| title | CPCANet: Deep Unfolding Common Principal Component Analysis for Domain Generalization |
|---|---|
| authors | Yu-Hsi Chen, Abd-Krim Seghouane |
| date | 2026-05-07 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.05136 |
| affiliation | The University of Melbourne |
| links | abs pdf hf code |
| abstract | 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. |
cite
@misc{chen2026cpcanet,
title={CPCANet: Deep Unfolding Common Principal Component Analysis for Domain Generalization},
author={Yu-Hsi Chen and Abd-Krim Seghouane},
year={2026},
eprint={2605.05136},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.05136}
}