@article{han2021general,
	title={General Greedy De-bias Learning},
	author={Han, Xinzhe and Wang, Shuhui and Su, Chi and Huang, Qingming and Tian, Qi},
	journal={arXiv preprint arXiv:2112.10572 },
	year={2021}
}

@inproceedings{han2021greedy,
  title={Greedy gradient ensemble for robust visual question answering},
  author={Han, Xinzhe and Wang, Shuhui and Su, Chi and Huang, Qingming and Tian, Qi},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={1584--1593},
  year={2021}
}

loss = -(logits.log_softmax(-1) * labels).mean() + weight * (logits.log_softmax(-1) * bias * labels).mean()

CUDA_VISIBLE_DEVICES=0 python main.py --dataset cpv2 --mode gge_iter --debias ce_decompose --topq 1 --topv -1 --qvp 5 --output []