Quasi-Dense Similarity Learning for Multiple Object Tracking

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. Our code and trained models are available at http://vis.xyz/pub/qdtrack.

PDF Abstract CVPR 2021 PDF CVPR 2021 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Multiple Object Tracking BDD100K val QDTrack mMOTA 36.6 # 2
mIDF1 50.8 # 2
Multi-Object Tracking DanceTrack QDTrack HOTA 45.7 # 8
DetA 72.1 # 8
AssA 29.2 # 8
MOTA 83.0 # 9
IDF1 44.8 # 8
Multi-Object Tracking MOT16 QDTrack MOTA 69.8 # 10
IDF1 67.1 # 6
Multi-Object Tracking MOT17 QDTrack MOTA 68.7 # 18
IDF1 66.3 # 17
One-Shot Object Detection PASCAL VOC 2012 val QDTrack MAP 22.1 # 1
Multiple Object Tracking Waymo Open Dataset QDTrack MOTA 55.6 # 1
mAP 49.5 # 1
Category Vehicle # 1


No methods listed for this paper. Add relevant methods here