用最优传输理论增强对比学习，让特征空间更有序、分类更清晰。
SinSim: Sinkhorn-Regularized SimCLR
- 在SimCLR基础上引入Sinkhorn正则化，优化特征分布结构。
- 在多个数据集上超越SimCLR，接近VICReg和Barlow Twins表现。
- 适合关注自监督表征质量与几何结构的研究者。
自监督学习通过消除标签需求革新了表示学习。对比学习方法如SimCLR通过最大化图像增强视图间的相似性来学习表示，但缺乏显式正则化以保证全局结构化的潜在空间，常导致泛化能力不足。本文提出SinSim，一种SimCLR的新扩展，结合最优传输理论中的Sinkhorn正则化，以增强表示结构。该正则化项为熵正则化的Wasserstein距离，促使特征空间分布更均匀且具有几何感知性，同时保持判别力。在多个数据集上的实证评估显示，SinSim优于SimCLR，并达到与主流自监督方法（如VICReg和Barlow Twins）相当的性能。UMAP可视化进一步揭示了更优的类别可分性和结构化特征分布。结果表明，将基于运输的正则化引入对比学习，是一种原理性强且有效的学习鲁棒、结构化表示的方法。研究为自监督学习框架中应用运输约束开辟了新方向。
原文摘要 · Abstract (English)
Self-supervised learning has revolutionized representation learning by eliminating the need for labeled data. Contrastive learning methods, such as SimCLR, maximize the agreement between augmented views of an image but lack explicit regularization to enforce a globally structured latent space. This limitation often leads to suboptimal generalization. We propose SinSim, a novel extension of SimCLR that integrates Sinkhorn regularization from optimal transport theory to enhance representation structure. The Sinkhorn loss, an entropy-regularized Wasserstein distance, encourages a well-dispersed and geometry-aware feature space, preserving discriminative power. Empirical evaluations on various datasets demonstrate that SinSim outperforms SimCLR and achieves competitive performance against prominent self-supervised methods such as VICReg and Barlow Twins. UMAP visualizations further reveal improved class separability and structured feature distributions. These results indicate that integrating optimal transport regularization into contrastive learning provides a principled and effective mechanism for learning robust, well-structured representations. Our findings open new directions for applying transport-based constraints in self-supervised learning frameworks.
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。