发表机构
The University of Melbourne(墨尔本大学)
机构由 AI 辅助整理,请以论文原文为准。AI 中文总结
研究针对域泛化问题,提出投影追踪CPCANet(PP-CPCANet),通过在Stiefel流形上学习全局正交基并联合优化,引入新目标提取共同主成分,在四个DG基准实验中实现最优性能且训练稳定。
AI 中文摘要
域泛化旨在学习对分布变化具有鲁棒性的表示。近期的几何对齐方法,如CPCANet,通过逐批共同主成分分析(CPCA)提取域不变结构。然而,由于小批量训练中的小样本量问题,CPCANet存在协方差估计秩亏问题。为解决此限制,我们提出投影追踪CPCANet(PP-CPCANet),这是一个无协方差框架,在Stiefel流形上学习全局正交基并通过凯莱变换与网络参数联合优化。我们还引入了一个打破对称性的分离中位数PP散度目标,以通过密集且鲁棒的优化信号提取共同主成分(CPC)。在四个域泛化基准上的实验表明,PP-CPCANet在保持稳定训练的同时实现了最优性能。
英文摘要
Domain Generalization (DG) aims to learn representations robust to distribution shifts. Recent geometric alignment methods, such as CPCANet, extract domain-invariant structures through batch-wise Common Principal Component Analysis (CPCA). However, CPCANet suffers from rank-deficient covariance estimation due to the small-sample-size issue in mini-batch training. To address this limitation, we propose Projection Pursuit CPCANet (PP-CPCANet), a covariance-free framework that learns a global orthogonal basis on the Stiefel manifold and jointly optimizes it with network parameters via the Cayley transform. We further introduce a symmetry-breaking detached-median PP dispersion objective to extract common principal components (CPCs) with dense and robust optimization signals. Experiments on four DG benchmarks show that PP-CPCANet achieves SOTA performance while maintaining stable training.
Comments8 pages, 5 tables