Domain-Conditioned Normalization for Test-Time Domain Generalization
Abstract
Domain generalization aims to train a robust model on multiple source domains that generalizes well to unseen target domains. While considerable attention has focused on training domain generalizable models, a few recent studies have shifted the attention to test time, i.e., leveraging test samples for better target generalization. To this end, this paper proposes a novel test-time domain generalization method, Domain Conditioned Normalization (DCN), to infer the normalization statistics of the target domain from only a single test sample. In order to learn to predict the normalization statistics, DCN adopts a meta-learning framework and simulates the inference process of the normalization statistics at training. Extensive experimental results have shown that DCN brings consistent improvements to many state-of-the-art domain generalization methods on three widely adopted benchmarks.
Cite
Text
Jiang et al. "Domain-Conditioned Normalization for Test-Time Domain Generalization." European Conference on Computer Vision Workshops, 2022. doi:10.1007/978-3-031-25085-9_17Markdown
[Jiang et al. "Domain-Conditioned Normalization for Test-Time Domain Generalization." European Conference on Computer Vision Workshops, 2022.](https://mlanthology.org/eccvw/2022/jiang2022eccvw-domainconditioned/) doi:10.1007/978-3-031-25085-9_17BibTeX
@inproceedings{jiang2022eccvw-domainconditioned,
title = {{Domain-Conditioned Normalization for Test-Time Domain Generalization}},
author = {Jiang, Yuxuan and Wang, Yanfeng and Zhang, Ruipeng and Xu, Qinwei and Zhang, Ya and Chen, Xin and Tian, Qi},
booktitle = {European Conference on Computer Vision Workshops},
year = {2022},
pages = {291-307},
doi = {10.1007/978-3-031-25085-9_17},
url = {https://mlanthology.org/eccvw/2022/jiang2022eccvw-domainconditioned/}
}