UTPTrack: Towards Simple and Unified Token Pruning for Visual Tracking
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912930078916608 |
|---|---|
| author | Wu, Hao Wang, Xudong Zhang, Jialiang Tong, Junlong Chen, Xinghao Lin, Junyan Ma, Yunpu Shen, Xiaoyu |
| author_facet | Wu, Hao Wang, Xudong Zhang, Jialiang Tong, Junlong Chen, Xinghao Lin, Junyan Ma, Yunpu Shen, Xiaoyu |
| contents | One-stream Transformer-based trackers achieve advanced performance in visual object tracking but suffer from significant computational overhead that hinders real-time deployment. While token pruning offers a path to efficiency, existing methods are fragmented. They typically prune the search region, dynamic template, and static template in isolation, overlooking critical inter-component dependencies, which yields suboptimal pruning and degraded accuracy. To address this, we introduce UTPTrack, a simple and Unified Token Pruning framework that, for the first time, jointly compresses all three components. UTPTrack employs an attention-guided, token type-aware strategy to holistically model redundancy, a design that seamlessly supports unified tracking across multimodal and language-guided tasks within a single model. Extensive evaluations on 10 benchmarks demonstrate that UTPTrack achieves a new state-of-the-art in the accuracy-efficiency trade-off for pruning-based trackers, pruning 65.4% of vision tokens in RGB-based tracking and 67.5% in unified tracking while preserving 99.7% and 100.5% of baseline performance, respectively. This strong performance across both RGB and multimodal scenarios underlines its potential as a robust foundation for future research in efficient visual tracking. Code will be released at https://github.com/EIT-NLP/UTPTrack. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_23734 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | UTPTrack: Towards Simple and Unified Token Pruning for Visual Tracking Wu, Hao Wang, Xudong Zhang, Jialiang Tong, Junlong Chen, Xinghao Lin, Junyan Ma, Yunpu Shen, Xiaoyu Computer Vision and Pattern Recognition Computation and Language One-stream Transformer-based trackers achieve advanced performance in visual object tracking but suffer from significant computational overhead that hinders real-time deployment. While token pruning offers a path to efficiency, existing methods are fragmented. They typically prune the search region, dynamic template, and static template in isolation, overlooking critical inter-component dependencies, which yields suboptimal pruning and degraded accuracy. To address this, we introduce UTPTrack, a simple and Unified Token Pruning framework that, for the first time, jointly compresses all three components. UTPTrack employs an attention-guided, token type-aware strategy to holistically model redundancy, a design that seamlessly supports unified tracking across multimodal and language-guided tasks within a single model. Extensive evaluations on 10 benchmarks demonstrate that UTPTrack achieves a new state-of-the-art in the accuracy-efficiency trade-off for pruning-based trackers, pruning 65.4% of vision tokens in RGB-based tracking and 67.5% in unified tracking while preserving 99.7% and 100.5% of baseline performance, respectively. This strong performance across both RGB and multimodal scenarios underlines its potential as a robust foundation for future research in efficient visual tracking. Code will be released at https://github.com/EIT-NLP/UTPTrack. |
| title | UTPTrack: Towards Simple and Unified Token Pruning for Visual Tracking |
| topic | Computer Vision and Pattern Recognition Computation and Language |
| url | https://arxiv.org/abs/2602.23734 |