English

Conditional Alignment and Uniformity for Contrastive Learning with Continuous Proxy Labels

Machine Learning 2021-11-11 v1

Abstract

Contrastive Learning has shown impressive results on natural and medical images, without requiring annotated data. However, a particularity of medical images is the availability of meta-data (such as age or sex) that can be exploited for learning representations. Here, we show that the recently proposed contrastive y-Aware InfoNCE loss, that integrates multi-dimensional meta-data, asymptotically optimizes two properties: conditional alignment and global uniformity. Similarly to [Wang, 2020], conditional alignment means that similar samples should have similar features, but conditionally on the meta-data. Instead, global uniformity means that the (normalized) features should be uniformly distributed on the unit hyper-sphere, independently of the meta-data. Here, we propose to define conditional uniformity, relying on the meta-data, that repel only samples with dissimilar meta-data. We show that direct optimization of both conditional alignment and uniformity improves the representations, in terms of linear evaluation, on both CIFAR-100 and a brain MRI dataset.

Keywords

Cite

@article{arxiv.2111.05643,
  title  = {Conditional Alignment and Uniformity for Contrastive Learning with Continuous Proxy Labels},
  author = {Benoit Dufumier and Pietro Gori and Julie Victor and Antoine Grigis and Edouard Duchesnay},
  journal= {arXiv preprint arXiv:2111.05643},
  year   = {2021}
}

Comments

Accepted to MedNeurIPS 2021 (Oral)

R2 v1 2026-06-24T07:33:35.085Z