只在困难帧调用高精度模型，提升多目标跟踪效率与准确率
Selective Mask Propagation for Multi-Object Tracking
- 仅在基线跟踪器不确定时触发视频分割模型，降低计算开销
- 在DanceTrack上显著提升3种基线追踪器性能，在SportsMOT达87.2 HOTA
- 无需训练、可兼容任意基线模型和更优分割组件，适合实际部署
在多目标跟踪中，多数帧对轻量级基线追踪器而言容易处理，而少数帧本质困难。视频对象分割（VOS）模型可在基线追踪失败的困难帧中保持身份一致性，但计算与内存开销较大。本文提出选择性掩码传播：仅当分配不确定性信号触发时，才从基线追踪器切换至VOS模型。只有当VOS模型做出置信度高的矛盾预测时，才修正基线输出；弱或不明确预测则保留基线结果。该方法无需训练，将基线追踪器和VOS模型视为黑箱，且可通过替换更强大的分割模型获益。在DanceTrack上，选择性掩码传播显著提升了三种不同基线追踪器的表现。在SportsMOT上，采用SAM 3-Deep-EIoU结合全局轨迹关联的方法，在基准测试中达到87.2 HOTA，为当前最优水平。
原文摘要 · Abstract (English)
In multi-object tracking, most frames are easy for a lightweight base tracker while a small fraction is intrinsically hard. Video object segmentation (VOS) models can often preserve identity through the hard frames where the base tracker fails, but they are much more expensive in compute and memory. We propose selective mask propagation, a tracking algorithm that dispatches from a base tracker to a VOS model only on windows where an assignment-uncertainty signal fires. The base tracker's output is modified only when the VOS model makes a confident prediction that contradicts the base tracker's identity assignment; weak or inconclusive predictions preserve the base output. The method is training-free, treats both the base tracker and the VOS model as black boxes, and can benefit from replacing the VOS component with a more capable model. On DanceTrack, selective mask propagation significantly improves three different base trackers. On SportsMOT, where identity preservation is central to sports analytics, SAM 3-Deep-EIoU with global track association achieves state-of-the-art performance on the benchmark with 87.2 HOTA.
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。