Hard Negative Sampling Strategies for Contrastive Representation Learning
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:EOYZZ3M6record.jsonopen to challenge →
read the original 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.
This paper has not been read by Pith yet.
Forward citations
Cited by 2 Pith papers
-
Optimal Representations for Generalized Contrastive Learning with Imbalanced Datasets
In generalized contrastive learning with imbalanced classes, optimal representations collapse to class means whose angular geometry is determined by class proportions via convex optimization, and extreme imbalance cau...
-
HNC: Leveraging Hard Negative Captions towards Models with Fine-Grained Visual-Linguistic Comprehension Capabilities
Training on automatically generated hard negative captions improves vision-language models' zero-shot detection of fine-grained image-text mismatches and robustness to noisy inputs.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.