English

FARTrack: Fast Autoregressive Visual Tracking with High Performance

Computer Vision and Pattern Recognition 2026-03-09 v2

Abstract

Inference speed and tracking performance are two critical evaluation metrics in the field of visual tracking. However, high-performance trackers often suffer from slow processing speeds, making them impractical for deployment on resource-constrained devices. To alleviate this issue, we propose FARTrack, a Fast Auto-Regressive Tracking framework. Since autoregression emphasizes the temporal nature of the trajectory sequence, it can maintain high performance while achieving efficient execution across various devices. FARTrack introduces Task-Specific Self-Distillation and Inter-frame Autoregressive Sparsification, designed from the perspectives of shallow-yet-accurate distillation and redundant-to-essential token optimization, respectively. Task-Specific Self-Distillation achieves model compression by distilling task-specific tokens layer by layer, enhancing the model's inference speed while avoiding suboptimal manual teacher-student layer pairs assignments. Meanwhile, Inter-frame Autoregressive Sparsification sequentially condenses multiple templates, avoiding additional runtime overhead while learning a temporally-global optimal sparsification strategy. FARTrack demonstrates outstanding speed and competitive performance. It delivers an AO of 70.6% on GOT-10k in real-time. Beyond, our fastest model achieves a speed of 343 FPS on the GPU and 121 FPS on the CPU.

Keywords

Cite

@article{arxiv.2602.03214,
  title  = {FARTrack: Fast Autoregressive Visual Tracking with High Performance},
  author = {Guijie Wang and Tong Lin and Yifan Bai and Anjia Cao and Shiyi Liang and Wangbo Zhao and Xing Wei},
  journal= {arXiv preprint arXiv:2602.03214},
  year   = {2026}
}
R2 v1 2026-07-01T09:33:40.913Z