A comprehensive survey on test-time adaptation under distribution shifts

J Liang, R He, T Tan - International Journal of Computer Vision, 2024 - Springer
Abstract Machine learning methods strive to acquire a robust model during the training
process that can effectively generalize to test samples, even in the presence of distribution …

Source-free unsupervised domain adaptation: Current research and future directions

N Zhang, J Lu, K Li, Z Fang, G Zhang - Neurocomputing, 2024 - Elsevier
In the field of Transfer Learning, Source-Free Unsupervised Domain Adaptation (SFUDA)
emerges as a practical and novel task that enables a pre-trained model to adapt to a new …

Divide and adapt: Active domain adaptation via customized learning

D Huang, J Li, W Chen, J Huang… - Proceedings of the …, 2023 - openaccess.thecvf.com
Active domain adaptation (ADA) aims to improve the model adaptation performance by
incorporating the active learning (AL) techniques to label a maximally-informative subset of …

Class relationship embedded learning for source-free unsupervised domain adaptation

Y Zhang, Z Wang, W He - … of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
This work focuses on a practical knowledge transfer task defined as Source-Free
Unsupervised Domain Adaptation (SFUDA), where only a well-trained source model and …

Consistency regularization for generalizable source-free domain adaptation

L Tang, K Li, C He, Y Zhang… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Source-free domain adaptation (SFDA) aims to adapt a well-trained source model to an
unlabelled target domain without accessing the source dataset, making it applicable in a …

Diversifying spatial-temporal perception for video domain generalization

KY Lin, JR Du, Y Gao, J Zhou… - Advances in Neural …, 2024 - proceedings.neurips.cc
Video domain generalization aims to learn generalizable video classification models for
unseen target domains by training in a source domain. A critical challenge of video domain …

Activate and reject: towards safe domain generalization under category shift

C Chen, L Tang, L Tao, HY Zhou… - Proceedings of the …, 2023 - openaccess.thecvf.com
Albeit the notable performance on in-domain test points, it is non-trivial for deep neural
networks to attain satisfactory accuracy when deploying in the open world, where novel …

Human-centric autonomous systems with llms for user command reasoning

Y Yang, Q Zhang, C Li, DS Marta… - Proceedings of the …, 2024 - openaccess.thecvf.com
The evolution of autonomous driving has made remarkable advancements in recent years,
evolving into a tangible reality. However, a human-centric large-scale adoption hinges on …

Lead: Learning decomposition for source-free universal domain adaptation

S Qu, T Zou, L He, F Röhrbein, A Knoll… - Proceedings of the …, 2024 - openaccess.thecvf.com
Abstract Universal Domain Adaptation (UniDA) targets knowledge transfer in the presence
of both covariate and label shifts. Recently Source-free Universal Domain Adaptation (SF …

Distribution shift matters for knowledge distillation with webly collected images

J Tang, S Chen, G Niu… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract Knowledge distillation aims to learn a lightweight student network from a pre-
trained teacher network. In practice, existing knowledge distillation methods are usually …