustering module is then introduced as a pipeline to transform PSMs to pixel-level semantic pseudo masks for downstream tasks. We evaluated our method on two histological datasets: MoNuSeg (cell segmentation) and BCData (multi-class cell detection). Compared with other fully-supervised and weakly-supervised methods, our method can achieve competitive performance without any manual annotations. Our simple but effective framework can also achieve multi-class cell detection which can not be done by existing unsupervised methods. The results show the potential of PSMs that might inspire other research to deal with the hunger for labels in medical area.
Transformer and its variants are a powerful class of architectures for sequential recommendation, owing to their ability of capturing a user's dynamic interests from their past interactions. Despite their success, Transformer-based models often require the optimization of a large number of parameters, making them difficult to train from sparse data in sequential recommendation. To address the problem of data sparsity, previous studies have utilized self-supervised learning to enhance Transformers, such as pre-training embeddings from item attributes or contrastive data augmentations. However, these approaches encounter several training issues, including initialization sensitivity, manual data augmentations, and large batch-size memory bottlenecks. In this work, we investigate Transformers from the perspective of loss geometry, aiming to enhance the models' data efficiency and generalization in sequential recommendation. We observe that Transformers (e.g., SASRec) can converge to extremely sharp local minima if not adequately regularized. Inspired by the recent Sharpness-Aware Minimization (SAM), we propose SAMRec, which significantly improves the accuracy and robustness of sequential recommendation. SAMRec performs comparably to state-of-the-art self-supervised Transformers, such as S$^3$Rec and CL4SRec, without the need for pre-training or strong data augmentations.
Anomaly detection (AD), aiming to find samples that deviate from the training distribution, is essential in safety-critical applications. Though recent self-supervised learning based attempts achieve promising results by creating virtual outliers, their training objectives are less faithful to AD which requires a concentrated inlier distribution as well as a dispersive outlier distribution. In this paper, we propose Unilaterally Aggregated Contrastive Learning with Hierarchical Augmentation (UniCon-HA), taking into account both the requirements above. Specifically, we explicitly encourage the concentration of inliers and the dispersion of virtual outliers via supervised and unsupervised contrastive losses, respectively. Considering that standard contrastive data augmentation for generating positive views may induce outliers, we additionally introduce a soft mechanism to re-weight each augmented inlier according to its deviation from the inlier distribution, to ensure a purified concentration. Moreover, to prompt a higher concentration, inspired by curriculum learning, we adopt an easy-to-hard hierarchical augmentation strategy and perform contrastive aggregation at different depths of the network based on the strengths of data augmentation. Our method is evaluated under three AD settings including unlabeled one-class, unlabeled multi-class, and labeled multi-class, demonstrating its consistent superiority over other competitors.
This study explores the application of self-supervised learning (SSL) to the task of motion forecasting, an area that has not yet been extensively investigated despite the widespread success of SSL in computer vision and natural language processing. To address this gap, we introduce Forecast-MAE, an extension of the mask autoencoders framework that is specifically designed for self-supervised learning of the motion forecasting task. Our approach includes a novel masking strategy that leverages the strong interconnections between agents' trajectories and road networks, involving complementary masking of agents' future or history trajectories and random masking of lane segments. Our experiments on the challenging Argoverse 2 motion forecasting benchmark show that Forecast-MAE, which utilizes standard Transformer blocks with minimal inductive bias, achieves competitive performance compared to state-of-the-art methods that rely on supervised learning and sophisticated designs. Moreover, it outperforms the previous self-supervised learning method by a significant margin. Code is available at https://github.com/jchengai/forecast-mae.
