Highly Efficient Regression for Scalable Person Re-Identification

Hanxiao Wang, Shaogang Gong and Tao Xiang

Abstract

Existing person re-identification models are poor for scaling up to large data required in real-world applications due to: (1) Complexity: They employ complex models for optimal performance resulting in high computational cost for training at a large scale; (2) Inadaptability: Once trained, they are unsuitable for incremental update to incorporate any new data available. This work proposes a truly scalable solution to re-id by addressing both problems. Specifically, a Highly Efficient Regression (HER) model is formulated by embedding the Fisher's criterion to a ridge regression model for very fast re-id model learning with scalable memory/storage usage. Importantly, this new HER model supports faster than real-time incremental model updates therefore making real-time active learning feasible in re-id with human-in-the-loop. Extensive experiments show that such a simple and fast model not only outperforms notably the state-of-the-art re-id methods, but also is more scalable to large data with additional benefits to active learning for reducing human labelling effort in re-id deployment.

Session

Face and Gesture

Files

Extended Abstract (PDF, 168K)
Paper (PDF, 420K)

DOI

10.5244/C.30.134
https://dx.doi.org/10.5244/C.30.134

Citation

Bibtex

        @inproceedings{BMVC2016_134,
        	title={Highly Efficient Regression for Scalable Person Re-Identification},
        	author={Hanxiao Wang, Shaogang Gong and Tao Xiang},
        	year={2016},
        	month={September},
        	pages={134.1-134.14},
        	articleno={134},
        	numpages={14},
        	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
        	publisher={BMVA Press},
        	editor={Richard C. Wilson, Edwin R. Hancock and William A. P. Smith},
        	doi={10.5244/C.30.134},
        	isbn={1-901725-59-6},
        	url={https://dx.doi.org/10.5244/C.30.134}
        }