Related papers: Cross-Model Cross-Stream Learning for Self-Supervi…

Contrastive Learning (CL) performances as a rising approach to address the challenge of sparse and noisy recommendation data. Although having achieved promising results, most existing CL methods only perform either hand-crafted data or…

We present CrissCross, a self-supervised framework for learning audio-visual representations. A novel notion is introduced in our framework whereby in addition to learning the intra-modal and standard 'synchronous' cross-modal relations,…

Self-supervised learning has proved effective for skeleton-based human action understanding, which is an important yet challenging topic. Previous works mainly rely on contrastive learning or masked motion modeling paradigm to model the…

Self-supervised learning (SSL) has demonstrated its effectiveness in learning representations through comparison methods that align with human intuition. However, mainstream SSL methods heavily rely on high body datasets with single label,…

The major paradigm of applying a pre-trained language model to downstream tasks is to fine-tune it on labeled task data, which often suffers instability and low performance when the labeled examples are scarce.~One way to alleviate this…

We study how to train personalized models for different tasks on decentralized devices with limited local data. We propose "Structured Cooperative Learning (SCooL)", in which a cooperation graph across devices is generated by a graphical…

Multi-modal learning integrating medical images and tabular data has significantly advanced clinical decision-making in recent years. Self-Supervised Learning (SSL) has emerged as a powerful paradigm for pretraining these models on…

To tackle the difficulties in fitting paired real-world data for single image deraining (SID), recent unsupervised methods have achieved notable success. However, these methods often struggle to generate high-quality, rain-free images due…

Visual recognition is recently learned via either supervised learning on human-annotated image-label data or language-image contrastive learning with webly-crawled image-text pairs. While supervised learning may result in a more…

Despite their effectiveness, current deep learning models face challenges with images coming from different domains with varying appearance and content. We introduce SegCLR, a versatile framework designed to segment images across different…

Contrastive learning allows us to flexibly define powerful losses by contrasting positive pairs from sets of negative samples. Recently, the principle has also been used to learn cross-modal embeddings for video and text, yet without…

Self-supervised representation learning based on Contrastive Learning (CL) has been the subject of much attention in recent years. This is due to the excellent results obtained on a variety of subsequent tasks (in particular…

Learning effective visual representations without human supervision is a long-standing problem in computer vision. Recent advances in self-supervised learning algorithms have utilized contrastive learning, with methods such as SimCLR, which…

Technological advances facilitate the ability to acquire multimodal data, posing a challenge for recognition systems while also providing an opportunity to use the heterogeneous nature of the information to increase the generalization…

Masked image modelling (e.g., Masked AutoEncoder) and contrastive learning (e.g., Momentum Contrast) have shown impressive performance on unsupervised visual representation learning. This work presents Masked Contrastive Representation…

Unsupervised learning has been a long-standing goal of machine learning and is especially important for medical image analysis, where the learning can compensate for the scarcity of labeled datasets. A promising subclass of unsupervised…

Supervised contrastive learning (SCL) frameworks treat each class as independent and thus consider all classes to be equally important. This neglects the common scenario in which label hierarchy exists, where fine-grained classes under the…

Adaptive learning, also known as adaptive teaching, relies on learning path recommendation, which sequentially recommends personalized learning items (e.g., lectures, exercises) to satisfy the unique needs of each learner. Although it is…

Mental disorder populations exhibit pronounced heterogeneity -- that is, the significant differences between samples -- poses a significant challenge to the definition of positive pairs in contrastive learning. To address this, we propose a…

Contrastive learning has achieved great success in self-supervised visual representation learning, but existing approaches mostly ignored spatial information which is often crucial for visual representation. This paper presents…