Horizontal Pyramid Matching for Person Re-identification

By Yang Fu, Yunchao Wei, Yuqian Zhou, Humphrey Shi, Gao Huang, Xinchao Wang, Zhiqiang Yao, Thomas S. Huang. AAAI Conference on Artificial Intelligence, 2018

505 citations recorded by the source corpus.

Despite the remarkable progress in person re-identification (Re-ID), such approaches still suffer from the failure cases where the discriminative body parts are missing. To mitigate this type of failure, we propose a simple yet effective Horizontal Pyramid Matching (HPM) approach to fully exploit various partial information of a given person, so that correct person candidates can be identified even if some key parts are missing. With HPM, we make the following contributions to produce more robust feature representations for the Re-ID task: 1) we learn to classify using partial feature representations at different horizontal pyramid scales, which successfully enhance the discriminative capabilities of various person parts; 2) we exploit average and max pooling strategies to account for person-specific discriminative information in a global-local manner. To validate the effectiveness of our proposed HPM method, extensive experiments are conducted on three popular datasets including Market-1501, DukeMTMCReID and CUHK03. Respectively, we achieve mAP scores of 83.1%, 74.5% and 59.7% on these challenging benchmarks, which are the new state-of-the-arts.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/c2a5f27d97744bc1f96d7e1074395749e3c59bc8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

1. Yi Yang
2. Tao A. Xiang
3. Zhedong Zheng
4. Kaiyang Zhou
5. Cuiling Lan
6. Wenjun Zeng
7. Zhibo Chen
8. Xin Jin

In Computer Vision and Pattern Recognition

1. Tao A. Xiang
2. Yi Yang
3. Luc Van Gool
4. Xiaogang Wang
5. Yu Qiao
6. Yongxin Yang
7. Dacheng Tao
8. Chen Change Loy

Citations in the corpus

• Pose-Guided Feature Alignment for Occluded Person Re-Identification (2019, methodology): “However, the methods proposed in those previous works [31, 13, 32, 38, 24, 42] did not consider a situation that the target person is occluded by various obstructions like cars, trees, or other people.”
• High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification (2020, methodology): “Following the ideas above and inspired by recent developments on person ReID [43, 35, 24, 4] and human key-points prediction [2, 33], we utilize a CNN backbone to extract local features of different key-points.”
• Each Part Matters: Local Patterns Facilitate Cross-View Geo-Localization (2020, background): “Currently, some state-of-the-art works [42], [43], [44], [45] extend the PCB with more partitions or optimization losses.”
• GaitSet: Regarding Gait as a Set for Cross-View Gait Recognition (2018, methodology): “(Fu et al. 2018) proposed Horizontal Pyramid Pooling (HPP) to deal with it.”
• Style Normalization and Restitution for Generalizable Person Re-Identification (2020, methodology): “LReID denotes the widely-used ReID Loss (classification loss [39, 7], and triplet loss with batch hard mining [11]) on the ReID feature vectors.”
• Omni-Scale Feature Learning for Person Re-Identification (2019, methodology): “To exploit the upright body pose, [47, 71, 9, 55] add auxiliary supervision signals to features pooled horizontally from the last convolutional feature maps.”