Quasi-dense Similarity Learning For Multiple Object Tracking
2020 · Jiangmiao Pang, Linlu Qiu, Xia Li, et al.
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 MOT
Authors
(none)
Tags
Stats
Related papers
- Qdtrack: Quasi-dense Similarity Learning For Appearance-only Multiple Object Tracking (2022)15.75
- Smiletrack: Similarity Learning For Occlusion-aware Multiple Object Tracking (2022)17.36
- Deep Similarity Metric Learning For Real-time Pedestrian Tracking (2018)0.00
- Few-shot Object Counting With Similarity-aware Feature Enhancement (2022)18.62
- Mmf-track: Multi-modal Multi-level Fusion For 3D Single Object Tracking (2023)7.16
- DMV: Visual Object Tracking Via Part-level Dense Memory And Voting-based Retrieval (2020)0.00
- Multiple Convolutional Features In Siamese Networks For Object Tracking (2021)7.73
- MFST: Multi-features Siamese Tracker (2021)0.95