提出统一自监督对比学习的新框架，提升特征区分度与聚类性。
A Generalized Learning Framework for Self-Supervised Contrastive Learning
- 构建包含对齐与约束两部分的通用学习框架，统一现有方法
- 证明特征空间需兼顾类内紧凑与类间分离，提升表征质量
- 设计可插拔的自适应分布校准法，无需标签实现动态优化
自监督对比学习（SSCL）在多个下游任务中表现优异。本文将标准SSCL方法推广为一个由对齐部分和约束部分组成的通用学习框架（GLF），分析了BYOL、Barlow Twins和SwAV三种方法，并证明它们可在不同约束策略下统一于该框架。通过理论与实证分析，揭示设计约束部分的关键在于保持类内紧凑性和类间可分性，以更好保留输入的类别信息。由于缺乏标签，实现此目标具有挑战性。为此，本文提出一种通过迭代捕捉锚点与样本间动态关系的自适应分布校准（ADC）方法，确保原始空间中相近或远离锚点的样本，在特征空间中也保持相应距离。理论与实验均验证了ADC的有效性。
原文摘要 · Abstract (English)
Self-supervised contrastive learning (SSCL) has recently demonstrated superiority in multiple downstream tasks. In this paper, we generalize the standard SSCL methods to a Generalized Learning Framework (GLF) consisting of two parts: the aligning part and the constraining part. We analyze three existing SSCL methods: BYOL, Barlow Twins, and SwAV, and show that they can be unified under GLF with different choices of the constraining part. We further propose empirical and theoretical analyses providing two insights into designing the constraining part of GLF: intra-class compactness and inter-class separability, which measure how well the feature space preserves the class information of the inputs. However, since SSCL can not use labels, it is challenging to design a constraining part that satisfies these properties. To address this issue, we consider inducing intra-class compactness and inter-class separability by iteratively capturing the dynamic relationship between anchor and other samples and propose a plug-and-play method called Adaptive Distribution Calibration (ADC) to ensure that samples that are near or far from the anchor point in the original input space are closer or further away from the anchor point in the feature space. Both the theoretical analysis and the empirical evaluation demonstrate the superiority of ADC.
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。