Feature alignment is an approach to improving robustness to distribution shift that matches the distribution of feature activations between the training distribution and test distribution. A particularly simple but effective approach to feature alignment involves aligning the batch normalization statistics between the two distributions in a trained neural network. This technique has received renewed interest lately because of its impressive performance on robustness benchmarks. However, when and why this method works is not well understood. We investigate the approach in more detail and identify several limitations. We show that it only significantly helps with a narrow set of distribution shifts and we identify several settings in which it even degrades performance. We also explain why these limitations arise by pinpointing why this approach can be so effective in the first place. Our findings call into question the utility of this approach and Unsupervised Domain Adaptation more broadly for improving robustness in practice.
Technical University of Munich（慕尼黑工业大学）；Helmholtz Munich（亥姆霍兹慕尼黑中心）；ELLIS Institute Finland（芬兰ELLIS研究所）；Aalto University（阿尔托大学）；Finnish Center for Artificial Intelligence（芬兰人工智能中心）；Munich Center for Machine Learning（慕尼黑机器学习中心）；Munich Data Science Institute（慕尼黑数据科学研究所）；Ericsson Research（爱立信研究院）；KTH Royal Institute of Technology（KTH皇家理工学院）；Digital Futures（数字未来研究所）
Post-Hoc Uncertainty-Aware Explanations for Deployed Power Quality Disturbance Classifiers via Laplace Approximation
School of Engineering, Deakin University（德肯大学工程学院）；ARC Training Centre in Energy Technologies for Future Grids, School of Engineering, University of Wollongong（未来电网能源技术培训中心，沃尔灵宗大学工程学院）
Evaluating Post-hoc Interpretability with Intrinsic Interpretability
University of Coimbra（科英布拉大学）；IPO-Porto Research Centre（波尔图肿瘤学研究所研究中心）；University of Applied Sciences Western Switzerland (HES-SO Valais)（瑞士西部应用科学大学（瓦莱州高等专业学院））
On the Faithfulness of Post-Hoc Concept Bottleneck Models
Institute of Data Science, German Aerospace Center（数据科学研究所，德国航空航天中心）；Computer Vision Group Jena, Friedrich Schiller University Jena（贾恩计算机视觉小组，弗里德里希·席勒大学贾恩）；GEOMAR Helmholtz Centre for Ocean Research Kiel（基尔海洋研究赫尔姆霍茨中心）
Train Once, Forget Precisely: Anchored Optimization for Efficient Post-Hoc Unlearning
University College London, London, United Kingdom（伦敦大学学院）；University of Nottingham, Nottingham, United Kingdom（诺丁汉大学）；Bharati Vidyapeeth College of Engineering, New Delhi, India（巴里蒂大学工程学院）
Post-hoc Overall Survival Time Prediction from Brain MRI
Australian Institute for Machine Learning, The University of Adelaide（阿德莱德大学澳大利亚机器学习研究所）；Institute for Systems and Robotics, Instituto Superior Tecnico（高等理工学院系统与机器人研究所）
Beyond Known Fakes: Generalized Detection of AI-Generated Images via Post-hoc Distribution Alignment
School of Cyber Science and Technology, Shandong University（网络安全科学与技术学院，山东大学）；State Key Laboratory of Cryptography and Digital Economy Security, Shandong University（密码与数字经济安全国家重点实验室，山东大学）；Shandong Key Laboratory of Artificial Intelligence Security, Shandong University（人工智能安全山东省重点实验室，山东大学）
Deep Attention Reweighting: Post-Hoc Attention-Based Feature Aggregation in CNNs for Disentangling Core and Spurious Features under Spurious Correlations
Improved post-hoc probability calibration for out-of-domain MRI segmentation
Imperial College London（帝国理工学院）；Fudan University（复旦大学）；Friedrich-Alexander-Universität Erlangen-Nürnberg（埃尔朗根-纽伦堡弗里德里希-亚历山大大学）；Technical University of Munich（慕尼黑工业大学）
UrbanAlign: Post-hoc Semantic Calibration for VLM-Human Preference Alignment
Tsinghua University（清华大学）；University College London（伦敦大学学院）；Hong Kong University of Science and Technology（香港科学与技术大学）；Peking University（北京大学）；Southwest Jiaotong University（西南交通大学）；Zhejiang University（浙江大学）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；Renmin University of China（中国人民大学）；Southeast University（东南大学）
Single-weight Model Editing for Post-hoc Spurious Correlation Neutralization
Department of Computer Science and Software Engineering, University of Western Australia（西澳大学计算机科学与软件工程系）；School of Computing and Information Systems, University of Melbourne（墨尔本大学计算机科学与信息系）
