CLEAR：利用带反对比正则化的对比学习消除虚假的风格-内容关联
CLEAR: Unlearning Spurious Style-Content Associations with Contrastive LEarning with Anti-contrastive Regularization
AI总结：
提出CLEAR框架，通过Pair-Switching反对比正则化在VAE潜空间中解耦内容与风格，减少虚假关联并提升分布变化下的分类与风格操控能力。
摘要：
学习不受表面特征影响的表示，对于确保测试时这些特征的变化不会损害下游预测性能非常重要。例如，在医疗健康应用中，我们可能希望学习既包含病理信息、又不受种族、性别及其他生理变异来源影响的特征，从而确保预测在所有人口统计群体中都是公平且可泛化的。本文提出带反对比正则化的对比学习（Contrastive LEarning with Anti-contrastive Regularization，CLEAR），这是一个直观且易于实现的框架，可在训练期间有效分离本质（即任务相关）特征与表面（即任务无关）特征，从而在测试时表面特征发生变化时取得更好的性能。我们首先假设数据表示在语义上可被分离为任务相关的内容特征和任务无关的风格特征：前者包含与下游任务相关的信息，后者涵盖与这些任务无关的表面属性，但由于训练数据中存在无法泛化的内容关联，这些风格属性可能降低性能。随后，我们证明了名为 Pair-Switching（PS）的反对比惩罚能够最小化风格属性与内容标签之间的互信息。最后，我们在变分自编码器（Variational Auto-Encoder，VAE）的潜空间中实例化 CLEAR，并在多个图像数据集上通过实验对所得 CLEAR-VAE 进行定量和定性评估。结果表明，CLEAR-VAE使我们能够：(a) 在任意样本对之间交换和插值内容与风格；(b) 在内容与风格出现此前未见组合的情况下提升下游分类性能。我们的代码将公开发布。
英文摘要：
Learning representations unaffected by superficial characteristics is important to ensure that shifts in these characteristics at test time do not compromise downstream prediction performance. For instance, in healthcare applications, we might like to learn features that contain information about pathology yet are unaffected by race, sex, and other sources of physiologic variability, thereby ensuring predictions are equitable and generalizable across all demographics. Here we propose Contrastive LEarning with Anti-contrastive Regularization (CLEAR), an intuitive and easy-to-implement framework that effectively separates essential (i.e., task-relevant) characteristics from superficial (i.e., task-irrelevant) characteristics during training, leading to better performance when superficial characteristics shift at test time. We begin by supposing that data representations can be semantically separated into task-relevant content features, which contain information relevant to downstream tasks, and task-irrelevant style features, which encompass superficial attributes that are irrelevant to these tasks, yet may degrade performance due to associations with content present in training data that do not generalize. We then prove that our anti-contrastive penalty, which we call Pair-Switching (PS), minimizes the Mutual Information between the style attributes and content labels. Finally, we instantiate CLEAR in the latent space of a Variational Auto-Encoder (VAE), then perform experiments to quantitatively and qualitatively evaluate the resulting CLEAR-VAE over several image datasets. Our results show that CLEAR-VAE allows us to: (a) swap and interpolate content and style between any pair of samples, and (b) improve downstream classification performance in the presence of previously unseen combinations of content and style. Our code will be made publicly available.
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。
