Quasi-Dense Similarity Learning for Multiple Object Tracking
This work addresses the challenge of improving tracking accuracy and reducing ID switches in multiple object tracking for applications such as autonomous driving and surveillance, representing a strong specific gain rather than a foundational shift.
The paper tackles the problem of multiple object tracking by introducing Quasi-Dense Similarity Learning, which densely samples region proposals for contrastive learning, resulting in a method that outperforms existing approaches on benchmarks like MOT17 with 68.7 MOTA at 20.3 FPS and boosts MOTA by almost 10 points on BDD100K and Waymo.
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.