Share Email Print
cover

Proceedings Paper • new

Good practices on building effective CNN baseline model for person re-identification
Author(s): Fu Xiong; Yang Xiao; Zhiguo Cao; Kaicheng Gong; Zhiwen Fang; Joey Tianyi Zhou
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Person re-identification is indeed a challenging visual recognition task due to the critical issues of human pose variation, human body occlusion, camera view variation, etc. To address this, most of the state-of-the-art approaches are proposed based on deep convolutional neural network (CNN), being leveraged by its strong feature learning power and classification boundary fitting capacity. Although the vital role towards person re-identification, how to build effective CNN baseline model has not been well studied yet. To answer this open question, we propose 3 good practices in this paper from the perspectives of adjusting CNN architecture and training procedure. In particular, they are adding batch normalization after the global pooling layer, executing identity categorization directly using only one fully-connected layer, and using Adam as optimizer. The extensive experiments on 3 widely-used benchmark datasets demonstrate that, our propositions essentially facilitate the CNN baseline model to achieve the state-of-the-art performance without any other high-level domain knowledge or low-level technical trick.

Paper Details

Date Published: 6 May 2019
PDF: 11 pages
Proc. SPIE 11069, Tenth International Conference on Graphics and Image Processing (ICGIP 2018), 110690I (6 May 2019); doi: 10.1117/12.2524386
Show Author Affiliations
Fu Xiong, Huazhong Univ. of Science and Technology (China)
Yang Xiao, Huazhong Univ. of Science and Technology (China)
Zhiguo Cao, Huazhong Univ. of Science and Technology (China)
Kaicheng Gong, Huazhong Univ. of Science and Technology (China)
Zhiwen Fang, Hunan Univ. of Humanities, Science and Technology (China)
Joey Tianyi Zhou, A*STAR Institute of High Performance Computing (Singapore)


Published in SPIE Proceedings Vol. 11069:
Tenth International Conference on Graphics and Image Processing (ICGIP 2018)
Chunming Li; Hui Yu; Zhigeng Pan; Yifei Pu, Editor(s)

© SPIE. Terms of Use
Back to Top