While advancing rapidly, Artificial Intelligence still falls short of human intelligence in several key aspects due to inherent limitations in current AI technologies and our understanding of cognition. Humans have an innate ability to understand context, nuances, and subtle cues in communication, which allows us to comprehend jokes, sarcasm, and metaphors. Machines struggle to interpret such contextual information accurately. Humans possess a vast repository of common-sense knowledge that helps us make logical inferences and predictions about the world. Machines lack this innate understanding and often struggle with making sense of situations that humans find trivial. In this article, we review the prospective Machine Intelligence candidates, a review from Prof. Yann LeCun, and other work that can help close this gap between human and machine intelligence. Specifically, we talk about what's lacking with the current AI techniques such as supervised learning, reinforcement learning, self-supervised learning, etc. Then we show how Hierarchical planning-based approaches can help us close that gap and deep-dive into energy-based, latent-variable methods and Joint embedding predictive architecture methods.
In healthcare and biomedical applications, extreme computational requirements pose a significant barrier to adopting representation learning. Representation learning can enhance the performance of deep learning architectures by learning useful priors from limited medical data. However, state-of-the-art self-supervised techniques suffer from reduced performance when using smaller batch sizes or shorter pretraining epochs, which are more practical in clinical settings. We present Cross Architectural - Self Supervision (CASS) in response to this challenge. This novel siamese self-supervised learning approach synergistically leverages Transformer and Convolutional Neural Networks (CNN) for efficient learning. Our empirical evaluation demonstrates that CASS-trained CNNs and Transformers outperform existing self-supervised learning methods across four diverse healthcare datasets. With only 1% labeled data for finetuning, CASS achieves a 3.8% average improvement; with 10% labeled data, it gains 5.9%; and with 100% labeled data, it reaches a remarkable 10.13% enhancement. Notably, CASS reduces pretraining time by 69% compared to state-of-the-art methods, making it more amenable to clinical implementation. We also demonstrate that CASS is considerably more robust to variations in batch size and pretraining epochs, making it a suitable candidate for machine learning in healthcare applications.
Instance segmentation in electron microscopy (EM) volumes is tough due to complex shapes and sparse annotations. Self-supervised learning helps but still struggles with intricate visual patterns in EM. To address this, we propose a pretraining framework that enhances multiscale consistency in EM volumes. Our approach leverages a Siamese network architecture, integrating both strong and weak data augmentations to effectively extract multiscale features. We uphold voxel-level coherence by reconstructing the original input data from these augmented instances. Furthermore, we incorporate cross-attention mechanisms to facilitate fine-grained feature alignment between these augmentations. Finally, we apply contrastive learning techniques across a feature pyramid, allowing us to distill distinctive representations spanning various scales. After pretraining on four large-scale EM datasets, our framework significantly improves downstream tasks like neuron and mitochondria segmentation, especially with limited finetuning data. It effectively captures voxel and feature consistency, showing promise for learning transferable representations for EM analysis.
Recommender systems have become indispensable in music streaming services, enhancing user experiences by personalizing playlists and facilitating the serendipitous discovery of new music. However, the existing recommender systems overlook the unique challenges inherent in the music domain, specifically shuffle play, which provides subsequent tracks in a random sequence. Based on our observation that the shuffle play sessions hinder the overall training process of music recommender systems mainly due to the high unique transition rates of shuffle play sessions, we propose a Music Recommender System with Shuffle Play Recommendation Enhancement (MUSE). MUSE employs the self-supervised learning framework that maximizes the agreement between the original session and the augmented session, which is augmented by our novel session augmentation method, called transition-based augmentation. To further facilitate the alignment of the representations between the two views, we devise two fine-grained matching strategies, i.e., item- and similarity-based matching strategies. Through rigorous experiments conducted across diverse environments, we demonstrate MUSE's efficacy over 12 baseline models on a large-scale Music Streaming Sessions Dataset (MSSD) from Spotify. The source code of MUSE is available at \url{https://github.com/yunhak0/MUSE}.
