6 datasets found

Contrastive learning is one of the most successful paradigms for self-supervised learning (SSL). In a principled way, it considers two augmented views of the same image as...

Adaptive Multi-head Contrastive Learning (AMCL) framework, which tackles intra- and inter-sample similarity and adaptive temperature mechanism re-weighting each similarity pair.

Contrastive multiview coding.

Prototypical contrastive learning of unsupervised representations.

A simple framework for contrastive learning of visual representations.

Contrastive self-supervised learning (CSL) with a prototypical regularization has been introduced in learning meaningful representations for downstream tasks that require strong...