We present SDTracker, a method that harnesses the potential of synthetic data for multi-object tracking of real-world scenes in a domain generalization and semi-supervised fashion. First, we use the ImageNet dataset as an auxiliary to randomize the style of synthetic data. With out-of-domain data, we further enforce pyramid consistency loss across different "stylized" images from the same sample to learn domain invariant features. Second, we adopt the pseudo-labeling method to effectively utilize the unlabeled MOT17 training data. To obtain high-quality pseudo-labels, we apply proximal policy optimization (PPO2) algorithm to search confidence thresholds for each sequence. When using the unlabeled MOT17 training set, combined with the pure-motion tracking strategy upgraded via developed post-processing, we finally reach 61.4 HOTA.
@article{arxiv.2303.14653,
title = {SDTracker: Synthetic Data Based Multi-Object Tracking},
author = {Yingda Guan and Zhengyang Feng and Huiying Chang and Kuo Du and Tingting Li and Min Wang},
journal= {arXiv preprint arXiv:2303.14653},
year = {2023}
}