In the last decade, deep supervised learning has had tremendous success. However, its
flaws, such as its dependency on manual and costly annotations on large datasets and …

Current semantic segmentation methods focus only on mining" local" context, ie,
dependencies between pixels within individual images, by context-aggregation modules …

Unsupervised contrastive learning has achieved outstanding success, while the mechanism
of contrastive loss has been less studied. In this paper, we concentrate on the understanding …

Contrastive learning has become a key component of self-supervised learning approaches
for computer vision. By learning to embed two augmented versions of the same image close …

Deep neural networks currently provide the best quantitative models of the response
patterns of neurons throughout the primate ventral visual stream. However, such networks …

Recent self-supervised contrastive learning methods greatly benefit from the Siamese
structure that aims at minimizing distances between positive pairs. For high performance …

Despite the empirical successes of self-supervised learning (SSL) methods, it is unclear
what characteristics of their representations lead to high downstream accuracies. In this …

Contrastive learning has been shown to produce generalizable representations of audio
and visual data by maximizing the lower bound on the mutual information (MI) between …

Abstract Graph Contrastive Learning (GCL) has emerged to learn generalizable
representations from contrastive views. However, it is still in its infancy with two concerns: 1) …

In a wide range of multimodal tasks, contrastive learning has become a particularly
appealing approach since it can successfully learn representations from abundant …