English
Related papers

Related papers: Towards Robust Out-of-Distribution Generalization …

200 papers

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,…

Machine Learning · Computer Science 2026-01-30 Chen Cheng , Ang Li

Since out-of-distribution generalization is a generally ill-posed problem, various proxy targets (e.g., calibration, adversarial robustness, algorithmic corruptions, invariance across shifts) were studied across different research programs…

The quantification of uncertainty is important for the adoption of machine learning, especially to reject out-of-distribution (OOD) data back to human experts for review. Yet progress has been slow, as a balance must be struck between…

Machine Learning · Computer Science 2022-09-12 Derek Everett , Andre T. Nguyen , Luke E. Richards , Edward Raff

This paper reexamines the research on out-of-distribution (OOD) robustness in the field of NLP. We find that the distribution shift settings in previous studies commonly lack adequate challenges, hindering the accurate evaluation of OOD…

Computation and Language · Computer Science 2023-10-27 Lifan Yuan , Yangyi Chen , Ganqu Cui , Hongcheng Gao , Fangyuan Zou , Xingyi Cheng , Heng Ji , Zhiyuan Liu , Maosong Sun

Certifying the robustness of model performance under bounded data distribution drifts has recently attracted intensive interest under the umbrella of distributional robustness. However, existing techniques either make strong assumptions on…

Machine Learning · Computer Science 2022-08-02 Maurice Weber , Linyi Li , Boxin Wang , Zhikuan Zhao , Bo Li , Ce Zhang

Information-theoretic (IT) generalization bounds have been used to study the generalization of learning algorithms. These bounds are intrinsically data- and algorithm-dependent so that one can exploit the properties of data and algorithm to…

Machine Learning · Computer Science 2026-01-06 Ze Peng , Jian Zhang , Yisen Wang , Lei Qi , Yinghuan Shi , Yang Gao

Few-shot Out-of-Distribution (OOD) detection has emerged as a critical research direction in machine learning for practical deployment. Most existing Few-shot OOD detection methods suffer from insufficient generalization capability for the…

Computer Vision and Pattern Recognition · Computer Science 2025-08-11 Pinxuan Li , Bing Cao , Changqing Zhang , Qinghua Hu

Robust fine-tuning aims to achieve competitive in-distribution (ID) performance while maintaining the out-of-distribution (OOD) robustness of a pre-trained model when transferring it to a downstream task. To remedy this, most robust…

Machine Learning · Computer Science 2025-09-09 Xiang Yuan , Jun Shu , Deyu meng , Zongben Xu

In the context of modern machine learning, models deployed in real-world scenarios often encounter diverse data shifts like covariate and semantic shifts, leading to challenges in both out-of-distribution (OOD) generalization and detection.…

Machine Learning · Computer Science 2024-09-30 Han Wang , Yixuan Li

Although recent advances in machine learning have shown its success to learn from independent and identically distributed (IID) data, it is vulnerable to out-of-distribution (OOD) data in an open world. Domain generalization (DG) deals with…

Machine Learning · Computer Science 2024-05-14 Thai-Hoang Pham , Xueru Zhang , Ping Zhang

As the use of machine learning continues to expand, the importance of ensuring its safety cannot be overstated. A key concern in this regard is the ability to identify whether a given sample is from the training distribution, or is an…

Machine Learning · Computer Science 2023-08-11 Nicola Franco , Daniel Korth , Jeanette Miriam Lorenz , Karsten Roscher , Stephan Guennemann

Domain generalization (DG) aims to learn predictive models that can generalize to unseen domains. Most existing DG approaches focus on learning domain-invariant representations under the assumption of conditional distribution shift (i.e.,…

Machine Learning · Computer Science 2026-02-03 Jewon Yeom , Kyubyung Chae , Hyunggyu Lim , Yoonna Oh , Dongyoon Yang , Taesup Kim

Deep neural networks have attained remarkable performance when applied to data that comes from the same distribution as that of the training set, but can significantly degrade otherwise. Therefore, detecting whether an example is…

Computer Vision and Pattern Recognition · Computer Science 2020-04-02 Yen-Chang Hsu , Yilin Shen , Hongxia Jin , Zsolt Kira

Modern neural networks can assign high confidence to inputs drawn from outside the training distribution, posing threats to models in real-world deployments. While much research attention has been placed on designing new out-of-distribution…

Machine Learning · Computer Science 2022-03-08 Yifei Ming , Hang Yin , Yixuan Li

Supervised learning aims to train a classifier under the assumption that training and test data are from the same distribution. To ease the above assumption, researchers have studied a more realistic setting: out-of-distribution (OOD)…

Machine Learning · Computer Science 2024-04-09 Zhen Fang , Yixuan Li , Feng Liu , Bo Han , Jie Lu

Modern machine learning models deployed in the wild can encounter both covariate and semantic shifts, giving rise to the problems of out-of-distribution (OOD) generalization and OOD detection respectively. While both problems have received…

Machine Learning · Computer Science 2025-12-22 Haoyue Bai , Gregory Canal , Xuefeng Du , Jeongyeol Kwon , Robert Nowak , Yixuan Li

The discrepancy between in-distribution (ID) and out-of-distribution (OOD) samples can lead to \textit{distributional vulnerability} in deep neural networks, which can subsequently lead to high-confidence predictions for OOD samples. This…

Machine Learning · Computer Science 2023-10-03 Zhilin Zhao , Longbing Cao , Kun-Yu Lin

Deep network models perform excellently on In-Distribution (ID) data, but can significantly fail on Out-Of-Distribution (OOD) data. While developing methods focus on improving OOD generalization, few attention has been paid to evaluating…

Machine Learning · Computer Science 2021-11-22 Rui Hu , Jitao Sang , Jinqiang Wang , Rui Hu , Chaoquan Jiang

State-of-the-art image classifiers trained on massive datasets (such as ImageNet) have been shown to be vulnerable to a range of both intentional and incidental distribution shifts. On the other hand, several recent classifiers with…

Computer Vision and Pattern Recognition · Computer Science 2022-06-16 Benjamin Feuer , Ameya Joshi , Chinmay Hegde

As language models become more general purpose, increased attention needs to be paid to detecting out-of-distribution (OOD) instances, i.e., those not belonging to any of the distributions seen during training. Existing methods for…

Machine Learning · Computer Science 2024-07-19 Aryan Gulati , Xingjian Dong , Carlos Hurtado , Sarath Shekkizhar , Swabha Swayamdipta , Antonio Ortega