Positive Pair Geometry Matters: Optimal Transport for Contrastive Learning of Visual Representations
Akshit Nanda Shahzad Ahmad Ram Prasad Padhy
作者信息
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.引用本文复制引用
Akshit Nanda,Shahzad Ahmad,Ram Prasad Padhy.Positive Pair Geometry Matters: Optimal Transport for Contrastive Learning of Visual Representations[EB/OL].(2026-09-21)[2026-09-24].https://arxiv.org/abs/2609.24125.学科分类
计算技术、计算机技术
|国家预印本平台