Released code for Causal Attention for Unbiased Visual Recognition

This repo contains the codes of training our CaaM on NICO/ImageNet9 dataset. Due to my recent limited bandwidth, this codebase is still messy, which will be further refined and checked recently.

0. Bibtex

If you find our codes helpful, please cite our paper:

@inproceedings{wang2021causal,
  title={Causal Attention for Unbiased Visual Recognition},
  author={Wang, Tan and Zhou, Chang and Sun, Qianru and Zhang, Hanwang},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  year={2021}
}

1. Preparation

1. Installation: Python3.6, Pytorch1.6, tensorboard, timm(0.3.4), scikit-learn, opencv-python, matplotlib, yaml
2. Dataset:

1. Please remember to change the data path in the config file.

2. Evaluation:

1. For ResNet18 on NICO dataset

CUDA_VISIBLE_DEVICES=0 python train.py -cfg conf/ours_resnet18_multilayer2_bf0.02_noenv_pw5e5.yaml -debug -gpu -eval pretrain_model/nico_resnet18_ours_caam-best.pth

The results will be: Val Score: 0.4638461470603943 Test Score: 0.4661538600921631

1. For T2T-ViT7 on NICO dataset

CUDA_VISIBLE_DEVICES=0,1 python train.py -cfg conf/ours_t2tvit7_bf0.02_s4_noenv_pw5e4.yaml -debug -gpu -multigpu

 
 

 
To finish reading, please visit source site