Pyramid Person Matching Network for Person Re-identification

Chaojie Mao, Yingming Li, Zhongfei Zhang, Yaqing Zhang, Xi Li
Proceedings of the Ninth Asian Conference on Machine Learning, PMLR 77:487-497, 2017.

Abstract

In this work, we present a deep convolutional pyramid person matching network (PPMN) with specially designed Pyramid Matching Module to address the problem of person re-identification. The architecture takes a pair of RGB images as input, and outputs a similiarity value indicating whether the two input images represent the same person or not. Based on deep convolutional neural networks, our approach first learns the discriminative semantic representation with the semantic-component-aware features for persons and then employs the Pyramid Matching Module to match the common semantic-components of persons, which is robust to the variation of spatial scales and misalignment of locations posed by viewpoint changes. The above two processes are jointly optimized via a unified end-to-end deep learning scheme. Extensive experiments on several benchmark datasets demonstrate the effectiveness of our approach against the state-of-the-art approaches, especially on the rank-1 recognition rate.

Cite this Paper


BibTeX
@InProceedings{pmlr-v77-mao17a, title = {Pyramid Person Matching Network for Person Re-identification}, author = {Mao, Chaojie and Li, Yingming and Zhang, Zhongfei and Zhang, Yaqing and Li, Xi}, booktitle = {Proceedings of the Ninth Asian Conference on Machine Learning}, pages = {487--497}, year = {2017}, editor = {Zhang, Min-Ling and Noh, Yung-Kyun}, volume = {77}, series = {Proceedings of Machine Learning Research}, address = {Yonsei University, Seoul, Republic of Korea}, month = {15--17 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v77/mao17a/mao17a.pdf}, url = {https://proceedings.mlr.press/v77/mao17a.html}, abstract = {In this work, we present a deep convolutional pyramid person matching network (PPMN) with specially designed Pyramid Matching Module to address the problem of person re-identification. The architecture takes a pair of RGB images as input, and outputs a similiarity value indicating whether the two input images represent the same person or not. Based on deep convolutional neural networks, our approach first learns the discriminative semantic representation with the semantic-component-aware features for persons and then employs the Pyramid Matching Module to match the common semantic-components of persons, which is robust to the variation of spatial scales and misalignment of locations posed by viewpoint changes. The above two processes are jointly optimized via a unified end-to-end deep learning scheme. Extensive experiments on several benchmark datasets demonstrate the effectiveness of our approach against the state-of-the-art approaches, especially on the rank-1 recognition rate.} }
Endnote
%0 Conference Paper %T Pyramid Person Matching Network for Person Re-identification %A Chaojie Mao %A Yingming Li %A Zhongfei Zhang %A Yaqing Zhang %A Xi Li %B Proceedings of the Ninth Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2017 %E Min-Ling Zhang %E Yung-Kyun Noh %F pmlr-v77-mao17a %I PMLR %P 487--497 %U https://proceedings.mlr.press/v77/mao17a.html %V 77 %X In this work, we present a deep convolutional pyramid person matching network (PPMN) with specially designed Pyramid Matching Module to address the problem of person re-identification. The architecture takes a pair of RGB images as input, and outputs a similiarity value indicating whether the two input images represent the same person or not. Based on deep convolutional neural networks, our approach first learns the discriminative semantic representation with the semantic-component-aware features for persons and then employs the Pyramid Matching Module to match the common semantic-components of persons, which is robust to the variation of spatial scales and misalignment of locations posed by viewpoint changes. The above two processes are jointly optimized via a unified end-to-end deep learning scheme. Extensive experiments on several benchmark datasets demonstrate the effectiveness of our approach against the state-of-the-art approaches, especially on the rank-1 recognition rate.
APA
Mao, C., Li, Y., Zhang, Z., Zhang, Y. & Li, X.. (2017). Pyramid Person Matching Network for Person Re-identification. Proceedings of the Ninth Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 77:487-497 Available from https://proceedings.mlr.press/v77/mao17a.html.

Related Material