Jiajun Fan

NeurIPS 2025

Variational Supervised Contrastive Learning

In brief

What the paper does.

We propose VarCon, reformulating supervised contrastive learning as variational inference over latent class variables. Achieves SOTA among contrastive learning methods: 79.36% Top-1 on ImageNet-1K with ResNet-50, with superior embedding space organization and few-shot robustness.

Published in
The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025)
Paper
openreview.net/forum?id=uOOlHOq500

Cite

Cite the paper.

@inproceedings{wang2025varcon,
  title={Variational Supervised Contrastive Learning},
  author={Wang, Ziwen and Fan, Jiajun and Nguyen, Thao and Ji, Heng and Liu, Ge},
  booktitle={Advances in Neural Information Processing Systems},
  year={2025},
  url={https://openreview.net/forum?id=uOOlHOq500}
}