重新思考无人机跟踪中的遮挡建模
Rethinking Occlusion Modeling for UAV Tracking
把遮挡从随机 dropout 重新建模为受空间依赖约束的结构化过程，并用聚类生成密度自适应的遮挡模式做训练增强；同时用深度相关的先验动态调整 Transformer 推理深度，这套「结构化遮挡增广 + 代价感知早退」可直接迁移到其他单流跟踪器或需要部分可见性鲁棒性的检测/分割模型。
原文依据 we introduce Clustered Occlusion Modeling (COM) to generate realistic, density-adaptive occlusion patterns
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论遮挡仍是无人机跟踪中的主要挑战之一，动态视角与复杂环境常常导致目标部分或完全不可见。现有基于 Transformer 的跟踪器通常将遮挡视为随机信息丢弃，忽视了其在真实场景中结构化且具有空间相关性的本质。我们将无人机跟踪中的遮挡建模重新理解为一个由空间依赖关系支配的结构化过程。基于这一洞见，我们提出聚类遮挡建模（Clustered Occlusion Modeling, COM），用于生成真实、密度自适应的遮挡模式，从而增强部分可见条件下的特征鲁棒性。此外，我们设计了代价感知深度偏置（Cost-Aware Depth Bias, CADB），它利用深度相关的先验来调整推理深度，在保持有竞争力精度的同时获得更好的效率。将 COM 与 CADB 集成到统一的单流 Transformer 框架中，我们称之为 OCTrack，该跟踪器在易发生遮挡的环境中实现了鲁棒且高效的无人机跟踪。在多个无人机基准上的大量实验验证了其有效性，并展示了最优的性能。
英文原文摘要 1110 字符
Occlusion remains one of the major challenges in UAV tracking, where dynamic viewpoints and complex environments often cause partial or complete visibility loss.Existing transformer-based trackers typically regard occlusion as random information dropout, overlooking its structured and spatially correlated nature in real-world scenes.We rethink occlusion modeling in UAV tracking as a structured process governed by spatial dependencies.Based on this insight, we introduce Clustered Occlusion Modeling (COM) to generate realistic, density-adaptive occlusion patterns that enhance feature robustness under partial visibility.Furthermore, we design Cost-Aware Depth Bias (CADB), which employs a depth-dependent prior to adjust inference depth, yielding better efficiency while maintaining competitive accuracy.Integrating COM and CADB into a unified single-stream transformer framework, termed OCTrack, our tracker achieves robust and efficient UAV tracking in occlusion-prone environments.Extensive experiments on multiple UAV benchmarks validate its effectiveness and demonstrate state-of-the-art performance.