用语义不同的样本对学习视觉表征，突破对比学习传统
Rethinking Positive Pairs in Contrastive Learning
- 通过任意样本对优化相似性，不依赖语义相同配对
- 发现不同类别样本在子空间中可呈现相似性
- 适合研究对比学习新范式或数据效率提升的学者
AI训练通常使用语义不同的样本对来增强类别间区分度，而相似性一般由语义相同的样本对学习。本文提出SimLAP：一种从任意样本对学习视觉表征的简单框架。该方法基于观察——任意两类样本之间存在一个子空间，其中语义不同的样本表现出相似性。利用这一现象，SimLAP同时优化任意样本对的相似性并学习该子空间。实验验证了该方法的有效性，并讨论其优势。
原文摘要 · Abstract (English)
The training methods in AI do involve semantically distinct pairs of samples. However, their role typically is to enhance the between class separability. The actual notion of similarity is normally learned from semantically identical pairs. This paper presents SimLAP: a simple framework for learning visual representation from arbitrary pairs. SimLAP explores the possibility of learning similarity from semantically distinct sample pairs. The approach is motivated by the observation that for any pair of classes there exists a subspace in which semantically distinct samples exhibit similarity. This phenomenon can be exploited for a novel method of learning, which optimises the similarity of an arbitrary pair of samples, while simultaneously learning the enabling subspace. The feasibility of the approach will be demonstrated experimentally and its merits discussed.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。