从因果视角评估特征，提升跨域图像分类的泛化能力
Causal-Driven Feature Evaluation for Cross-Domain Image Classification
- 基于因果必要性与充分性评估特征在域转移下的有效性
- 多域基准测试中，尤其在剧烈域偏移下性能显著提升
- 适合关注模型鲁棒性与可解释性的研究者
分布外（OOD）泛化是现实世界分类中的核心挑战，测试分布常与训练数据差异显著。现有方法多追求域不变表示，隐含假设不变性即可靠性，但跨域不变的特征未必具有因果预测效力。本文从因果视角重新审视OOD分类，提出基于必要性与充分性评估学习表征的因果有效性。我们引入一种显式的分段级框架，直接衡量特征在跨域中的因果效力，提供比单纯不变性更可靠的判据。在多域基准上的实验表明，该方法在挑战性域偏移下实现一致的性能提升，验证了因果评估对鲁棒泛化的价值。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。