The recently advanced unsupervised learning approaches use the siamese-like framework
to compare two" views" from the same image for learning representations. Making the two …

Unsupervised representation learning with contrastive learning achieves great success
recently. However, these methods have to duplicate each training batch to construct …

Contrastive learning models based on Siamese structure have demonstrated remarkable
performance in self-supervised learning. Such a success of contrastive learning relies on …

Contrastive learning has recently shown immense potential in unsupervised visual
representation learning. Existing studies in this track mainly focus on intra-image invariance …

Contrastive learning has been adopted as a core method for unsupervised visual
representation learning. Without human annotation, the common practice is to perform an …

Masked Autoencoder (MAE) has demonstrated superior performance on various vision tasks
via randomly masking image patches and reconstruction. However, effective data …

By leveraging contrastive learning, clustering, and other pretext tasks, unsupervised
methods for learning image representations have reached impressive results on standard …

Contrastive learning methods for unsupervised visual representation learning have reached
remarkable levels of transfer performance. We argue that the power of contrastive learning …

This paper presents SimCLR: a simple framework for contrastive learning of visual
representations. We simplify recently proposed contrastive self-supervised learning …

Self-supervised visual representation learning aims to learn useful representations without
relying on human annotations. Joint embedding approach bases on maximizing the …