Virginia Tech® home

Hard Negative Sampling Strategies for Contrastive Representation Learning

Hoda Eldardiry, Ismini Lourentzou, Muntasir Wahed, Afrina Tabassum

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.

Publication Details

Date of publication: June 01, 2022

Journal: arXiv

Page number(s):

Volume:

Issue Number:

Publication Note: Afrina Tabassum, Muntasir Wahed, Hoda Eldardiry, Ismini Lourentzou: Hard Negative Sampling Strategies for Contrastive Representation Learning. CoRR abs/2206.01197 (2022)