受《盲人摸象》哲学启发的对比学习增强方法
Enhancing Contrastive Learning Inspired by the Philosophy of "The Blind Men and the Elephant"
AI总结：
针对对比学习数据增强策略的优化需求，受“盲人摸象”启发提出JointCrop和JointBlur方法，首次将两种增强参数的联合分布引入对比学习，在多个基准模型上实现性能提升且无额外计算开销。
摘要：
对比学习是自监督视觉表征学习中的主流技术，通常通过对同一张图像应用两种数据增强来生成正样本对。设计有效的数据增强策略对对比学习的成功至关重要。受“盲人摸象”故事启发，我们提出JointCrop和JointBlur方法。这些方法通过利用两种增强参数的联合分布生成更具挑战性的正样本对，从而使对比学习能获取更有效的特征表征。据我们所知，这是首次明确将两种数据增强参数的联合分布纳入对比学习的尝试。作为无额外计算开销的即插即用框架，JointCrop和JointBlur提升了SimCLR、BYOL、MoCo v1、MoCo v2、MoCo v3、SimSiam和Dino基准模型的性能，且改进显著。
英文摘要：
Contrastive learning is a prevalent technique in self-supervised vision representation learning, typically generating positive pairs by applying two data augmentations to the same image. Designing effective data augmentation strategies is crucial for the success of contrastive learning. Inspired by the story of the blind men and the elephant, we introduce JointCrop and JointBlur. These methods generate more challenging positive pairs by leveraging the joint distribution of the two augmentation parameters, thereby enabling contrastive learning to acquire more effective feature representations. To the best of our knowledge, this is the first effort to explicitly incorporate the joint distribution of two data augmentation parameters into contrastive learning. As a plug-and-play framework without additional computational overhead, JointCrop and JointBlur enhance the performance of SimCLR, BYOL, MoCo v1, MoCo v2, MoCo v3, SimSiam, and Dino baselines with notable improvements.
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。
