CPCANet: Deep Unfolding Common Principal Component Analysis for Domain Generalization
Summary
CPCANet is a domain generalization framework that uses Common Principal Component Analysis to discover structured domain-invariant subspaces, achieving state-of-the-art performance in zero-shot transfer.
View Cached Full Text
Cached at: 05/11/26, 07:20 AM
Paper page - CPCANet: Deep Unfolding Common Principal Component Analysis for Domain Generalization
Source: https://huggingface.co/papers/2605.05136
Abstract
CPCANet is a domain generalization framework that uses Common Principal Component Analysis to discover structured domain-invariant subspaces through differentiable neural layers, achieving state-of-the-art performance in zero-shot transfer.
Domain Generalization(DG) aims to learn representations that remain robust under out-of-distribution (OOD) shifts and generalize effectively to unseen target domains. While recentinvariant learningstrategies and architectural advances have achieved strong performance, explicitly discovering a structureddomain-invariant subspacethrough second-order statistics remains underexplored. In this work, we propose CPCANet, a novel framework grounded inCommon 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 inzero-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.
View arXiv pageView PDFProject pageGitHub0Add to collection
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2605.05136 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2605.05136 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2605.05136 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
Learning High Coverage Discriminative Parsimonious Rulesets
This paper introduces CDPR, a new approach for learning highly accurate and interpretable rule sets for classification using submodular maximization, achieving over 2.5x improvement in coverage compared to existing methods.
PR-CAD: Progressive Refinement for Unified Controllable and Faithful Text-to-CAD Generation with Large Language Models
PR-CAD introduces a unified framework using LLMs for iterative text-to-CAD generation and editing, achieving state-of-the-art controllability and faithfulness via reinforcement learning and a curated high-fidelity dataset.
Generalized Category Discovery in Federated Graph Learning
This paper introduces GCD-FGL, a federated graph learning framework designed for generalized category discovery in dynamic environments. It addresses challenges like the neighborhood absorption effect and global semantic inconsistency to improve novel category detection across distributed clients.
First per-image PCA decomposition of Kodak suite reveals deliberate curation
First per-image PCA decomposition of the 24-image Kodak PCD0992 suite reveals deliberate curation spanning two orders of magnitude in inter-channel redundancy.
@jcjohnss: GPIC should be the new standard benchmark for generative modeling. Training 1 epoch on GPIC is the same cost as 100 epo…
GPIC is a new large-scale image-text dataset and benchmark for generative modeling, claimed to be much more efficient than ImageNet and a better proxy for real-world problems, with fully permissive licensing for research and commercial use.