Quasi-Dense Similarity Learning for Multiple Object Tracking


METADATA ONLY
Loading...

Date

2021

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

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, QDTrack 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. More info is at https://www.vis.xyz/pub/qdtrack.

Publication status

published

Editor

Book title

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Journal / series

Volume

Pages / Article No.

164 - 173

Publisher

IEEE

Event

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Organisational unit

09688 - Yu, Fisher (ehemalig) / Yu, Fisher (former) check_circle

Notes

Conference lecture on June 21, 2021.

Funding

Related publications and datasets