University of Oulu

FAN, C., HONG, X., TIAN, L., MING, Y., PIETIKÄINEN, M., ZHAO, G. (2018) PCANet-II: When PCANet Meets the Second Order Pooling. IEICE Transactions on Information and Systems, E101.D (8), 2159-2162. doi:10.1587/transinf.2017EDL8258

PCANet-II : when PCANet meets the second order pooling

Saved in:
Author: Fan, Chunxiao1; Hong, Xiaopeng2; Tian, Lei1,2;
Organizations: 1Beijing University of Posts and Telecommunications
2The Center for Machine Vision and Signal Analysis, University of Oulu
Format: article
Version: published version
Access: open
Online Access: PDF Full Text (PDF, 0.5 MB)
Persistent link:
Language: English
Published: Institute of Electronics, Information and Communication Engineers, 2018
Publish Date: 2019-03-01


PCANet, as one noticeable shallow network, employs the histogram representation for feature pooling. However, there are three main problems about this kind of pooling method. First, the histogram-based pooling method binarizes the feature maps and leads to inevitable discriminative information loss. Second, it is difficult to effectively combine other visual cues into a compact representation, because the simple concatenation of various visual cues leads to feature representation inefficiency. Third, the dimensionality of histogram-based output grows exponentially with the number of feature maps used. In order to overcome these problems, we propose a novel shallow network model, named as PCANet-II. Compared with the histogram-based output, the second order pooling not only provides more discriminative information by preserving both the magnitude and sign of convolutional responses, but also dramatically reduces the size of output features. Thus we combine the second order statistical pooling method with the shallow network, i.e., PCANet. Moreover, it is easy to combine other discriminative and robust cues by using the second order pooling. So we introduce the binary feature difference encoding scheme into our PCANet-II to further improve robustness. Experiments demonstrate the effectiveness and robustness of our proposed PCANet-II method.

see all

Series: IEICE transactions on information and systems
ISSN: 0916-8532
ISSN-E: 1745-1361
ISSN-L: 0916-8532
Volume: E101.D
Issue: 8
Pages: 2159 - 2162
DOI: 10.1587/transinf.2017EDL8258
Type of Publication: A1 Journal article – refereed
Field of Science: 113 Computer and information sciences
Funding: This work was supported by the BUPT Excellent Ph.D. Students Foundation CX2016304, the National Natural Science Foundation of China (No. NSFC-61402046, 61572205), the Academy of Finland, Infotech Oulu, and Tekes Fidipro Program.
Copyright information: © 2018 The Institute of Electronics, Information and Communication Engineers. Published in this repository with the kind permission of the publisher.