一、摘要

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 FairMOT which consists of two homogeneous branches to predict pixel-wise objectness scores and re-ID features. The achieved fairness between the tasks allows 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 https://github.com/ifzhang/FairMOT

主要讲了当前模型准确率低的两个原因：
- 将re-ID当做次要的任务
- 使用ROI-Align直接从目标检测得到矩形框提取re-ID特征
提出FairMOT模型，由目标检测分支和re-ID分支组成（像素级别）

二、分析具体原因并提出对应解决问题

2.1 Unfairness Caused by Anchors

虽然基于锚（anchor）的框架在目标检测上能够取到很好的效果，但是在学习re-ID特征上会造成大量的ID switches

忽视re-ID任务：re-ID特征时从目标识别任务得到的矩形框提取的，即re-ID特征的质量很大幅度上依赖于目标识别任务得到的矩形框
**一个矩形框（anchors）包含多个目标：从该矩形框使用ROI-Pool or ROI-Align方法提取出来的特征可能属于干扰对象或背景，会影响检测及re-ID的准确率（**作者提出的解决方法，只从目标的中心提取特征）
**多个矩形框（anchors）包含同个目标：**当图像经历小扰动时，例如，由于数据增加，同一锚可能被迫估计不同的身份

作者的解决方法：使用anchors-free的网络

2.2 Unfairness Caused by Features

之前许多模型中，目标检测分支和re-ID分支共享特征

目标检测分支：需要深层、抽象的特征来推断目标的类别和位置