FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking

4 Apr 2020  ·  Yifu Zhang, Chunyu Wang, Xinggang Wang, Wen-Jun Zeng, Wenyu Liu ·

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.

PDF Abstract

Results from the Paper


 Ranked #1 on Multi-Object Tracking on 2DMOT15 (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Multi-Object Tracking 2DMOT15 FairMOT MOTA 60.6 # 1
Multi-Object Tracking DanceTrack FairMOT HOTA 39.7 # 8
DetA 66.7 # 7
AssA 23.8 # 7
MOTA 82.2 # 7
IDF1 40.8 # 7
Multi-Object Tracking MOT16 FairMOT MOTA 74.9 # 4
Multi-Object Tracking MOT17 FairMOT MOTA 73.7 # 8
IDF1 72.3 # 6
Multi-Object Tracking MOT20 FairMOT MOTA 61.8 # 8
IDF1 67.3 # 7
Object Tracking PathTrack FairMOT MOTA 44.9 # 1

Methods