With the proliferation of social media, a growing number of users search for and join group activities in their daily life. This develops a need for the study on the group identification (GI) task, i.e., recommending groups to users. The major challenge in this task is how to predict users' preferences for groups based on not only previous group participation of users but also users' interests in items. Although recent developments in Graph Neural Networks (GNNs) accomplish embedding multiple types of objects in graph-based recommender systems, they, however, fail to address this GI problem comprehensively. In this paper, we propose a novel framework named Group Identification via Transitional Hypergraph Convolution with Graph Self-supervised Learning (GTGS). We devise a novel transitional hypergraph convolution layer to leverage users' preferences for items as prior knowledge when seeking their group preferences. To construct comprehensive user/group representations for GI task, we design the cross-view self-supervised learning to encourage the intrinsic consistency between item and group preferences for each user, and the group-based regularization to enhance the distinction among group embeddings. Experimental results on three benchmark datasets verify the superiority of GTGS. Additional detailed investigations are conducted to demonstrate the effectiveness of the proposed framework.
Graph representation learning (GRL) methods, such as graph neural networks and graph transformer models, have been successfully used to analyze graph-structured data, mainly focusing on node classification and link prediction tasks. However, the existing studies mostly only consider local connectivity while ignoring long-range connectivity and the roles of nodes. In this paper, we propose Unified Graph Transformer Networks (UGT) that effectively integrate local and global structural information into fixed-length vector representations. First, UGT learns local structure by identifying the local substructures and aggregating features of the $k$-hop neighborhoods of each node. Second, we construct virtual edges, bridging distant nodes with structural similarity to capture the long-range dependencies. Third, UGT learns unified representations through self-attention, encoding structural distance and $p$-step transition probability between node pairs. Furthermore, we propose a self-supervised learning task that effectively learns transition probability to fuse local and global structural features, which could then be transferred to other downstream tasks. Experimental results on real-world benchmark datasets over various downstream tasks showed that UGT significantly outperformed baselines that consist of state-of-the-art models. In addition, UGT reaches the expressive power of the third-order Weisfeiler-Lehman isomorphism test (3d-WL) in distinguishing non-isomorphic graph pairs. The source code is available at https://github.com/NSLab-CUK/Unified-Graph-Transformer.
Message passing neural networks have shown a lot of success on graph-structured data. However, there are many instances where message passing can lead to over-smoothing or fail when neighboring nodes belong to different classes. In this work, we introduce a simple yet general framework for improving learning in message passing neural networks. Our approach essentially upsamples edges in the original graph by adding "slow nodes" at each edge that can mediate communication between a source and a target node. Our method only modifies the input graph, making it plug-and-play and easy to use with existing models. To understand the benefits of slowing down message passing, we provide theoretical and empirical analyses. We report results on several supervised and self-supervised benchmarks, and show improvements across the board, notably in heterophilic conditions where adjacent nodes are more likely to have different labels. Finally, we show how our approach can be used to generate augmentations for self-supervised learning, where slow nodes are randomly introduced into different edges in the graph to generate multi-scale views with variable path lengths.
Body language (BL) refers to the non-verbal communication expressed through physical movements, gestures, facial expressions, and postures. It is a form of communication that conveys information, emotions, attitudes, and intentions without the use of spoken or written words. It plays a crucial role in interpersonal interactions and can complement or even override verbal communication. Deep multi-modal learning techniques have shown promise in understanding and analyzing these diverse aspects of BL. The survey emphasizes their applications to BL generation and recognition. Several common BLs are considered i.e., Sign Language (SL), Cued Speech (CS), Co-speech (CoS), and Talking Head (TH), and we have conducted an analysis and established the connections among these four BL for the first time. Their generation and recognition often involve multi-modal approaches. Benchmark datasets for BL research are well collected and organized, along with the evaluation of SOTA methods on these datasets. The survey highlights challenges such as limited labeled data, multi-modal learning, and the need for domain adaptation to generalize models to unseen speakers or languages. Future research directions are presented, including exploring self-supervised learning techniques, integrating contextual information from other modalities, and exploiting large-scale pre-trained multi-modal models. In summary, this survey paper provides a comprehensive understanding of deep multi-modal learning for various BL generations and recognitions for the first time. By analyzing advancements, challenges, and future directions, it serves as a valuable resource for researchers and practitioners in advancing this field. n addition, we maintain a continuously updated paper list for deep multi-modal learning for BL recognition and generation: https://github.com/wentaoL86/awesome-body-language.