FairMOT：多目标跟踪中检测与重识别的公平性
FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking
摘要：
多目标跟踪（MOT）是计算机视觉中的一个重要问题，有着广泛的应用。将MOT公式化为单个网络中的目标检测和re-ID的多任务学习是有吸引力的，因为它允许两个任务的联合优化并且具有高计算效率。然而，我们发现，这两项任务往往相互竞争，需要认真解决。特别是，以前的作品通常把重新识别作为一个次要的任务，其准确性是严重影响的主要检测任务。结果，网络偏向于主要检测任务，这对重新识别任务不公平。为了解决这个问题，我们提出了一个简单而有效的方法，称为FairMOT的基础上无锚目标检测架构CenterNet。请注意，它不是CenterNet和re-ID的天真组合。相反，我们提出了一系列详细的设计，这些设计对于通过彻底的实证研究实现良好的跟踪结果至关重要。所得到的方法实现了高精度的检测和跟踪。该方法在几个公共数据集上的性能大大优于最先进的方法。源代码和预训练的模型在https://github.com/ifzhang/FairMOT上发布。
英文摘要：
Multi-object tracking (MOT) is an important problem in computer vision which has a wide range of applications. Formulating MOT as multi-task learning of object detection and re-ID in a single network is appealing since it allows joint optimization of the two tasks and enjoys high computation efficiency. However, we find that the two tasks tend to compete with each other which need to be carefully addressed. In particular, previous works usually treat re-ID as a secondary task whose accuracy is heavily affected by the primary detection task. As a result, the network is biased to the primary detection task which is not fair to the re-ID task. To solve the problem, we present a simple yet effective approach termed as FairMOT based on the anchor-free object detection architecture CenterNet. Note that it is not a naive combination of CenterNet and re-ID. Instead, we present a bunch of detailed designs which are critical to achieve good tracking results by thorough empirical studies. The resulting approach achieves high accuracy for both detection and tracking. The approach outperforms the state-of-the-art methods by a large margin on several public datasets. The source code and pre-trained models are released at https://github.com/ifzhang/FairMOT.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
