[论文解读] A Simple Baseline for Multi-Object Tracking.

Yifu Zhang, Chunyu Wang+3 more|arXiv (Cornell University)|Apr 4, 2020

Video Surveillance and Tracking Methods参考文献 25被引用 76

一句话总结

FairMOT 通过两个同构分支联合优化目标检测与重识别（re-ID），提出了一种简单但高效的单网络多目标跟踪方法。通过确保任务间的公平性，并用更鲁棒的特征提取方法替代 ROI-Align，FairMOT 在多个基准上实现了最先进性能，显著减少了身份切换，并优于先前方法。

ABSTRACT

There has been remarkable progress on object detection and re-identification (re-ID) in recent years which are the key components of multi-object tracking. However, little attention has been focused on jointly accomplishing the two tasks in a single network. Our study shows that the previous attempts ended up with degraded accuracy mainly because the re-ID task is not fairly learned which causes many identity switches. The unfairness lies in two-fold: (1) they treat re-ID as a secondary task whose accuracy heavily depends on the primary detection task. So training is largely biased to the detection task but ignores the re-ID task; (2) they use ROI-Align to extract re-ID features which is directly borrowed from object detection. However, this introduces a lot of ambiguity in characterizing objects because many sampling points may belong to disturbing instances or background. To solve the problems, we present a simple approach \emph{FairMOT} which consists of two homogeneous branches to predict pixel-wise objectness scores and re-ID features. The achieved fairness between the tasks allows \emph{FairMOT} to obtain high levels of detection and tracking accuracy and outperform previous state-of-the-arts by a large margin on several public datasets. The source code and pre-trained models are released at this https URL.

研究动机与目标

• 解决多目标跟踪中检测与重识别任务之间训练不平衡的问题。
• 减少因重识别任务学习不公平导致的身份切换。
• 通过用更鲁棒的方法替代 ROI-Align，消除重识别特征提取中的歧义。
• 设计一个具有同构分支的统一网络，用于检测与重识别，以提升任务公平性。
• 在不使用复杂架构或后处理的情况下，实现最先进水平的跟踪精度。

提出的方法

• FairMOT 使用单个网络，包含两个同构分支：一个用于预测像素级目标性分数，另一个用于预测重识别特征。
• 重识别分支采用一种避免 ROI-Align 引入歧义的特征提取方法，后者可能从背景或干扰物中采样点。
• 网络通过一个平衡的损失函数进行端到端训练，公平地加权检测与重识别目标。
• 直接使用特征图进行重识别，无需依赖区域建议，减少噪声并提升特征一致性。
• 该方法避免使用额外的头部网络或复杂后处理，保持简洁与高效。
• 训练策略确保重识别任务并非次要，而是在优化过程中与检测任务同等优先。

实验结果

研究问题

• RQ1 当检测与重识别任务均被公平优化时，联合学习对跟踪性能有何影响？
• RQ2 用更鲁棒的特征提取方法替代 ROI-Align 对重识别准确率与身份一致性有何影响？
• RQ3 能否通过一种简单、单分支架构在多目标跟踪中实现最先进性能，而无需复杂组件？
• RQ4 为何先前方法尽管检测精度高，仍存在较高的身份切换率？
• RQ5 任务公平性在端到端多目标跟踪中在多大程度上提升了重识别性能？

主要发现

• FairMOT 在多个公开多目标跟踪基准上实现了最先进性能，优于先前的 SOTA 方法。
• 通过确保检测与重识别任务之间的公平学习，该方法显著减少了身份切换。
• 用更鲁棒的特征提取策略替代 ROI-Align，提升了重识别特征的质量与一致性。
• 为检测与重识别设计同构分支，带来了更优的优化与性能。
• 该模型在检测与重识别两方面均实现了高精度，且无需复杂后处理或辅助网络。
• 源代码与预训练模型已公开发布，支持可复现性与进一步研究。