用教师模型指导追踪器学习精准目标外观，提升跟踪稳定性。
Learning to Track from Privileged Target Appearances
- 通过师生框架，将过去/当前/未来帧的精确目标图像作为训练信号。
- 在LaSOT数据集上，追踪准确率（AUC）提升15.2个百分点。
- 适合需要高精度长期跟踪的应用，如自动驾驶与视频监控。
目标模板决定了视觉追踪器搜索的内容，但推理时可用的模板在定位准确性与外观新鲜度之间权衡：初始真值模板准确但过时，近期模板反映当前外观却来自不确定预测。我们通过一个不可部署的虚拟参考（oracle）提供当前帧的精确目标裁剪，在LaSOT上使AUC提升15.2个百分点。这一差距揭示了仅训练阶段的机会：帧级真值可提供当前和未来帧的精确目标裁剪，但部署时不可用。我们提出特权外观迁移追踪（PATT），一种师生训练框架，通过多层级表示预测将这些特权外观传递给可部署追踪器。教师观察过去、当前和未来帧的精确目标裁剪，学生仅接收过去帧模板，并学习预测教师的搜索表示。为避免传递不可靠信号，PATT根据教师相对定位优势和绝对定位精度加权转移过程。训练完成后，教师、隐式预测器、可靠性权重及特权裁剪均被移除，仅保留学生模型进行推理。在七个基准测试中，无论长短期追踪协议，两种模型规模均取得一致提升。
原文摘要 · Abstract (English)
Target templates define what a visual tracker searches for, yet the templates available at inference trade off localization certainty with appearance freshness: the initial ground-truth template is exact but becomes stale, whereas recent templates better reflect the current appearance but are cropped from uncertain predictions. We quantify this bottleneck with a non-deployable oracle that supplies an exact current-frame target crop, improving AUC on LaSOT by 15.2 percentage points. This gap reveals a training-only opportunity: frame-level ground truths provide exact current- and future-frame target crops, although such crops are unavailable at deployment. We introduce Privileged Appearance Transfer for Tracking (PATT), a teacher-student training framework that transfers these privileged appearances to a deployable tracker through multi-level representation prediction. The privileged teacher observes exact target crops from past, current, and future frames, whereas the student receives only past-frame templates and learns to predict the teacher's search representations. To avoid transferring unreliable teacher signals, PATT weights this transfer by the teacher's relative localization advantage over the student and its absolute localization accuracy. After training, the teacher, latent predictor, reliability weights, and privileged crops are removed, leaving standard student-only inference. Across seven benchmarks at two model scales, PATT achieves consistent gains under both long- and short-term tracking protocols.
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。