多相似性对比学习
Multi-Similarity Contrastive Learning
AI总结：
本文提出多相似性对比损失MSCon，通过联合利用多个相似性度量并根据不确定性自动加权，学习可泛化表示，在域内和域外任务上均优于现有基线。
摘要：
给定一个相似性度量，对比方法学习一种表示，使得相似的样本被拉近，不相似的样本被推开。对比学习技术已被广泛用于学习从图像分类到字幕生成等任务的表示。然而，现有的对比学习方法可能无法泛化，因为它们没有考虑不同相似性关系的可能性。在本文中，我们提出了一种新颖的多相似性对比损失（MSCon），通过联合利用多个相似性度量的监督来学习可泛化的嵌入。我们的方法根据相应相似性的不确定性自动学习对比相似性权重，对不确定的任务进行降权，从而在新任务上获得更好的域外泛化能力。我们通过实验表明，使用MSCon训练的网络在域内和域外设置下均优于最先进的基线方法。
英文摘要：
Given a similarity metric, contrastive methods learn a representation in which examples that are similar are pushed together and examples that are dissimilar are pulled apart. Contrastive learning techniques have been utilized extensively to learn representations for tasks ranging from image classification to caption generation. However, existing contrastive learning approaches can fail to generalize because they do not take into account the possibility of different similarity relations. In this paper, we propose a novel multi-similarity contrastive loss (MSCon), that learns generalizable embeddings by jointly utilizing supervision from multiple metrics of similarity. Our method automatically learns contrastive similarity weightings based on the uncertainty in the corresponding similarity, down-weighting uncertain tasks and leading to better out-of-domain generalization to new tasks. We show empirically that networks trained with MSCon outperform state-of-the-art baselines on in-domain and out-of-domain settings.
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。
