MaST：面向轻量型目标跟踪的运动感知稀疏流水线
MaST: Motion-aware Sparse Pipeline for Lightweight Object Tracking
浏览论文内容
中文总结 AI 辅助
针对Transformer目标跟踪器计算成本过高的问题，提出MaST框架，通过运动先验优化token剪枝、设计原生稀疏预测头，在轻量型跟踪任务中取得最优性能，速度优于现有方法。
中文摘要 AI 辅助
基于Transformer的目标跟踪器以其优异性能著称，但密集token处理往往会带来过高的计算成本，限制了在边缘设备上的实时部署。尽管近期研究探索了token剪枝以减少计算量，但往往未能形成端到端的稀疏流水线：早期层的token分数因缺乏运动先验而存在噪声，且许多跟踪器最终会回归到密集重塑以输入密集预测头，这部分抵消了剪枝带来的节省。本文提出运动感知稀疏跟踪器（Motion-aware Sparse Tracker，MaST），这是一种从token到框均实现稀疏化的跟踪框架。首先，MaST注入轻量型运动先验以优化基于交叉注意力的重要性分数，支持在搜索区域中更早、更稳定地减少token数量。其次，我们引入原生稀疏预测头，其直接基于保留的非结构化token运行，采用“分数优先、一次回归”的设计，消除了密集填充/重塑操作，减少了冗余计算。在多个基准上的大量实验表明，MaST在轻量型跟踪器中达到了新的最优水平：MaST-tiny在LaSOT上获得63.8 AUC，在TrackingNet上获得80.1 SUC，超越了此前最优的AsymTrack-S，分别提升了1.0 AUC和2.2 SUC，同时在Jetson Nano上以152 FPS运行，速度几乎是AsymTrack-S（88 FPS）的两倍。代码可在该https链接获取。
英文摘要
Transformer-based object trackers are renowned for their strong performance, yet dense token processing often leads to prohibitive computational cost, limiting real-time deployment on edge devices. While recent works explore token pruning to reduce computation, they often stop short of an end-to-end sparse pipeline, as early-layer token scores can be noisy without a motion prior, and many trackers ultimately fall back to dense reshaping to feed the dense prediction head that partially negates the savings. We introduce Motion-aware Sparse Tracker (MaST), a sparse tracking framework that makes sparsity effective from tokens to boxes. First, MaST injects a lightweight motion prior to refine cross-attention-based importance scores, enabling earlier and more stable token reduction in the search region. Second, we introduce a natively sparse prediction head that operates directly on the retained unstructured tokens with a score-first, regress-once design, eliminating dense padding/reshaping and reducing redundant computation. Extensive experiments on multiple benchmarks demonstrate that MaST establishes new state of the art among lightweight trackers, where MaST-tiny attains 63.8 AUC on LaSOT and 80.1 SUC on TrackingNet, surpassing the prior best AsymTrack-S by +1.0 AUC and +2.2 SUC while running at 152 FPS on Jetson Nano, nearly twice as fast as AsymTrack-S at 88 FPS. Code is available at https://github.com/TsingWei/MaST.
发表机构
- South China University of Technology（华南理工大学）
- Pengcheng Laboratory（鹏城实验室）
机构由 AI 辅助整理，请以论文原文为准。
