CPCANet: Deep Unfolding Common Principal Component Analysis for Domain Generalization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Yu-Hsi, Seghouane, Abd-Krim
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918486765207552
author Chen, Yu-Hsi
Seghouane, Abd-Krim
author_facet Chen, Yu-Hsi
Seghouane, Abd-Krim
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_05136
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CPCANet: Deep Unfolding Common Principal Component Analysis for Domain Generalization
Chen, Yu-Hsi
Seghouane, Abd-Krim
Computer Vision and Pattern Recognition
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.
title CPCANet: Deep Unfolding Common Principal Component Analysis for Domain Generalization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.05136