论文标题
对比代表学习的硬性负面抽样策略
Hard Negative Sampling Strategies for Contrastive Representation Learning
论文作者
论文摘要
在对比学习中，挑战之一是在没有标签信息的情况下选择适当的\ textit {硬负}示例。基于特征相似性的随机抽样或重要性采样方法通常会导致次优性能。在这项工作中，我们介绍了Undemix，这是一种严格的负面抽样策略，考虑了锚点相似性，模型不确定性和代表性。几个基准的实验结果表明，与最先进的对比度学习方法相比，UNEMIX改善了阴性样品的选择，随后在下游性能。
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.
