ML Anthology

SimpleDG: Simple Domain Generalization Baseline Without Bells and Whistles

Zhi Lv, Bo Lin, Siyuan Liang, Lihua Wang, Mochen Yu, Yao Tang, Jiajun Liang
ECCVW 2022 pp. 477-487
doi:10.1007/978-3-031-25075-0_32 /eccvw/2022/lv2022eccvw-simpledg/

Abstract

We present a simple domain generalization baseline, which wins second place in both the common context generalization track and the hybrid context generalization track respectively in NICO CHALLENGE 2022. We verify the founding in recent literature, domainbed, that ERM is a strong baseline compared to recent state-of-the-art domain generalization methods and propose SimpleDG which includes several simple yet effective designs that further boost generalization performance. Code is available at https://github.com/megvii-research/ SimpleDG .

PDF ECCVW Semantic Scholar

Cite

Text

Lv et al. "SimpleDG: Simple Domain Generalization Baseline Without Bells and Whistles." European Conference on Computer Vision Workshops, 2022. doi:10.1007/978-3-031-25075-0_32

Markdown

[Lv et al. "SimpleDG: Simple Domain Generalization Baseline Without Bells and Whistles." European Conference on Computer Vision Workshops, 2022.](https://mlanthology.org/eccvw/2022/lv2022eccvw-simpledg/) doi:10.1007/978-3-031-25075-0_32

BibTeX

@inproceedings{lv2022eccvw-simpledg,
  title     = {{SimpleDG: Simple Domain Generalization Baseline Without Bells and Whistles}},
  author    = {Lv, Zhi and Lin, Bo and Liang, Siyuan and Wang, Lihua and Yu, Mochen and Tang, Yao and Liang, Jiajun},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2022},
  pages     = {477-487},
  doi       = {10.1007/978-3-031-25075-0_32},
  url       = {https://mlanthology.org/eccvw/2022/lv2022eccvw-simpledg/}
}