LiteTrack: Layer Pruning with Asynchronous Feature Extraction for Lightweight and Efficient Visual Tracking

Qingmao Wei1; Bi Zeng1; Jianqi Liu1; Li He2; Guotian Zeng1

10.1109/ICRA57147.2024.10610022

2024-05-17

979-8-3503-8458-1

2024 IEEE International Conference on Robotics and Automation (ICRA)

13-17 May 2024

Yokohama, Japan

The recent advancements in transformer-based visual trackers have led to significant progress, attributed to their strong modeling capabilities. However, as performance improves, running latency correspondingly increases, presenting a challenge for real-time robotics applications, especially on edge devices with computational constraints. In response to this, we introduce LiteTrack, an efficient transformer-based tracking model optimized for high-speed operations across various devices. It achieves a more favorable trade-off between accuracy and efficiency than the other lightweight trackers. The main innovations of LiteTrack encompass: 1) asynchronous feature extraction and interaction between the template and search region for better feature fushion and cutting redundant computation, and 2) pruning encoder layers from a heavy tracker to refine the balnace between performance and speed. As an example, our fastest variant, LiteTrack-B4, achieves 65.2% AO on the GOT-10k benchmark, surpassing all preceding efficient trackers, while running over 100 fps with ONNX on the Jetson Orin NX edge device. Moreover, our LiteTrack-B9 reaches competitive 72.2% AO on GOT-10k and 82.4% AUC on TrackingNet, and operates at 171 fps on an NVIDIA 2080Ti GPU. The code and demo materials will be available at https://github.com/TsingWei/LiteTrack.

其他

EI

1.School of Computer, Guangdong University of Technology, Guangzhou, China
2.Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen, China

Qingmao Wei,Bi Zeng,Jianqi Liu,et al. LiteTrack: Layer Pruning with Asynchronous Feature Extraction for Lightweight and Efficient Visual Tracking[C],2024.