English

Hard Negative Sampling Strategies for Contrastive Representation Learning

Machine Learning 2022-06-03 v1 Artificial Intelligence Computer Vision and Pattern Recognition

Abstract

One of the challenges in contrastive learning is the selection of appropriate \textit{hard negative} examples, in the absence of label information. Random sampling or importance sampling methods based on feature similarity often lead to sub-optimal performance. In this work, we introduce UnReMix, a hard negative sampling strategy that takes into account anchor similarity, model uncertainty and representativeness. Experimental results on several benchmarks show that UnReMix improves negative sample selection, and subsequently downstream performance when compared to state-of-the-art contrastive learning methods.

Keywords

Cite

@article{arxiv.2206.01197,
  title  = {Hard Negative Sampling Strategies for Contrastive Representation Learning},
  author = {Afrina Tabassum and Muntasir Wahed and Hoda Eldardiry and Ismini Lourentzou},
  journal= {arXiv preprint arXiv:2206.01197},
  year   = {2022}
}
R2 v1 2026-06-24T11:37:31.135Z