PCANet-II: When PCANet Meets the Second Order Pooling

被引:8
作者
Fan, Chunxiao [1 ]
Hong, Xiaopeng [2 ]
Tian, Lei [1 ,2 ]
Ming, Yue [1 ]
Pietikainen, Matti [2 ]
Zhao, Guoying [2 ]
机构
[1] Beijing Univ Posts & Telecommun, Beijing, Peoples R China
[2] Univ Oulu, Ctr Machine Vis & Signal Anal, Oulu, Finland
基金
中国国家自然科学基金; 芬兰科学院;
关键词
second order pooling; binary feature difference; face recognition; pain estimation; LOCAL BINARY PATTERNS; BASE-LINE; FACE;
D O I
10.1587/transinf.2017EDL8258
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
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.
引用
收藏
页码:2159 / 2162
页数:4
相关论文
共 20 条
[11]   Learning Stacked Image Descriptor for Face Recognition [J].
Lei, Zhen ;
Yi, Dong ;
Li, Stan Z. .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2016, 26 (09) :1685-1696
[12]   Learning Discriminant Face Descriptor [J].
Lei, Zhen ;
Pietikainen, Matti ;
Li, Stan Z. .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2014, 36 (02) :289-302
[13]   Bilinear CNN Models for Fine-grained Visual Recognition [J].
Lin, Tsung-Yu ;
RoyChowdhury, Aruni ;
Maji, Subhransu .
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, :1449-1457
[14]   Extended local binary patterns for face recognition [J].
Liu, Li ;
Fieguth, Paul ;
Zhao, Guoying ;
Pietikainen, Matti ;
Hu, Dewen .
INFORMATION SCIENCES, 2016, 358 :56-72
[15]   Joint Feature Learning for Face Recognition [J].
Lu, Jiwen ;
Liong, Venice Erin ;
Wang, Gang ;
Moulin, Pierre .
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2015, 10 (07) :1371-1383
[16]  
Lucey P., 2011, Proceedings 2011 IEEE International Conference on Automatic Face & Gesture Recognition (FG 2011), P57, DOI 10.1109/FG.2011.5771462
[17]   Learning iterative quantization binary codes for face recognition [J].
Tian, Lei ;
Fan, Chunxiao ;
Ming, Yue .
NEUROCOMPUTING, 2016, 214 :629-642
[18]   Pedestrian detection via classification on Riemannian manifolds [J].
Tuzel, Oncel ;
Porikli, Fatih ;
Meer, Peter .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2008, 30 (10) :1713-1727
[19]   A Discriminative Feature Learning Approach for Deep Face Recognition [J].
Wen, Yandong ;
Zhang, Kaipeng ;
Li, Zhifeng ;
Qiao, Yu .
COMPUTER VISION - ECCV 2016, PT VII, 2016, 9911 :499-515
[20]   Leveraging Semantic Links for High Efficiency Page-Level FTL Design [J].
Zhou, Jian ;
Chen, Xunchao ;
Wang, Jun ;
Wu, Fei ;
Zhou, You ;
Xie, Changsheng .
2016 IEEE 36TH INTERNATIONAL CONFERENCE ON DISTRIBUTED COMPUTING SYSTEMS WORKSHOPS (ICDCSW 2016), 2016, :84-89