Related papers: Combating Representation Learning Disparity with G…

Semi-supervised learning (SSL) over graph-structured data emerges in many network science applications. To efficiently manage learning over graphs, variants of graph neural networks (GNNs) have been developed recently. By succinctly…

Skeleton-based action recognition has recently made significant progress. However, data imbalance is still a great challenge in real-world scenarios. The performance of current action recognition algorithms declines sharply when training…

Self-supervised learning (SSL) approaches have shown promising capabilities in learning the representation from unlabeled data. Amongst them, momentum-based frameworks have attracted significant attention. Despite being a great success,…

Real-world data often follow a long-tailed distribution with a high imbalance in the number of samples between classes. The problem with training from imbalanced data is that some background features, common to all classes, can be…

Self-supervised learning (especially contrastive learning) methods on heterogeneous graphs can effectively get rid of the dependence on supervisory data. Meanwhile, most existing representation learning methods embed the heterogeneous…

Deep Metric Learning (DML) methods have been proven relevant for visual similarity learning. However, they sometimes lack generalization properties because they are trained often using an inappropriate sample selection strategy or due to…

Generative self-supervised learning (SSL), especially masked autoencoders, has become one of the most exciting learning paradigms and has shown great potential in handling graph data. However, real-world graphs are always heterogeneous,…

Deep learning has achieved remarkable progress for visual recognition on large-scale balanced datasets but still performs poorly on real-world long-tailed data. Previous methods often adopt class re-balanced training strategies to…

Self-supervised learning (SSL) methods aim to learn view-invariant representations by maximizing the similarity between the features extracted from different crops of the same image regardless of cropping size and content. In essence, this…

Graph Neural Networks (GNNs) struggle to balance heterophily and homophily in representation learning, a challenge further amplified in self-supervised settings. We propose H$^3$GNNs, an end-to-end self-supervised learning framework that…

Real-world data typically follow a long-tailed distribution, where a few majority categories occupy most of the data while most minority categories contain a limited number of samples. Classification models minimizing cross-entropy struggle…

Self-supervised heterogeneous graph learning (SHGL) has shown promising potential in diverse scenarios. However, while existing SHGL methods share a similar essential with clustering approaches, they encounter two significant limitations:…

Self-Supervised Learning (SSL) methods harness the concept of semantic invariance by utilizing data augmentation strategies to produce similar representations for different deformations of the same input. Essentially, the model captures the…

In the real world, long-tailed data distributions are prevalent, making it challenging for models to effectively learn and classify tail classes. However, we discover that in the field of drug chemistry, certain tail classes exhibit higher…

Generative adversarial networks (GAN) and generative diffusion models (DM) have been widely used in real-world image super-resolution (Real-ISR) to enhance the image perceptual quality. However, these generative models are prone to…

Self-supervised learning (SSL) has emerged as a powerful strategy for representation learning under limited annotation regimes, yet its effectiveness remains highly sensitive to many factors, especially the nature of the target task. In…

Self-Supervised Learning (SSL) has shown significant potential and has garnered increasing interest in graph learning. However, particularly for generative SSL methods, its potential in Heterogeneous Graph Learning (HGL) remains relatively…

Most of the current self-supervised representation learning (SSL) methods are based on the contrastive loss and the instance-discrimination task, where augmented versions of the same image instance ("positives") are contrasted with…

In this paper, we investigate what constitutes a good representation or model in self-supervised learning (SSL). We argue that a good representation should exhibit universality, characterized by three essential properties: discriminability,…

This paper proposes a novel pixel-level distribution regularization scheme (DRSL) for self-supervised domain adaptation of semantic segmentation. In a typical setting, the classification loss forces the semantic segmentation model to…