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

By Yifu Zhang, Chunyu Wang, Xinggang Wang, Wenjun Zeng, Wenyu Liu. International Journal of Computer Vision, 2020

1,833 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/9cf9b6a1c3bea5dd2079bf599946ec85db9e5673

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

StrongSORT: Make DeepSORT Great Again (2022, methodology): “Extensive experiments demonstrate that they can create notable improvements in StrongSORT and other state-of-the-art trackers, e.g., Center-Track [66], TransTrack [45] and FairMOT [64], with running speeds of 1.7 ms and 7.1 ms per image, respectively, on MOT17.”
TrackFormer: Multi-Object Tracking with Transformers (2021, methodology): “However, we surpass or perform on-par with several modern methods [55,66,68] that were trained on significantly more data, i.”
Deep OC-Sort: Multi-Pedestrian Tracking by Adaptive Re-Identification (2023, methodology): “Since then more methods [11, 12, 13] have improved upon integrating visual information by training discriminative appearance models in an end-to-end manner.”
YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors (2022, background): “For example, multi-object tracking [90, 91], autonomous driving [17, 39], robotics [34, 55], medical image analysis [33, 44], etc.”
BoT-SORT: Robust Associations Multi-Pedestrian Tracking (2022, background): “Recently, several joint trackers [46, 51, 59, 26, 53, 32, 24, 44] have been proposed to train detection and some other components jointly, e.g., motion, embedding, and association models.”
Track to Detect and Segment: An Online Multi-Object Tracker (2021, background): “, the cross-entropy loss LCEembed as in [45, 61].”
Rethinking the Competition Between Detection and ReID in Multiobject Tracking (2020, methodology): “Alternatively, the one-shot methods [7]–[10] integrate detection and ID embedding extraction into a unified framework.”
Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking (2022, background): “Appearancebased object matching [44,70,79] has also become popular, but falls short in many cases, especially when scenes are crowded and objects are represented coarsely (e.”
Quasi-Dense Similarity Learning for Multiple Object Tracking (2020, methodology): “Appearance similarity in MOT To exploit instance appearance similarity to strengthen tracking and re-identify vanished objects, some methods directly use an independent model [2,20,22,29,38,40,45,49] or add an extra embedding head to the detector for end-to-end training [26,44,50,53].”
DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion (2021, methodology): “Motivated by these dataset properties, most recently developed multi-object tracking methods [23, 32, 33, 39] highly rely”