UTPTrack：面向视觉跟踪的简单统一词元剪枝
UTPTrack: Towards Simple and Unified Token Pruning for Visual Tracking
提出一种注意力引导、词元类型感知的统一剪枝策略，可同时压缩搜索区域、动态模板和静态模板中的视觉词元，为基于单流 Transformer 的跟踪器在保持精度的同时大幅降低计算量，该思路可迁移到其他需要处理多源视觉词元的 Transformer 任务。
原文依据 UTPTrack employs an attention-guided, token type-aware strategy to holistically model redundancy
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于单流 Transformer 的跟踪器在视觉目标跟踪中取得了先进性能，但存在显著的计算开销，阻碍了实时部署。尽管词元剪枝提供了一条效率提升路径，但仍存在一个关键局限：现有工作均未在搜索区域、动态模板和静态模板这三个关键组件上联合执行剪枝。这种孤立处理忽视了组件间的相互依赖，导致次优的剪枝效果和精度下降。为解决此问题，我们提出 UTPTrack，一个简单且统一的词元剪枝框架，首次联合压缩所有三个组件。UTPTrack 采用注意力引导、词元类型感知的策略来整体建模冗余，该设计能够在一个模型内无缝支持多模态和语言引导任务的统一跟踪。在 10 个基准上的综合评估表明，UTPTrack 在基于剪枝的跟踪器中实现了精度-效率权衡的新最优，在基于 RGB 的跟踪中剪除 65.4% 的视觉词元，在统一跟踪中剪除 67.5% 的视觉词元，同时分别保持基线性能的 99.7% 和 100.5%。在 RGB 和多模态场景下的强劲表现凸显了其作为高效视觉跟踪未来研究坚实基础的潜力。
英文原文摘要 1342 字符
One-stream Transformer-based trackers achieve advanced performance in visual object tracking suffer from significant computational overhead that hinders real-time deployment. While token pruning offers a path to efficiency, a critical limitation persists: no existing work performs pruning jointly across all three critical components--the search region, dynamic template, and static template. This isolation overlooks interdependencies, yielding 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 multi-modal and language-guided tasks within a single model. Comprehensive 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.