HiFT: Hierarchical Feature Transformer for Aerial Tracking
Ziang Cao, Changhong Fu, Junjie Ye, Bowen Li, and Yiming Li
Our paper is Accepted by ICCV 2021.


Most existing Siamese-based tracking methods execute the classification and regression of the target object based on the similarity maps. However, they either employ a single map from the last convolutional layer which degrades the localization accuracy in complex scenarios or separately use multiple maps for decision making, introducing intractable computations for aerial mobile platforms. Thus, in this work, we propose an efficient and effective hierarchical feature transformer (HiFT) for aerial tracking. Hierarchical similarity maps generated by multi-level convolutional layers are fed into the feature transformer to achieve the interactive fusion of spatial (shallow layers) and semantics cues (deep layers). Consequently, not only the global contextual information can be raised, facilitating the target search, but also our end-to-end architecture with the transformer can efficiently learn the interdependencies among multi-level features, thereby discovering a tracking-tailored feature space with strong discriminability. Comprehensive evaluations on four aerial benchmarks have proven the effectiveness of HiFT. Real-world tests on the aerial platform have strongly validated its practicability with a real-time speed.


This figure shows the workflow of our tracker.

About Code

1. Environment setup

This code has been tested on Ubuntu 18.04, Python 3.8.3, Pytorch 0.7.0/1.6.0, CUDA 10.2.
Please install related libraries before running this code:

pip install -r requirements.txt

2. Test

Download pretrained model: general_model(code: c99t) and put it into tools/snapshot directory.

Download testing datasets and put them into test_dataset directory. If you want to test the tracker on a new dataset, please refer to pysot-toolkit to set test_dataset.

python test.py                                
	--dataset UAV10fps                 #dataset_name
	--snapshot snapshot/general_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: train_dataset/dataset_name/readme.md has listed detailed operations about how to generate training datasets.

Train a model

To train the SiamAPN model, run train.py with the desired configs:

cd tools
python train.py

4. Evaluation

We provide the tracking results (code: tj12) of [email protected], DTB70, UAV20L, and UAV123. If you want to evaluate the tracker, please put those results into results directory.

python eval.py 	                          \
	--tracker_path ./results          \ # result path
	--dataset UAV20                  \ # dataset_name
	--tracker_prefix 'general_model'   # tracker_name

5. Contact

If you have any questions, please contact me.

Ziang Cao

Email: [email protected]

Qualitative Evaluation


Performance Comparison


Result on DTB70 and UAV20L

For more evaluations, please refer to our paper.


	author={Cao, Ziang and Fu, Changhong and Ye, Junjie and Li, Bowen and Li, Yiming},   
	booktitle={Proceedings of the IEEE International Conference on Computer Vision (ICCV)}, 
	title={{HiFT: Hierarchical Feature Transformer for Aerial Tracking}},


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