English
Related papers

Related papers: Mitigating the Bias in the Model for Continual Tes…

200 papers

Experiencing domain shifts during test-time is nearly inevitable in practice and likely results in a severe performance degradation. To overcome this issue, test-time adaptation continues to update the initial source model during…

Computer Vision and Pattern Recognition · Computer Science 2022-11-10 Robert A. Marsden , Mario Döbler , Bin Yang

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

Domain adaptation (DA) aims to transfer knowledge learned from a labeled source domain to an unlabeled or a less labeled but related target domain. Ideally, the source and target distributions should be aligned to each other equally to…

Computer Vision and Pattern Recognition · Computer Science 2022-08-15 Jian Hu , Haowen Zhong , Junchi Yan , Shaogang Gong , Guile Wu , Fei Yang

Domain generalization aims at developing suitable learning algorithms in source training domains such that the model learned can generalize well on a different unseen testing domain. We present a novel two-stage approach called…

Machine Learning · Computer Science 2025-04-07 Hao Yan , Yuhong Guo

Online Test-Time Adaptation (OTTA) has emerged as an effective strategy to handle distributional shifts, allowing on-the-fly adaptation of pre-trained models to new target domains during inference, without the need for source data. We…

Computer Vision and Pattern Recognition · Computer Science 2024-05-14 WeiQin Chuah , Ruwan Tennakoon , Alireza Bab-Hadiashar

While the design of blind image quality assessment (IQA) algorithms has improved significantly, the distribution shift between the training and testing scenarios often leads to a poor performance of these methods at inference time. This…

Computer Vision and Pattern Recognition · Computer Science 2023-09-27 Subhadeep Roy , Shankhanil Mitra , Soma Biswas , Rajiv Soundararajan

In online continual learning (CL), models trained on changing distributions easily forget previously learned knowledge and bias toward newly received tasks. To address this issue, we present Continual Bias Adaptor (CBA), a bi-level…

Machine Learning · Computer Science 2024-08-27 Quanziang Wang , Renzhen Wang , Yichen Wu , Xixi Jia , Minghao Zhou , Deyu Meng

Unsupervised domain adaption has been widely adopted in tasks with scarce annotated data. Unfortunately, mapping the target-domain distribution to the source-domain unconditionally may distort the essential structural information of the…

Computer Vision and Pattern Recognition · Computer Science 2023-07-11 Munan Ning , Donghuan Lu , Yujia Xie , Dongdong Chen , Dong Wei , Yefeng Zheng , Yonghong Tian , Shuicheng Yan , Li Yuan

Since distribution shifts are likely to occur after a model's deployment and can drastically decrease the model's performance, online test-time adaptation (TTA) continues to update the model during test-time, leveraging the current test…

Computer Vision and Pattern Recognition · Computer Science 2024-01-03 Mario Döbler , Florian Marencke , Robert A. Marsden , Bin Yang

We introduce a practical Domain Adaptation (DA) paradigm called Class-Incremental Domain Adaptation (CIDA). Existing DA methods tackle domain-shift but are unsuitable for learning novel target-domain classes. Meanwhile, class-incremental…

Machine Learning · Computer Science 2020-08-05 Jogendra Nath Kundu , Rahul Mysore Venkatesh , Naveen Venkat , Ambareesh Revanur , R. Venkatesh Babu

Neural networks are known to be data hungry and domain sensitive, but it is nearly impossible to obtain large quantities of labeled data for every domain we are interested in. This necessitates the use of domain adaptation strategies. One…

Computation and Language · Computer Science 2019-10-08 Zi-Yi Dou , Xinyi Wang , Junjie Hu , Graham Neubig

Unsupervised tabular anomaly detection methods typically learn feature patterns from normal samples during training and subsequently identify samples that deviate from these patterns as anomalies during testing. However, in practical…

Machine Learning · Computer Science 2026-05-12 Wei Huang , Hezhe Qiao , Kailai Zhang , Zaisheng Ye , Yu-Ming Shang , Xiangling Fu

In this paper, we study the task of source-free domain adaptation (SFDA), where the source data are not available during target adaptation. Previous works on SFDA mainly focus on aligning the cross-domain distributions. However, they ignore…

Computer Vision and Pattern Recognition · Computer Science 2021-06-01 Guanglei Yang , Hao Tang , Zhun Zhong , Mingli Ding , Ling Shao , Nicu Sebe , Elisa Ricci

Test-time adaptation (TTA) enhances model robustness by enabling adaptation to target distributions that differ from training distributions, improving real-world generalizability. However, most existing TTA approaches focus on adjusting the…

Machine Learning · Computer Science 2026-05-05 Yewon Han , Seoyun Yang , Taesup Kim

Continual test-time adaptive object detection (CTTA-OD) aims to online adapt a source pre-trained detector to ever-changing environments during inference under continuous domain shifts. Most existing CTTA-OD methods prioritize effectiveness…

Computer Vision and Pattern Recognition · Computer Science 2025-06-04 Kunyu Wang , Xueyang Fu , Xin Lu , Chengjie Ge , Chengzhi Cao , Wei Zhai , Zheng-Jun Zha

Unwanted samples from private source categories in the learning objective of a partial domain adaptation setup can lead to negative transfer and reduce classification performance. Existing methods, such as re-weighting or aggregating target…

Computer Vision and Pattern Recognition · Computer Science 2023-10-20 Sandipan Choudhuri , Arunabha Sen

Fully test-time adaptation (FTTA) adapts a model that is trained on a source domain to a target domain during the testing phase, where the two domains follow different distributions and source data is unavailable during the training phase.…

Artificial Intelligence · Computer Science 2023-12-15 Houcheng Su , Daixian Liu , Mengzhu Wang , Wei Wang

This paper studies a new, practical but challenging problem, called Class-Incremental Unsupervised Domain Adaptation (CI-UDA), where the labeled source domain contains all classes, but the classes in the unlabeled target domain increase…

Computer Vision and Pattern Recognition · Computer Science 2022-08-01 Hongbin Lin , Yifan Zhang , Zhen Qiu , Shuaicheng Niu , Chuang Gan , Yanxia Liu , Mingkui Tan

Domain adaptation (DA) is the topical problem of adapting models from labelled source datasets so that they perform well on target datasets where only unlabelled or partially labelled data is available. Many methods have been proposed to…

Computer Vision and Pattern Recognition · Computer Science 2020-07-28 Da Li , Timothy Hospedales

Multivariate time-series anomaly detection (MTSAD) aims to identify deviations from normality in multivariate time-series and is critical in real-world applications. However, in real-world deployments, distribution shifts are ubiquitous and…

Machine Learning · Computer Science 2026-04-03 HyunGi Kim , Jisoo Mok , Hyungyu Lee , Juhyeon Shin , Sungroh Yoon
‹ Prev 1 8 9 10 Next ›