Awesome

IoUattack

:herb: IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object Tracking

Shuai Jia, Yibing Song, Chao Ma and Xiaokang Yang

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021.

Introduction

<img src="https://github.com/VISION-SJTU/IoUattack/blob/main/demo/intro.png" width='500'/><br/>

We observe that the increase of noise level positively correlates to the decrease of IoU scores, but their directions are not exactly the same.

• Our IoU attack seeks to inject the lowest amount of noisy perturbations at the same contour line of IoU score for each iteration.
• We choose three representative trackers with different structures, SiamRPN++, DiMP and LTMU, respectively.

Results

Result for SiamRPN++ on multiple datasets

Result for DiMP on multiple datasets

Result for LTMU on multiple datasets

:herb: All raw results are available. [Google_drive]

Code

:herb: The code of IoU attack for SiamRPN++ is released!!

• You should put the datasets into pysot/testing_dataset folder.
• Please download the pretrained model and set the environments of SiamPRN++.
• See SiamRPN++ for more details.

Test the original performance on VOT2018 dataset, please use the following command.

cd pysot/experiments/siamrpn_r50_l234_dwxcorr
python -u ../../tools/test_original.py 	\
	--snapshot model.pth 	\ # model path
	--dataset VOT2018 	\ # dataset name
	--config config.yaml	  # config file

Test IoU attack on VOT2018 dataset, please use the following command.

cd pysot/experiments/siamrpn_r50_l234_dwxcorr
python -u ../../tools/test_IoU_attack.py 	\
	--snapshot model.pth 	\ # model path
	--dataset VOT2018 	\ # dataset name
	--config config.yaml	  # config file

For the adversarial attack of other datasets, you should change the dataset name as mentioned above.

Demo

<img src="https://github.com/VISION-SJTU/IoUattack/blob/main/demo/car_clean.gif" width='300'/> <img src="https://github.com/VISION-SJTU/IoUattack/blob/main/demo/car_attack.gif" width='300'/><br/>         <img src="https://github.com/VISION-SJTU/IoUattack/blob/main/demo/legend.png" width='300'/><br/>

Citation

If any part of our paper and code is helpful to your work, please generously citing:

@inproceedings{jia-cvpr21-iouattack,
  title={IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object Tracking},
  author={Jia, Shuai and Song, Yibing and Ma, Chao and Yang, Xiaokang},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2021}
}

Thank you :)

Reference

We choose three representative trackers, SiamRPN++, DiMP and LTMU. The original code of these trackers are list as follows:

• SiamRPN++: https://github.com/STVIR/pysot
• DiMP: https://github.com/visionml/pytracking
• LTMU: https://github.com/Daikenan/LTMU

We also refer to the code of Boundary Attack for IoU attack.

• Boundary Attack: https://github.com/greentfrapp/boundary-attack

Thanks for their wonderful works!

License

Licensed under an MIT license.