LGAICVJun 2, 2022

Hard Negative Sampling Strategies for Contrastive Representation Learning

arXiv:2206.01197v128 citationsh-index: 18
Originality Incremental advance
AI Analysis

This addresses a key bottleneck in unsupervised contrastive learning for representation learning practitioners, though it appears incremental as it builds on existing sampling methods.

The paper tackles the challenge of selecting hard negative examples in contrastive learning without labels by introducing UnReMix, a strategy that considers anchor similarity, model uncertainty, and representativeness. Experimental results show it improves negative sample selection and downstream performance compared to state-of-the-art methods.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes