FARTrack: 快速自回归视觉跟踪与高性能
FARTrack: Fast Autoregressive Visual Tracking with High Performance
AI总结：
FARTrack通过任务特定自蒸馏和帧间自回归稀疏化，实现了高效且高性能的视觉跟踪，在GOT-10k上达到70.6%的AO，同时在GPU和CPU上分别达到343 FPS和121 FPS。
摘要：
在视觉跟踪领域，推理速度和跟踪性能是两个关键的评估指标。然而，高性能跟踪器往往处理速度较慢，使其在资源受限的设备上难以部署。为了解决这一问题，我们提出了FARTrack，一种快速自回归跟踪框架。由于自回归强调轨迹序列的时间特性，它可以在各种设备上实现高效执行的同时保持高性能。FARTrack引入了任务特定的自蒸馏和帧间自回归稀疏化，分别从浅而准确的蒸馏和冗余到本质的标记优化的角度进行设计。任务特定的自蒸馏通过逐层蒸馏任务特定的标记来实现模型压缩，提高模型的推理速度，同时避免次优的手动教师-学生层配对分配。同时，帧间自回归稀疏化依次压缩多个模板，避免额外的运行时开销，同时学习一个时间全局最优的稀疏化策略。FARTrack展示了出色的速度和竞争性的性能。它在GOT-10k上实时情况下实现了70.6%的AO。此外，我们的最快模型在GPU上以343 FPS的速度，在CPU上以121 FPS的速度运行。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
