解决视觉追踪中历史预测噪声导致的模型漂移问题
Drift-Resilient Temporal Priors for Visual Tracking
- 通过可靠性校准过滤历史状态噪声，保留真实模板信息
- 生成动态时间先验，提升追踪稳定性，最高达77.5%成功率
- 可无缝嵌入主流追踪器，适合需要高精度长期追踪场景
时间信息对视觉追踪至关重要，但现有多帧追踪器易因简单聚合噪声历史预测而产生模型漂移。本文提出DTPTrack，一种轻量且通用的模块，可无缝集成至现有追踪器以抑制漂移。框架包含两个核心组件：(1) 时间可靠性校准器（TRC），学习为每帧历史状态分配可靠性评分，过滤噪声并锚定真实模板；(2) 时间引导合成器（TGS），将校准后的历史信息转化为一组紧凑的动态时间先验，提供预测引导。为验证其通用性，我们将DTPTrack集成至OSTrack、ODTrack和LoRAT三种不同架构，在所有基线中均取得显著性能提升。最佳模型基于扩展的LoRATv2主干，在多个基准上达到新纪录：LaSOT上成功率为77.5%，GOT-10k上AO为80.3%。
原文摘要 · Abstract (English)
Temporal information is crucial for visual tracking, but existing multi-frame trackers are vulnerable to model drift caused by naively aggregating noisy historical predictions. In this paper, we introduce DTPTrack, a lightweight and generalizable module designed to be seamlessly integrated into existing trackers to suppress drift. Our framework consists of two core components: (1) a Temporal Reliability Calibrator (TRC) mechanism that learns to assign a per-frame reliability score to historical states, filtering out noise while anchoring on the ground-truth template; and (2) a Temporal Guidance Synthesizer (TGS) module that synthesizes this calibrated history into a compact set of dynamic temporal priors to provide predictive guidance. To demonstrate its versatility, we integrate DTPTrack into three diverse tracking architectures--OSTrack, ODTrack, and LoRAT-and show consistent, significant performance gains across all baselines. Our best-performing model, built upon an extended LoRATv2 backbone, sets a new state-of-the-art on several benchmarks, achieving a 77.5% Success rate on LaSOT and an 80.3% AO on GOT-10k.
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。