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

arXiv:2609.24125 · cs.CV, cs.CG · Submitted 2026-09-21 · Read on arXiv

cs.CV, cs.CG

Submitted: 2026-09-21

Updated: 2026-09-21

Terminology

• Optimal Transport — 12× in this paper · explained in 5 episodes
• Self-Supervised Learning — 12× in this paper · explained in 8 episodes
• Contrastive Learning — 10× in this paper · explained in 5 episodes
• Embeddings — 9× in this paper · explained in 2 episodes
• Regularization — 8× in this paper · explained in 3 episodes
• Representation Learning — 8× in this paper · explained in 2 episodes
• Accuracy — 7× in this paper · explained in 1 episode
• Clustering — 6× in this paper · explained in 2 episodes
• Benchmark — 5× in this paper · explained in 2 episodes
• Benchmarking — 4× in this paper · explained in 3 episodes
• Cosine Similarity — 4× in this paper · explained in 3 episodes
• Alignment — 3× in this paper · explained in 1 episode
• Data Augmentation — 3× in this paper · explained in 7 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Adam — 2× in this paper · explained in 2 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Predictive Coding — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Computational overhead — 1× in this paper · explained in 2 episodes
• Domain Adaptation — 1× in this paper · explained in 5 episodes
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• Feature Extraction — 1× in this paper · explained in 2 episodes
• Optimal Transport (OT) — 1× in this paper · explained in 4 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Self-Supervised Learning (SSL) — 1× in this paper · explained in 4 episodes
• Street View House Numbers — 1× in this paper
• Transfer Learning — 1× in this paper · explained in 10 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Wasserstein Distance — 1× in this paper · explained in 4 episodes

Sources

• Representation Learning with Contrastive Predictive Coding
• DINOv3

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models