Quasi-Dense Similarity Learning for Multiple Object Tracking

Jiangmiao Pang, Linlu Qiu, Xia Li, Haofeng Chen, Qi Li, Trevor Darrell, Fisher Yu
CVPR 2021 Oral

Quasi-Dense Similarity Learning for Multiple Object Tracking

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.

Video

Results

Visualization on BDD100K

Quantitative results

BDD100K test set

mMOTAmIDF1ID Sw.
35.552.310790

MOT

DatasetMOTAIDF1ID Sw.MTML
MOT1669.867.11097316150
MOT1768.766.33378957516

Note: Unlike some concurrent works on the MOT dataset, we didn’t use the CrowdHuman dataset for pre-training.

Waymo validation set

CategoryMOTAIDF1ID Sw.
Vehicle55.666.224309
Pedestrian50.358.46347
Cyclist26.245.756
All44.056.830712

TAO

SplitAP50AP75AP
val16.15.07.0
test12.44.55.2

Paper

Code

paper
github.com/SysCV/qdtrack

Citation

@InProceedings{qdtrack,
  title = {Quasi-Dense Similarity Learning for Multiple Object Tracking},
  author = {Pang, Jiangmiao and Qiu, Linlu and Li, Xia and Chen, Haofeng and Li, Qi and Darrell, Trevor and Yu, Fisher},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  month = {June},
  year = {2021}
}

Related


Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation

Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation

NeurIPS 2021 Spotlight We propose Prototypical Cross-Attention Network (PCAN), capable of leveraging rich spatio-temporal information for online multiple object tracking and segmentation.


Tracking Every Thing in the Wild

Tracking Every Thing in the Wild

ECCV 2022 We introduce a new metric, Track Every Thing Accuracy (TETA), and a Track Every Thing tracker (TETer), which performs association using Class Exemplar Matching (CEM).


Video Mask Transfiner for High-Quality Video Instance Segmentation

Video Mask Transfiner for High-Quality Video Instance Segmentation

ECCV 2022 We introduce the HQ-YTVIS dataset as long as Tube-Boundary AP, which provides training, validation and testing support to facilitate future development of VIS methods aiming at higher mask quality.


Video Mask Transfiner for High-Quality Video Instance Segmentation

Video Mask Transfiner for High-Quality Video Instance Segmentation

ECCV 2022 We propose Video Mask Transfiner (VMT) method, capable of leveraging fine-grained high-resolution features thanks to a highly efficient video transformer structure.


SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation

SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation

CVPR 2022 We introduce the largest synthetic dataset for autonomous driving to study continuous domain adaptation and multi-task perception.


Transforming Model Prediction for Tracking

Transforming Model Prediction for Tracking

CVPR 2022 We propose a tracker architecture employing a Transformer-based model prediction module.


Monocular Quasi-Dense 3D Object Tracking

Monocular Quasi-Dense 3D Object Tracking

TPAMI 2022 We combine quasi-dense tracking on 2D images and motion prediction in 3D space to achieve significant advance in 3D object tracking from monocular videos.


BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning

BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning

CVPR 2020 Oral The largest driving video dataset for heterogeneous multitask learning.


Joint Monocular 3D Vehicle Detection and Tracking

Joint Monocular 3D Vehicle Detection and Tracking

ICCV 2019 We propose a novel online framework for 3D vehicle detection and tracking from monocular videos.