[CJA 2023] Template-guided frequency attention and adaptive cross-entropy loss for UAV visual tracking
This is an official pytorch implementation of the 2023 Chinese Journal of Aeronautics paper:
Template-guided frequency attention and adaptive cross-entropy loss for UAV visual tracking
(accepted by Chinese Journal of Aeronautics, DOI: https://doi.org/10.1016/j.cja.2023.03.048)
The paper can be downloaded from Chinese Journal of Aeronautics
The models and raw results can be downloaded from BaiduYun.
Datasets | TGFAT_r50_l234 |
---|---|
UAV123(Suc./Pre.) | 0.617/0.827 |
UAVDT(Suc./Pre.) | 0.606/0.844 |
Note:
r50_lxyz
denotes the outputs of stage x, y, and z in ResNet-50.
Please find installation instructions in INSTALL.md
.
export PYTHONPATH=/path/to/TGFAT:$PYTHONPATH
python tools/demo.py \
--config experiments/siamban_mobilev2_l234/config.yaml \
--snapshot experiments/siamban_mobilev2_l234/MobileTrack.pth
--video demo/bag.avi
Download datasets and put them into testing_dataset
directory. Jsons of commonly used datasets can be downloaded from Google Drive or BaiduYun. If you want to test tracker on new dataset, please refer to pysot-toolkit to setting testing_dataset
.
cd experiments/siamban_mobilev2_l234
python -u ../../tools/test.py \
--snapshot TGFAT.pth \ # model path
--dataset UAV123 \ # dataset name
--config config.yaml # config file
The testing results will in the current directory(results/dataset/model_name/)
assume still in experiments/siamban_mobilev2_l234
python ../../tools/eval.py \
--tracker_path ./results \ # result path
--dataset UAV123 \ # dataset name
--num 1 \ # number thread to eval
--tracker_prefix 'ch*' # tracker_name
See TRAIN.md for detailed instruction.
The code based on the PySOT , SiamBAN , FcaNet and SiamCAN
We would like to express our sincere thanks to the contributors.