<ul><li>Contrastive learning has been effective in shaping representation spaces by pulling similar samples together and pushing dissimilar ones apart.</li><li>Variational Supervised Contrastive Learning (VarCon) addresses limitations by reformulating supervised contrastive learning as variational inference over latent class variables.</li><li>VarCon maximizes a posterior-weighted evidence lower bound for efficient class-aware matching and control over intra-class dispersion in the embedding space.</li><li>Experiments show that VarCon achieves state-of-the-art performance in contrastive learning, clearer decision boundaries, semantic organization, and superior performance in few-shot learning and robustness across various augmentation strategies.</li></ul>

Variational Supervised Contrastive Learning

Discover more