Deep Reinforcement Learning Attention Selection For Person Re-Identification

XU LAN, HangXiao Wang, Shaogang Gong and Xiatian Zhu

Abstract

Existing person re-identification (re-id) methods assume the provision of accurately cropped person bounding boxes with minimum background noise, mostly by manually cropping. This is significantly breached in practice when person bounding boxes must be detected automatically given a very large number of images and/or videos processed. Compared to carefully cropped manually, auto-detected bounding boxes are far less accurate with random amount of background clutter which can degrade notably person re-id matching accuracy. In this work, we develop a joint learning deep model that optimises person re-id attention selection within any auto-detected person bounding boxes by reinforcement learning of background clutter minimisation subject to re-id label pairwise constraints. Specifically, we formulate a novel unified re-id architecture called Identity DiscriminativE Attention reinforcement Learning (IDEAL) to accurately select re-id attention in auto-detected bounding boxes for optimising re-id performance. Our model can improve re-id accuracy comparable to that from exhaustive human manual cropping of bounding boxes with additional advantages from identity discriminative attention selection that specially benefits re-id tasks beyond human knowledge.

Session

Posters

Files

PDF iconPaper (PDF)

DOI

10.5244/C.31.121
https://dx.doi.org/10.5244/C.31.121

Citation

XU LAN, HangXiao Wang, Shaogang Gong and Xiatian Zhu. Deep Reinforcement Learning Attention Selection For Person Re-Identification. In T.K. Kim, S. Zafeiriou, G. Brostow and K. Mikolajczyk, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 121.1-121.16. BMVA Press, September 2017.

Bibtex

            @inproceedings{BMVC2017_121,
                title={Deep Reinforcement Learning Attention Selection For Person Re-Identification},
                author={XU LAN, HangXiao Wang, Shaogang Gong and Xiatian Zhu},
                year={2017},
                month={September},
                pages={121.1-121.16},
                articleno={121},
                numpages={16},
                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.31.121},
                isbn={1-901725-60-X},
                url={https://dx.doi.org/10.5244/C.31.121}
            }