Divide and Fuse: A Re-ranking Approach for Person Re-identification

Rui Yu, Zhichao Zhou, Song Bai and Xiang Bai

Abstract

As re-ranking is a necessary procedure to boost person re-identification (re-ID) performance on large-scale datasets, the diversity of feature becomes crucial to person reID for its importance both on designing pedestrian descriptions and re-ranking based on feature fusion. However, in many circumstances, only one type of pedestrian feature is available. In this paper, we propose a “Divide and Fuse” re-ranking framework for person re-ID. It exploits the diversity from different parts of a high-dimensional feature vector for fusion-based re-ranking, while no other features are accessible. Specifically, given an image, the extracted feature is divided into sub-features. Then the contextual information of each sub-feature is iteratively encoded into a new feature. Finally, the new features from the same image are fused into one vector for re-ranking. Experimental results on two person re-ID benchmarks demonstrate the effectiveness of the proposed framework.

Session

Posters

Files

Paper (PDF)

DOI

10.5244/C.31.135
https://dx.doi.org/10.5244/C.31.135

Citation

Bibtex

            @inproceedings{BMVC2017_135,
                title={Divide and Fuse: A Re-ranking Approach for Person Re-identification},
                author={Rui Yu, Zhichao Zhou, Song Bai and Xiang Bai},
                year={2017},
                month={September},
                pages={135.1-135.13},
                articleno={135},
                numpages={13},
                booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
                publisher={BMVA Press},
                editor={Tae-Kyun Kim, Stefanos Zafeiriou, Gabriel Brostow and Krystian Mikolajczyk},
                doi={10.5244/C.31.135},
                isbn={1-901725-60-X},
                url={https://dx.doi.org/10.5244/C.31.135}
            }