ML Anthology

A Three-Stage Model Fusion Method for Out-of-Distribution Generalization

Jiahao Wang, Hao Wang, Zhuojun Dong, Hua Yang, Yuting Yang, Qianyue Bao, Fang Liu, Licheng Jiao
ECCVW 2022 pp. 488-499
doi:10.1007/978-3-031-25075-0_33 /eccvw/2022/wang2022eccvw-threestage/

Abstract

Training a model from scratch in a data-deficient environment is a challenging task. In this challenge, multiple differentiated backbones are used to train, and a number of tricks are used to assist in model training, such as initializing weights, mixup, and cutmix. Finally, we propose a three-stage model fusion to improve our accuracy. Our final accuracy of Top-1 on the public test set is 84.62421%.

PDF ECCVW Semantic Scholar

Cite

Text

Wang et al. "A Three-Stage Model Fusion Method for Out-of-Distribution Generalization." European Conference on Computer Vision Workshops, 2022. doi:10.1007/978-3-031-25075-0_33

Markdown

[Wang et al. "A Three-Stage Model Fusion Method for Out-of-Distribution Generalization." European Conference on Computer Vision Workshops, 2022.](https://mlanthology.org/eccvw/2022/wang2022eccvw-threestage/) doi:10.1007/978-3-031-25075-0_33

BibTeX

@inproceedings{wang2022eccvw-threestage,
  title     = {{A Three-Stage Model Fusion Method for Out-of-Distribution Generalization}},
  author    = {Wang, Jiahao and Wang, Hao and Dong, Zhuojun and Yang, Hua and Yang, Yuting and Bao, Qianyue and Liu, Fang and Jiao, Licheng},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2022},
  pages     = {488-499},
  doi       = {10.1007/978-3-031-25075-0_33},
  url       = {https://mlanthology.org/eccvw/2022/wang2022eccvw-threestage/}
}