Positive Pair Geometry Matters: Optimal Transport for Contrastive Learning of Visual Representations

2026-09-21

AI Summary

为解决对比学习中随机增强可能改变语义内容的问题，提出OTCLR方法，通过最优传输生成几何一致的正样本，提高表示质量和迁移学习性能。

Abstract

Contrastive self-supervised learning has achieved strong performance by learning representations from multiple augmented views of the same image. However, most existing methods construct positive pairs using independently sampled stochastic augmentations, which may alter semantic content and ignore the intrinsic geometry of the data distribution. In this work, we propose OTCLR, an optimal transport-aware framework for contrastive learning representations that generates geometry-consistent positive samples. Instead of directly contrasting two randomly augmented views, we construct intermediate views between the original image and its augmented variants through entropic optimal-transport displacement interpolation. These transport-interpolated samples serve as positive views that better preserve image structure while explicitly modeling spatial distributional geometry. To further promote smooth representation learning, we evaluate auxiliary Sinkhorn regularization terms that encourage transport-interpolated views to remain consistent with their endpoint images. The proposed method can be incorporated into standard contrastive learning pipelines without modifying the encoder architecture. Experiments on multiple benchmark datasets show that our approach improves representation quality and transfer learning performance compared with conventional augmentation-based contrastive learning baselines.

Problem

• contrastive learning
• positive pairs
• data distribution geometry
• optimal transport
• representation learning

Innovation

• Optimal Transport
• Contrastive Learning
• Entropic Optimal-Transport Displacement Interpolation
• Sinkhorn Regularization