Causal-Driven Feature Evaluation for Cross-Domain Image Classification

• URL: http://arxiv.org/abs/2601.20176v2
• Date: Thu, 29 Jan 2026 03:28:15 GMT
• Title: Causal-Driven Feature Evaluation for Cross-Domain Image Classification
• Authors: Chen Cheng, Ang Li,
• Abstract summary: We propose to evaluate learned representations based on their necessity and sufficiency under distribution shift.<n>Experiments on multi-domain benchmarks demonstrate consistent improvements in OOD performance.
• Score: 12.414378175740794
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• FEED: Fairness-Enhanced Meta-Learning for Domain Generalization [13.757379847454372]
  Generalizing to out-of-distribution data while aware of model fairness is a significant and challenging problem in meta-learning. This paper introduces an approach to fairness-aware meta-learning that significantly enhances domain generalization capabilities.
  arXiv  Detail & Related papers  (2024-11-02T17:34:33Z)
• Diagnosing and Rectifying Fake OOD Invariance: A Restructured Causal Approach [51.012396632595554]
  Invariant representation learning (IRL) encourages the prediction from invariant causal features to labels de-confounded from the environments. Recent theoretical results verified that some causal features recovered by IRLs merely pretend domain-invariantly in the training environments but fail in unseen domains. We develop an approach based on conditional mutual information with respect to RS-SCM, then rigorously rectify the spurious and fake invariant effects.
  arXiv  Detail & Related papers  (2023-12-15T12:58:05Z)
• Towards Effective Semantic OOD Detection in Unseen Domains: A Domain Generalization Perspective [19.175929188731715]
  Two prevalent types of distributional shifts in machine learning are the covariate shift and the semantic shift. Traditional OOD detection techniques typically address only one of these shifts. We introduce a novel problem, semantic OOD detection across domains, which simultaneously addresses both shifts.
  arXiv  Detail & Related papers  (2023-09-18T23:48:22Z)
• ATTA: Anomaly-aware Test-Time Adaptation for Out-of-Distribution Detection in Segmentation [22.084967085509387]
  We propose a dual-level OOD detection framework to handle domain shift and semantic shift jointly. The first level distinguishes whether domain shift exists in the image by leveraging global low-level features. The second level identifies pixels with semantic shift by utilizing dense high-level feature maps.
  arXiv  Detail & Related papers  (2023-09-12T06:49:56Z)
• Moderately Distributional Exploration for Domain Generalization [32.57429594854056]
  We show that MODE can endow models with provable generalization performance on unknown target domains. experimental results show that MODE achieves competitive performance compared to state-of-the-art baselines.
  arXiv  Detail & Related papers  (2023-04-27T06:50:15Z)
• Instrumental Variable-Driven Domain Generalization with Unobserved Confounders [53.735614014067394]
  Domain generalization (DG) aims to learn from multiple source domains a model that can generalize well on unseen target domains. We propose an instrumental variable-driven DG method (IV-DG) by removing the bias of the unobserved confounders with two-stage learning. In the first stage, it learns the conditional distribution of the input features of one domain given input features of another domain. In the second stage, it estimates the relationship by predicting labels with the learned conditional distribution.
  arXiv  Detail & Related papers  (2021-10-04T13:32:57Z)
• Variational Disentanglement for Domain Generalization [68.85458536180437]
  We propose to tackle the problem of domain generalization by delivering an effective framework named Variational Disentanglement Network (VDN) VDN is capable of disentangling the domain-specific features and task-specific features, where the task-specific features are expected to be better generalized to unseen but related test data.
  arXiv  Detail & Related papers  (2021-09-13T09:55:32Z)
• Contrastive ACE: Domain Generalization Through Alignment of Causal Mechanisms [34.99779761100095]
  Domain generalization aims to learn knowledge invariant across different distributions. We consider the causal invariance of the average causal effect of the features to the labels.
  arXiv  Detail & Related papers  (2021-06-02T04:01:22Z)
• A Bit More Bayesian: Domain-Invariant Learning with Uncertainty [111.22588110362705]
  Domain generalization is challenging due to the domain shift and the uncertainty caused by the inaccessibility of target domain data. In this paper, we address both challenges with a probabilistic framework based on variational Bayesian inference. We derive domain-invariant representations and classifiers, which are jointly established in a two-layer Bayesian neural network.
  arXiv  Detail & Related papers  (2021-05-09T21:33:27Z)
• Learning Causal Semantic Representation for Out-of-Distribution Prediction [125.38836464226092]
  We propose a Causal Semantic Generative model (CSG) based on a causal reasoning so that the two factors are modeled separately. We show that CSG can identify the semantic factor by fitting training data, and this semantic-identification guarantees the boundedness of OOD generalization error.
  arXiv  Detail & Related papers  (2020-11-03T13:16:05Z)
• Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation [109.73983088432364]
  We propose the first method that aims to simultaneously learn invariant representations and risks under the setting of semi-supervised domain adaptation (Semi-DA) We introduce the LIRR algorithm for jointly textbfLearning textbfInvariant textbfRepresentations and textbfRisks.
  arXiv  Detail & Related papers  (2020-10-09T15:42:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.