English
Related papers

Related papers: MEMO: Test Time Robustness via Adaptation and Augm…

200 papers

Deep classifiers may encounter significant performance degradation when processing unseen testing data from varying centers, vendors, and protocols. Ensuring the robustness of deep models against these domain shifts is crucial for their…

Computer Vision and Pattern Recognition · Computer Science 2023-06-06 Yuhao Huang , Xin Yang , Xiaoqiong Huang , Xinrui Zhou , Haozhe Chi , Haoran Dou , Xindi Hu , Jian Wang , Xuedong Deng , Dong Ni

This paper explores the intricate relationship between interpretability and robustness in deep learning models. Despite their remarkable performance across various tasks, deep learning models often exhibit critical vulnerabilities,…

Machine Learning · Computer Science 2024-12-30 Navid Nayyem , Abdullah Rakin , Longwei Wang

A deployed question answering (QA) model can easily fail when the test data has a distribution shift compared to the training data. Robustness tuning (RT) methods have been widely studied to enhance model robustness against distribution…

Computation and Language · Computer Science 2023-02-10 Hai Ye , Yuyang Ding , Juntao Li , Hwee Tou Ng

Recent work introduced the epinet as a new approach to uncertainty modeling in deep learning. An epinet is a small neural network added to traditional neural networks, which, together, can produce predictive distributions. In particular,…

Machine Learning · Computer Science 2022-07-04 Xiuyuan Lu , Ian Osband , Seyed Mohammad Asghari , Sven Gowal , Vikranth Dwaracherla , Zheng Wen , Benjamin Van Roy

Test-time defenses are used to improve the robustness of deep neural networks to adversarial examples during inference. However, existing methods either require an additional trained classifier to detect and correct the adversarial samples,…

Machine Learning · Computer Science 2024-08-26 Anurag Singh , Mahalakshmi Sabanayagam , Krikamol Muandet , Debarghya Ghoshdastidar

Large pre-trained language models have shown remarkable performance over the past few years. These models, however, sometimes learn superficial features from the dataset and cannot generalize to the distributions that are dissimilar to the…

Computation and Language · Computer Science 2022-10-31 Jieyu Zhao , Xuezhi Wang , Yao Qin , Jilin Chen , Kai-Wei Chang

Test-time domain adaptation effectively adjusts the source domain model to accommodate unseen domain shifts in a target domain during inference. However, the model performance can be significantly impaired by continuous distribution changes…

Machine Learning · Computer Science 2024-01-29 Xingzhi Zhou , Zhiliang Tian , Ka Chun Cheung , Simon See , Nevin L. Zhang

Robust machine learning for regulatory genomics is studied under biologically and technically induced distribution shifts. Deep convolutional and attention based models achieve strong in distribution performance on DNA regulatory sequence…

Genomics · Quantitative Biology 2026-02-20 Yiyao Yang

Deep neural networks often produce overconfident predictions, undermining their reliability in safety-critical applications. This miscalibration is further exacerbated under distribution shift, where test data deviates from the training…

Computer Vision and Pattern Recognition · Computer Science 2025-08-28 Yilin Zhang , Cai Xu , You Wu , Ziyu Guan , Wei Zhao

While the traditional viewpoint in machine learning and statistics assumes training and testing samples come from the same population, practice belies this fiction. One strategy -- coming from robust statistics and optimization -- is thus…

Machine Learning · Statistics 2024-07-08 Maxime Cauchois , Suyash Gupta , Alnur Ali , John C. Duchi

A machine learning model that generalizes well should obtain low errors on unseen test examples. Thus, if we learn an optimal model in training data, it could have better generalization performance in testing tasks. However, learning such a…

Computer Vision and Pattern Recognition · Computer Science 2023-02-22 Penghao Jiang , Xin Ke , ZiFeng Wang , Chunxi Li

Deep learning-based diagnostic systems have demonstrated potential in skin disease diagnosis. However, their performance can easily degrade on test domains due to distribution shifts caused by input-level corruptions, such as imaging…

Image and Video Processing · Electrical Eng. & Systems 2024-05-21 Ming Hu , Siyuan Yan , Peng Xia , Feilong Tang , Wenxue Li , Peibo Duan , Lin Zhang , Zongyuan Ge

The label shift problem refers to the supervised learning setting where the train and test label distributions do not match. Existing work addressing label shift usually assumes access to an \emph{unlabelled} test sample. This sample may be…

Machine Learning · Computer Science 2021-08-18 Jingzhao Zhang , Aditya Menon , Andreas Veit , Srinadh Bhojanapalli , Sanjiv Kumar , Suvrit Sra

Pretrained vision-language models such as CLIP exhibit strong zero-shot generalization but remain sensitive to distribution shifts. Test-time adaptation adapts models during inference without access to source data or target labels, offering…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Wenxuan Bao , Yanjun Zhao , Xiyuan Yang , Jingrui He

Time-series anomaly detection deals with the problem of detecting anomalous timesteps by learning normality from the sequence of observations. However, the concept of normality evolves over time, leading to a "new normal problem", where the…

Machine Learning · Computer Science 2024-01-23 Dongmin Kim , Sunghyun Park , Jaegul Choo

State-of-the-art pre-trained language models (PLMs) outperform other models when applied to the majority of language processing tasks. However, PLMs have been found to degrade in performance under distribution shift, a phenomenon that…

Computation and Language · Computer Science 2022-12-06 Ayush Singh , John E. Ortega

Test-time adaptation (TTA) intends to adapt the pretrained model to test distributions with only unlabeled test data streams. Most of the previous TTA methods have achieved great success on simple test data streams such as independently…

Computer Vision and Pattern Recognition · Computer Science 2023-03-27 Longhui Yuan , Binhui Xie , Shuang Li

Nowadays, pretrained models are increasingly used as general-purpose backbones and adapted at test-time to downstream environments where target data are scarce and unlabeled. While this paradigm has proven effective for improving clean…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Stefano Bianchettin , Giulio Rossolini , Giorgio Buttazzo

Deep neural networks are the default choice of learning models for computer vision tasks. Extensive work has been carried out in recent years on explaining deep models for vision tasks such as classification. However, recent work has shown…

Computer Vision and Pattern Recognition · Computer Science 2021-08-17 Anindya Sarkar , Anirban Sarkar , Vineeth N Balasubramanian

Class distribution plays an important role in learning deep classifiers. When the proportion of each class in the test set differs from the training set, the performance of classification nets usually degrades. Such a label distribution…

Image and Video Processing · Electrical Eng. & Systems 2022-07-12 Wenao Ma , Cheng Chen , Shuang Zheng , Jing Qin , Huimao Zhang , Qi Dou