通过可微分的主成分分析，让模型在不同数据分布下仍保持稳定表现。
CPCANet: Deep Unfolding Common Principal Component Analysis for Domain Generalization
- 将统计学中的公共主成分分析转化为可训练的神经网络层
- 在四个基准上实现零样本迁移的最好效果
- 无需针对数据集调参，适合各类视觉任务
领域泛化（DG）旨在学习对分布外（OOD）变化鲁棒的表示，以有效泛化到未见目标域。尽管近期的不变性学习策略和架构进步已取得优异性能，但通过二阶统计量显式发现结构化的域不变子空间仍研究不足。本文提出CPCANet，基于公共主成分分析（CPCA）的新型框架，将迭代的Flury-Gautschi（FG）算法展开为全可微神经层。该方法将CPCA的统计特性融入端到端可训练框架，强制在多域间发现共享子空间，同时保持可解释性。在四个标准DG基准上的实验表明，CPCANet在零样本迁移中达到当前最优（SOTA）性能。此外，该方法与架构无关，无需数据集特异性调参，为分布偏移下的鲁棒表征学习提供简单高效方案。代码已公开于https://github.com/wish44165/CPCANet。
原文摘要 · Abstract (English)
Domain Generalization (DG) aims to learn representations that remain robust under out-of-distribution (OOD) shifts and generalize effectively to unseen target domains. While recent invariant learning strategies and architectural advances have achieved strong performance, explicitly discovering a structured domain-invariant subspace through second-order statistics remains underexplored. In this work, we propose CPCANet, a novel framework grounded in Common Principal Component Analysis (CPCA), which unrolls the iterative Flury-Gautschi (FG) algorithm into fully differentiable neural layers. This approach integrates the statistical properties of CPCA into an end-to-end trainable framework, enforcing the discovery of a shared subspace across diverse domains while preserving interpretability. Experiments on four standard DG benchmarks demonstrate that CPCANet achieves state-of-the-art (SOTA) performance in zero-shot transfer. Moreover, CPCANet is architecture-agnostic and requires no dataset-specific tuning, providing a simple and efficient approach to learning robust representations under distribution shift. Code is available at https://github.com/wish44165/CPCANet.
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。