Similarity-Guided Layer-Adaptive Vision Transformer for UAV Tracking
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917949807263744 |
|---|---|
| author | Xue, Chaocan Zhong, Bineng Liang, Qihua Zheng, Yaozong Li, Ning Xue, Yuanliang Song, Shuxiang |
| author_facet | Xue, Chaocan Zhong, Bineng Liang, Qihua Zheng, Yaozong Li, Ning Xue, Yuanliang Song, Shuxiang |
| contents | Vision transformers (ViTs) have emerged as a popular backbone for visual tracking. However, complete ViT architectures are too cumbersome to deploy for unmanned aerial vehicle (UAV) tracking which extremely emphasizes efficiency. In this study, we discover that many layers within lightweight ViT-based trackers tend to learn relatively redundant and repetitive target representations. Based on this observation, we propose a similarity-guided layer adaptation approach to optimize the structure of ViTs. Our approach dynamically disables a large number of representation-similar layers and selectively retains only a single optimal layer among them, aiming to achieve a better accuracy-speed trade-off. By incorporating this approach into existing ViTs, we tailor previously complete ViT architectures into an efficient similarity-guided layer-adaptive framework, namely SGLATrack, for real-time UAV tracking. Extensive experiments on six tracking benchmarks verify the effectiveness of the proposed approach, and show that our SGLATrack achieves a state-of-the-art real-time speed while maintaining competitive tracking precision. Codes and models are available at https://github.com/GXNU-ZhongLab/SGLATrack. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_06625 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Similarity-Guided Layer-Adaptive Vision Transformer for UAV Tracking Xue, Chaocan Zhong, Bineng Liang, Qihua Zheng, Yaozong Li, Ning Xue, Yuanliang Song, Shuxiang Computer Vision and Pattern Recognition Vision transformers (ViTs) have emerged as a popular backbone for visual tracking. However, complete ViT architectures are too cumbersome to deploy for unmanned aerial vehicle (UAV) tracking which extremely emphasizes efficiency. In this study, we discover that many layers within lightweight ViT-based trackers tend to learn relatively redundant and repetitive target representations. Based on this observation, we propose a similarity-guided layer adaptation approach to optimize the structure of ViTs. Our approach dynamically disables a large number of representation-similar layers and selectively retains only a single optimal layer among them, aiming to achieve a better accuracy-speed trade-off. By incorporating this approach into existing ViTs, we tailor previously complete ViT architectures into an efficient similarity-guided layer-adaptive framework, namely SGLATrack, for real-time UAV tracking. Extensive experiments on six tracking benchmarks verify the effectiveness of the proposed approach, and show that our SGLATrack achieves a state-of-the-art real-time speed while maintaining competitive tracking precision. Codes and models are available at https://github.com/GXNU-ZhongLab/SGLATrack. |
| title | Similarity-Guided Layer-Adaptive Vision Transformer for UAV Tracking |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.06625 |