PCANet-II: When PCANet Meets the Second Order Pooling

Chunxiao FAN  Xiaopeng HONG  Lei TIAN  Yue MING  Matti PIETIKÄINEN  Guoying ZHAO  

IEICE TRANSACTIONS on Information and Systems   Vol.E101-D   No.8   pp.2159-2162
Publication Date: 2018/08/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2017EDL8258
Type of Manuscript: LETTER
Category: Pattern Recognition
second order pooling,  binary feature difference,  face recognition,  pain estimation,  

Full Text: PDF(550.6KB)
>>Buy this Article

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.