Research
Divergence-Based Similarity Function for Multi-View Contrastive Learning
arXiv:2507.06560v5 Announce Type: replace Abstract: Recent success in contrastive learning has sparked growing interest in more effectively leveraging multiple augmented views of data. While prior met
arXiv:2507.06560v5 Announce Type: replace Abstract: Recent success in contrastive learning has sparked growing interest in more effectively leveraging multiple augmented views of data. While prior methods incorporate multiple views at the loss or feature level, they primarily capture pairwise relationships and fail to model the joint structure across all views. In this work, we propose a divergence-based similarity function (DSF) that explicitly captures the joint structure by representing each set of augmented views as a distribution and measuring similarity as the divergence between distributions. Extensive experiments demonstrate that DSF consistently improves performance across diverse tasks, including kNN classification, linear evaluation, transfer learning, and distribution shift, while also achieving greater efficiency than other multi-view methods. Furthermore, we establish a connection between DSF and cosine similarity, and demonstrate that, unlike cosine similarity, DSF operates effectively without the need for tuning a temperature hyperparameter.
Related
- FARCLUSS: Fuzzy Adaptive Rebalancing and Contrastive Uncertainty Learning for Semi-Supervised Semantic Segmentation
- Skeleton-Snippet Contrastive Learning with Multiscale Feature Fusion for Action Localization
- Robust Multi-View Classification under Noisy Supervision via Global Anchor Consensus
Source: arXiv cs.CV | 2026-09-11