通过联合裁剪与模糊生成更难正样本，提升对比学习效果
Enhancing Contrastive Learning Inspired by the Philosophy of "The Blind Men and the Elephant"
- 用联合分布设计裁剪和模糊增强，生成更具挑战性的正样本
- 在多个主流模型上实现显著性能提升，最高增益达2.1%
- 无需额外计算开销，可直接替换现有增强策略
对比学习是自监督视觉表征学习中的主流方法，通常通过对同一图像施加两次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’寓言启发，我们提出JointCrop和JointBlur方法，通过利用两个增强参数的联合分布生成更具挑战性的正样本对，从而帮助对比学习获取更有效的特征表示。据我们所知，这是首次将两个增强参数的联合分布显式引入对比学习。作为无额外计算开销的即插即用框架，JointCrop和JointBlur在SimCLR、BYOL、MoCo v1、MoCo v2、MoCo v3、SimSiam和Dino等基线模型上均取得显著性能提升。
原文摘要 · Abstract (English)
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.
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。