PCANet-II: When PCANet Meets the Second Order Pooling

TL;DR

PCANet-II enhances the original PCANet by integrating second order pooling, which preserves more discriminative information, reduces feature dimensionality, and improves robustness, addressing limitations of histogram-based pooling.

Contribution

The paper introduces PCANet-II, a shallow network combining second order pooling with PCANet to improve feature discriminability and robustness while reducing output size.

Findings

Second order pooling provides more discriminative features.

PCANet-II reduces feature dimensionality compared to histogram pooling.

Experimental results demonstrate improved robustness and effectiveness.

Abstract

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.