提出新自监督学习框架，同时捕捉线性与非线性依赖关系
Self-Supervised Learning Using Nonlinear Dependence
- 用核方法融合线性相关与非线性依赖，统一现有自监督范式
- 在多个基准上提升表征质量，验证框架有效性
- 适合处理高维视觉数据中的复杂样本关系，如图像、视频
自监督学习因标注数据稀缺而受到广泛关注。现有方法多关注特征方差与线性相关性，常忽视样本间复杂关系及高维视觉数据中普遍存在的非线性依赖。本文提出相关性-依赖自监督学习（CDSSL），通过整合线性相关与非线性依赖，统一并扩展现有自监督范式，涵盖样本级与特征级交互。方法引入希尔伯特-施密特独立性准则（HSIC），在再生核希尔伯特空间中稳健捕捉非线性依赖，增强表征学习能力。在多种基准上的实验表明，CDSSL能有效提升表示质量。
原文摘要 · Abstract (English)
Self-supervised learning has gained significant attention in contemporary applications, particularly due to the scarcity of labeled data. While existing SSL methodologies primarily address feature variance and linear correlations, they often neglect the intricate relations between samples and the nonlinear dependencies inherent in complex data--especially prevalent in high-dimensional visual data. In this paper, we introduce Correlation-Dependence Self-Supervised Learning (CDSSL), a novel framework that unifies and extends existing SSL paradigms by integrating both linear correlations and nonlinear dependencies, encapsulating sample-wise and feature-wise interactions. Our approach incorporates the Hilbert-Schmidt Independence Criterion (HSIC) to robustly capture nonlinear dependencies within a Reproducing Kernel Hilbert Space, enriching representation learning. Experimental evaluations on diverse benchmarks demonstrate the efficacy of CDSSL in improving representation quality.
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。