提出新自监督学习方法PEIRA，通过回归对齐实现稳定表征学习。
PEIRA: Learning Predictive Encoders through Inter-View Regressor Alignment
- 用线性回归对齐双视图表示，构建可解释的显式目标函数
- 理论证明仅有非退化稳定解，且对应主要相关子空间
- 在ImageNet和CIFAR-10上性能媲美现有先进方法
非对比自监督学习是预测表征学习的有效框架，但如SimSiam、BYOL、I-JEPA或DINO等主流方法依赖自蒸馏训练教师-学生网络，缺乏明确优化目标。本文分析了基于正则化线性回归预测两视图表示的联合嵌入预测架构（JEPA）变体的动力学特性，完全刻画其稳定性：非退化稳定平衡点与主导非线性典型相关子空间对齐，而退化平衡点也可能成为稳定吸引子。受此启发，提出PEIRA，一种通过最优线性回归迹定义显式目标的非对比自监督方法。理论表明其唯一稳定平衡点为非平凡全局最小值，并恢复相同典型相关子空间；正则化控制有效维度。ImageNet-1K与CIFAR-10实验显示，PEIRA性能可比于VICReg和LeJEPA基线，定性结果支持理论。
原文摘要 · Abstract (English)
Non-contrastive self-supervised learning (SSL) is an effective framework for predictive representation learning, but popular (and in practice effective) methods such as SimSiam, BYOL, I-JEPA or DINO, which rely on a form of self-distillation to train a teacher-student network, remain poorly understood as they typically do not minimize a well-defined objective. We analyze the dynamics of a variant of the Joint Embedding Predictive Architecture (JEPA) using a regularized linear regressor to predict the learned representations of two views of the data from one another, and fully characterize its stability: non-collapsed stable equilibria align with leading nonlinear canonical correlation subspaces, while collapsed equilibria may also be stable attractors. Motivated by this result, we introduce PEIRA, a non-contrastive SSL method with an explicit objective defined through the trace of the optimal linear regressor. We show that its only stable equilibria are nontrivial global minimizers and recover the same canonical correlation subspaces, with regularization selecting the effective dimension. Experiments on ImageNet-1K and CIFAR-10 show PEIRA is competitive with VICReg and LeJEPA baselines, and qualitative empirical results support the theory.
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。