Quasi-Dense Similarity Learning for Multiple Object Tracking

By Jiangmiao Pang, Linlu Qiu, Xia Li, Haofeng Chen, Qi Li, Trevor Darrell, Fisher Yu. Computer Vision and Pattern Recognition, 2020

488 citations recorded by the source corpus.

Similarity learning has been recognized as a crucial step for object tracking. However, existing multiple object tracking methods only use sparse ground truth matching as the training objective, while ignoring the majority of the informative regions on the images. In this paper, we present Quasi-Dense Similarity Learning, which densely samples hundreds of region proposals on a pair of images for contrastive learning. We can directly combine this similarity learning with existing detection methods to build Quasi-Dense Tracking (QDTrack) without turning to displacement regression or motion priors. We also find that the resulting distinctive feature space admits a simple nearest neighbor search at the inference time. Despite its simplicity, QD-Track outperforms all existing methods on MOT, BDD100K, Waymo, and TAO tracking benchmarks. It achieves 68.7 MOTA at 20.3 FPS on MOT17 without using external training data. Compared to methods with similar detectors, it boosts almost 10 points of MOTA and significantly decreases the number of ID switches on BDD100K and Waymo datasets. Our code and trained models are available at https://github.com/SysCV/qdtrack.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/4586e787deb9ae3230f132d0368a89bb3887af9f

How researchers see this paper

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

In Aerospace Engineering

1. Wenjun Zeng
2. Pei Sun
3. Yifu Zhang
4. Wenyu Liu
5. Jinkun Cao
6. Xinggang Wang
7. Kris M. Kitani
8. Ping Luo

In Computer Vision and Pattern Recognition

1. Kris M. Kitani
2. Xinggang Wang
3. Ping Luo
4. Jinkun Cao
5. Luc Van Gool
6. Song Bai
7. Wenyu Liu
8. Chunhua Shen

Citations in the corpus

• 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.”
• MOTR: End-to-End Multiple-Object Tracking with TRansformer (2021, unknown): “8 / / 18498 160332 3039 QuasiDense (Pang et al. 2021) 66.”
• TrackFormer: Multi-Object Tracking with Transformers (2021, unknown): “7 816 579 18498 160332 3039 QuasiDense [32] – – 68.”
• FairMOT: On the Fairness of Detection and Re-identification in Multiple Object Tracking (2020, methodology): “JointDetection andRe-IDThefirst class ofmethods (Voigtlaender et al. 2019;Wang et al. 2020b; Liang et al. 2020; Pang et al. 2021; Lu et al. 2020) perform object detection and re-ID feature extraction in a single network in order to reduce inference time.”
• DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion (2021, methodology): “Association by pure appearance matching [23] could easily make success on these datasets and we will show that given the perfect detector, the tracking problem on these datasets can be solved by a very naive association strategy, in Section 4.”