Code for the paper "Graph Attention Tracking". (CVPR2021)

1. Environment setup

This code has been tested on Ubuntu 16.04, Python 3.5, Pytorch 1.2.0, CUDA 9.0.
Please install related libraries before running this code:

pip install -r requirements.txt

2. Test

Dataset SiamGAT Model Link
OTB100 Success 71.0 Google Driver/
Precision 91.7
UAV123 Success 64.6
Precision 84.3
LaSOT Success 53.9 Google Driver/
Norm precision 63.3
Precision 53.0
GOT10k AO 63.1 Google Driver/
SR0.5 74.6
SR0.75 50.4
TrackingNet Success 75.3 Google Driver/
Norm precision 80.7
Precision 69.8

Download testing datasets and put them into test_dataset directory. Jsons of commonly used datasets can be downloaded from BaiduYun. If you want to test the tracker on a new dataset, please refer to pysot-toolkit to set test_dataset.

The tracking result can be download from BaiduYun (extract code: 5o17) or GoogleDriver for comparision.

python \    
        --config ../experiments/siamgat_googlenet_otb_uav/config.yaml \
	--dataset UAV123 \                                 # dataset_name
	--snapshot snapshot/otb_uav_model.pth              # tracker_name

The testing result will be saved in the results/dataset_name/tracker_name directory.

3. Train

Prepare training datasets

Download the datasets´╝Ü

Note: training_dataset/dataset_name/ has listed detailed operations about how to generate training datasets.

Download pretrained backbones

Download pretrained backbones from link and put them into pretrained_models directory.

Train a model

To train the SiamGAT model, run with the desired configs:

cd tools

4. Evaluation

We provide the tracking results (extract code: 0wod) (results in Google driver) of GOT-10k, LaSOT, OTB100 and UAV123. If you want to evaluate the tracker on OTB100, UAV123 and LaSOT, please put those results into results directory. Evaluate GOT-10k on Server.
Get TrackingNet results from BaiduYun (extract code: iwlj), and evaluate it on Server.

python 	                          \
	--tracker_path ./results          \ # result path
	--dataset UAV123                  \ # dataset_name
	--tracker_prefix 'otb_uav_model'   # tracker_name

5. Acknowledgement

The code is implemented based on pysot and SiamCAR. We would like to express our sincere thanks to the contributors.

6. Cite

If you use SiamGAT in your work please cite our papers:

author = {Guo, Dongyan and Shao, Yanyan and Cui, Ying and Wang, Zhenhua and Zhang, Liyan and Shen, Chunhua},
title = {Graph Attention Tracking},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2021}

author = {Guo, Dongyan and Wang, Jun and Cui, Ying and Wang, Zhenhua and Chen, Shengyong},
title = {SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Tracking},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}