论文标题
FAIRMOT：关于多个对象跟踪中检测和重新识别的公平性
FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking
论文作者
论文摘要
多对象跟踪（MOT）是计算机视觉中的重要问题，具有广泛的应用程序。在单个网络中以多任务的学习为对象检测和重新ID的多任务学习很有吸引力，因为它允许对这两个任务进行联合优化并具有较高的计算效率。但是，我们发现这两个任务倾向于相互竞争，需要仔细解决。特别是，以前的作品通常将重新ID视为次要任务，其准确性受主要检测任务的影响很大。结果，网络偏向主要检测任务，这对重新ID任务不公平。为了解决该问题，我们提出了一种基于无锚对象检测体系结构的简单而有效的方法，称为Fairmot。请注意，这不是百分之股和重新ID的幼稚组合。取而代之的是，我们提出了许多详细的设计，这些设计对于通过彻底的经验研究获得良好的跟踪结果至关重要。最终的方法可在检测和跟踪方面具有很高的精度。该方法在几个公共数据集上的优于最先进的方法。源代码和预培训模型将在https://github.com/ifzhang/fairmot上发布。
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.
