用强化学习直接优化目标定位，让追踪更准。
RELO: Reinforcement Learning to Localize for Visual Object Tracking
- 把定位当作强化学习问题，用奖励驱动找目标位置。
- 在LaSOText上达到57.5% AUC，无需模板更新。
- 提升跨帧语义一致性，计算开销几乎不变。
传统视觉目标追踪器使用手工设计的空间先验（如热图）进行目标定位，这类先验仅提供代理监督，与追踪优化和评估指标（如交并比IoU、成功曲线下的面积AUC）对齐度差。本文提出RELO（REinforcement-learning-to-LOcalize），将目标定位建模为马尔可夫决策过程，用强化学习学习空间位置上的定位策略，奖励函数结合帧级IoU与序列级AUC。此外引入层对齐的时间令牌传播机制，提升帧间语义一致性，计算开销极低。在多个基准测试中表现优异，在不更新模板的LaSOText上达到57.5% AUC，验证了奖励驱动定位优于先验驱动定位的有效性。
原文摘要 · Abstract (English)
Conventional visual object trackers localize targets using handcrafted spatial priors, often in the form of heatmaps. Such priors provide only surrogate supervision and are poorly aligned with tracking optimization and evaluation metrics, such as intersection over union (IoU) and area under the success curve (AUC). Here, we introduce RELO, a REinforcement-learning-to-LOcalize method for visual object tracking that formulates target localization as a Markov decision process. Specifically, RELO replaces handcrafted spatial priors with a localization policy learned over spatial positions via reinforcement learning, with rewards combining frame-level IoU and sequence-level AUC. We additionally introduce layer-aligned temporal token propagation to improve semantic consistency across frames, with negligible computational overhead. Across multiple benchmarks, RELO achieves superior results, attaining 57.5% AUC on LaSOText without template updates. This confirms that reward-driven localization provides an effective alternative to prior-driven localization for visual object tracking.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。