重新思考对比学习中的正样本对
Rethinking Positive Pairs in Contrastive Learning
AI总结：
本文提出SimLAP框架，从语义不同的样本对中学习视觉表示，通过优化任意样本对相似性并学习使能子空间，为对比学习提供了新方法。
摘要：
AI中的训练方法确实涉及语义不同的样本对。然而，它们的作用通常是增强类间可分性。实际相似性的概念通常是从语义相同的样本对中学习到的。本文提出了SimLAP：一个从任意样本对中学习视觉表示的简单框架。SimLAP探索了从语义不同的样本对中学习相似性的可能性。该方法的动机是观察到，对于任意一对类别，存在一个子空间，在其中语义不同的样本表现出相似性。这种现象可以用于一种新颖的学习方法，该方法优化任意样本对的相似性，同时学习使能子空间。将通过实验证明该方法的可行性，并讨论其优点。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
