Dictionary Learning with Iterative Laplacian Regularisation for Unsupervised Person Re-identification

Elyor Kodirov, Tao Xiang and Shaogang Gong

Abstract

Many existing approaches to person re-identification (Re-ID) are based on supervised learning, which requires hundreds of matching pairs to be labelled for each pair of cameras. This severely limits their scalability for real-world applications. This work aims to overcome this limitation by developing a novel unsupervised Re-ID approach. The approach is based on a new dictionary learning for sparse coding formulation with a graph Laplacian regularisation term whose value is set iteratively. As an unsupervised model, the dictionary learning model is well-suited to the unsupervised task, whilst the regularisation term enables the exploitation of cross-view identity-discriminative information ignored by existing unsupervised Re-ID methods. Importantly this model is also flexible in utilising any labelled data if available. Experiments on two benchmark datasets demonstrate that the proposed approach significantly outperforms the state-of-the-arts.

Session

Poster 1

Files

Extended Abstract (PDF, 102K)
Paper (PDF, 239K)

DOI

10.5244/C.29.44
https://dx.doi.org/10.5244/C.29.44

Citation

Bibtex

@inproceedings{BMVC2015_44,
	title={Dictionary Learning with Iterative Laplacian  Regularisation for Unsupervised Person Re-identification},
	author={Elyor Kodirov and Tao Xiang and Shaogang Gong},
	year={2015},
	month={September},
	pages={44.1-44.12},
	articleno={44},
	numpages={12},
	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.29.44},
	isbn={1-901725-53-7},
	url={https://dx.doi.org/10.5244/C.29.44}
}