LoopTrack：参数高效Transformer跟踪的简单基线
LoopTrack: A Simple Baseline for Parameter-Efficient Transformer Tracking
AI总结：
提出LoopTrack，一种参数高效的Transformer跟踪框架，通过循环共享参数块减少参数，并引入目标感知循环和门控目标记忆，在多个数据集上实现精度与参数的良好权衡。
AI中文摘要：
当前基于Transformer的跟踪方法通常堆叠多个具有独立参数的Transformer块，以建模目标模板与搜索区域之间的交互，从而实现目标定位。这些跟踪器常因堆叠的块而产生大量参数开销，使其难以部署在资源受限的设备上。为解决此问题，我们提出了一种参数高效的Transformer跟踪框架，称为LoopTrack，它通过循环架构重复应用一组共享参数的Transformer块来交互特征，显著减少了参数数量。为进一步利用目标线索，我们提出了两种轻量级设计，包括目标感知循环（TAL）和门控目标记忆（GTM）。前者利用一次循环生成的中间目标信息来指导后续循环中的特征交互，实现渐进式特征细化；后者则在帧间维护紧凑的记忆，并将其纳入循环过程，为跟踪器提供长期信息，缓解跟踪中的时间漂移。与现有Transformer跟踪器相比，LoopTrack以更少的模型参数实现多轮特征交互，使其部署更加资源友好。在多个数据集上的大量实验中，LoopTrack展现了良好的精度-参数权衡。特别是，我们的LoopTrack$_{\ m One}$使用单个共享Transformer块，在LaSOT上达到66.2%的SUC分数，仅需3.4M参数；而LoopTrack$_{\ m Three}$使用三个共享块，以6.4M参数达到69.3%的SUC分数，超越了现有参数高效跟踪方法，且模型规模相当或更小。通过LoopTrack，我们旨在为参数高效的Transformer跟踪建立一个简单而强大的基线。我们的代码和模型将发布。
英文摘要：
Current Transformer-based tracking methods typically stack multiple Transformer blocks with separate parameters to model interactions between the target template and the search region for target localization. These trackers often incur substantial parameter overhead from stacked blocks, making their deployment on resource-limited devices difficult. To address this, we propose a parameter-efficient Transformer tracking framework, dubbed LoopTrack, which repeatedly applies a set of Transformer blocks with shared parameters to interact features in a looped architecture for tracking, significantly reducing the number of parameters. To further exploit target cues, we present two lightweight designs, including target-aware looping (TAL) and gated target memory (GTM). The former applies intermediate target information generated by one loop to guide feature interaction in the subsequent loop, enabling progressive feature refinement, while the latter maintains a compact memory across frames, which is incorporated into the loop process to provide long-term information to the tracker, mitigating temporal drift in tracking. Compared to existing Transformer trackers, LoopTrack enables multiple rounds of feature interaction with fewer model parameters, making it resource-friendly for deployment. In extensive experiments on multiple datasets, LoopTrack shows a favorable accuracy-parameter trade-off. In particular, our LoopTrack$_{\rm One}$, with a single shared Transformer block, achieves 66.2\% SUC score on LaSOT with only 3.4M parameters, while LoopTrack$_{\rm Three}$, using three shared blocks, achieves 69.3\% SUC score with 6.4M parameters, surpassing existing parameter-efficient tracking methods with comparable or larger model size. With LoopTrack, we aim to establish a simple yet strong baseline for parameter-efficient Transformer tracking. Our code and models will be released.
