A part power set model for scale-free person retrieval

Shen，Yunhang1; Ji，Rongrong1,2; Hong，Xiaopeng3,4; Zheng，Feng5; Guo，Xiaowei6; Wu，Yongjian6; Huang，Feiyue6

10.24963/ijcai.2019/471

2019

1045-0823

IJCAI International Joint Conference on Artificial Intelligence

2019-August

3397-3403

Recently, person re-identification (re-ID) has attracted increasing research attention, which has broad application prospects in video surveillance and beyond. To this end, most existing methods highly relied on well-aligned pedestrian images and hand-engineered part-based model on the coarsest feature map. In this paper, to lighten the restriction of such fixed and coarse input alignment, an end-to-end part power set model with multi-scale features is proposed, which captures the discriminative parts of pedestrians from global to local, and from coarse to fine, enabling part-based scale-free person re-ID. In particular, we first factorize the visual appearance by enumerating k-combinations for all k of n body parts to exploit rich global and partial information to learn discriminative feature maps. Then, a combination ranking module is introduced to guide the model training with all combinations of body parts, which alternates between ranking combinations and estimating an appearance model. To enable scale-free input, we further exploit the pyramid architecture of deep networks to construct multi-scale feature maps with a feasible amount of extra cost in term of memory and time. Extensive experiments on the mainstream evaluation datasets, including Market-1501, DukeMTMC-reID and CUHK03, validate that our method achieves the state-of-the-art performance.

Others

English

Key Technologies Research and Development Program[2016YFB1001503];Key Technologies Research and Development Program[2017J01125];Key Technologies Research and Development Program[2017M612134];Key Technologies Research and Development Program[2017YFC0113000];Key Technologies Research and Development Program[2018J01106];Key Technologies Research and Development Program[61572410];Key Technologies Research and Development Program[61772443];Key Technologies Research and Development Program[U1705262];

2-s2.0-85074923274

Scopus

1.Fujian Key Laboratory of Sensing and Computing for Smart City,School of Information Science and Engineering,Xiamen University,361005,China
2.Peng Cheng Laborotory,China
3.Xi'an Jiaotong University,China
4.University of Oulu,Finland
5.Southern University of Science and Technology,China
6.Tencent Youtu Lab,Tencent Technology (Shanghai) Co.,Ltd,

Shen，Yunhang,Ji，Rongrong,Hong，Xiaopeng,et al. A part power set model for scale-free person retrieval[C],2019:3397-3403.