Saved in:
Bibliographic Details
Main Authors: Cheng, Chen, Li, Ang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.20176
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912857360171008
author Cheng, Chen
Li, Ang
author_facet Cheng, Chen
Li, Ang
contents Out-of-distribution (OOD) generalization remains a fundamental challenge in real-world classification, where test distributions often differ substantially from training data. Most existing approaches pursue domain-invariant representations, implicitly assuming that invariance implies reliability. However, features that are invariant across domains are not necessarily causally effective for prediction. In this work, we revisit OOD classification from a causal perspective and propose to evaluate learned representations based on their necessity and sufficiency under distribution shift. We introduce an explicit segment-level framework that directly measures causal effectiveness across domains, providing a more faithful criterion than invariance alone. Experiments on multi-domain benchmarks demonstrate consistent improvements in OOD performance, particularly under challenging domain shifts, highlighting the value of causal evaluation for robust generalization.
format Preprint
id arxiv_https___arxiv_org_abs_2601_20176
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Causal-Driven Feature Evaluation for Cross-Domain Image Classification
Cheng, Chen
Li, Ang
Machine Learning
Artificial Intelligence
Out-of-distribution (OOD) generalization remains a fundamental challenge in real-world classification, where test distributions often differ substantially from training data. Most existing approaches pursue domain-invariant representations, implicitly assuming that invariance implies reliability. However, features that are invariant across domains are not necessarily causally effective for prediction. In this work, we revisit OOD classification from a causal perspective and propose to evaluate learned representations based on their necessity and sufficiency under distribution shift. We introduce an explicit segment-level framework that directly measures causal effectiveness across domains, providing a more faithful criterion than invariance alone. Experiments on multi-domain benchmarks demonstrate consistent improvements in OOD performance, particularly under challenging domain shifts, highlighting the value of causal evaluation for robust generalization.
title Causal-Driven Feature Evaluation for Cross-Domain Image Classification
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2601.20176