Share Email Print
cover

Proceedings Paper • new

Channel convolution residual block for person re-identification
Author(s): Zhengxin Zeng; Zhuqing Jiang; Aidong Men; Guodong Ju
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In previous works, the channel attention mechanism has been widely used in person re-identification. However, the channel attention mechanism completely compresses the spatial dimension during calculation, which harms the diversity of the channel information over different pixels. In this paper, a channel convolution residual block is proposed for more detailed inter-channel correlation modeling. First, we preserve spatial context information when introducing the channel dependency, which enables pixel-wise inter-channel correlation modeling. At the same time, a bottleneck strategy is used to reduce parameters in the spatial dimension. Second, the channel convolution instead of the fully connected layer is employed to reduce the parameters in the channel dimension. In addition, the inter-channel correlation is merged into the backbone network directly in the form of residual, and thus the block can be embedded in any deep neural networks. Experiments on Market1501 and DukeMTMC-ReID datasets demonstrate that the channel convolution residual block improves the accuracy of person re-identification task effectively.

Paper Details

Date Published: 3 January 2020
PDF: 6 pages
Proc. SPIE 11373, Eleventh International Conference on Graphics and Image Processing (ICGIP 2019), 113730B (3 January 2020); doi: 10.1117/12.2557238
Show Author Affiliations
Zhengxin Zeng, Beijing Univ. of Posts and Telecommunications (China)
Zhuqing Jiang, Beijing Univ. of Posts and Telecommunications (China)
Aidong Men, Beijing Univ. of Posts and Telecommunications (China)
Guodong Ju, GuangDong TUS-TuWei Technology Co., Ltd. (China)


Published in SPIE Proceedings Vol. 11373:
Eleventh International Conference on Graphics and Image Processing (ICGIP 2019)
Zhigeng Pan; Xun Wang, Editor(s)

© SPIE. Terms of Use
Back to Top