Online Domain Adaptation for Multi-Object Tracking

Adrien Gaidon and Eleonora Vig

Abstract

Automatically detecting, labeling, and tracking objects in videos depends first and foremost on accurate category-level object detectors. These might, however, not always be available in practice, as acquiring high-quality large scale labeled training datasets is either too costly or impractical for all possible real-world application scenarios. A scalable solution consists in re-using object detectors pre-trained on generic datasets. This work is the first to investigate the problem of on-line domain adaptation of object detectors for causal multi-object tracking (MOT). We propose to alleviate the dataset bias by adapting detectors from category to instances, and back: (i) we jointly learn all target models by adapting them from the pre-trained one, and (ii) we also adapt the pre-trained model on-line. We introduce an on-line multi-task learning algorithm to efficiently share parameters and reduce drift, while gradually improving recall. Our approach is applicable to any linear object detector, and we evaluate both cheap 'mini-Fisher Vectors' and expensive 'off-the-shelf' ConvNet features. We quantitatively measure the benefit of our domain adaptation strategy on the KITTI tracking benchmark and on a new dataset (PASCAL-to-KITTI) we introduce to study the domain mismatch problem in MOT.

Session

Tracking

Files

Extended Abstract (PDF, 1115K)
Paper (PDF, 2M)

DOI

10.5244/C.29.3
https://dx.doi.org/10.5244/C.29.3

Citation

Bibtex

@inproceedings{BMVC2015_3,
	title={Online Domain Adaptation for Multi-Object Tracking},
	author={Adrien Gaidon and Eleonora Vig},
	year={2015},
	month={September},
	pages={3.1-3.13},
	articleno={3},
	numpages={13},
	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
	publisher={BMVA Press},
	editor={Xianghua Xie, Mark W. Jones, and Gary K. L. Tam},
	doi={10.5244/C.29.3},
	isbn={1-901725-53-7},
	url={https://dx.doi.org/10.5244/C.29.3}
}