The principal component analysis network (PCANet) is an unsupervised parsimonious deep network, utilizing principal components as filters in its convolution layers. Albeit powerful, the PCANet consists of basic operations such as principal components and spatial pooling, which suffers from two fundamental problems. First, the principal components obtain information by transforming it to column vectors (which we call the amalgamated view), which incurs the loss of the spatial information in the data. Second, the generalized spatial pooling utilized in the PCANet induces feature redundancy and also fails to accommodate spatial statistics of natural images. In this research, we first propose a tensor-factorization based deep network called the Tensor Factorization Network (TFNet). The TFNet extracts features from the spatial structure of the data (which we call the minutiae view). We then show that the information obtained by the PCANet and the TFNet are distinctive and non-trivial but individually insufficient. This phenomenon necessitates the development of proposed HybridNet, which integrates the information discovery with the two views of the data. To enhance the discriminability of hybrid features, we propose Attn-HybridNet, which alleviates the feature redundancy by performing attention-based feature fusion. The significance of our proposed Attn-HybridNet is demonstrated on multiple real-world datasets where the features obtained with Attn-HybridNet achieves better classification performance over other popular baseline methods, demonstrating the effectiveness of the proposed technique.

翻译：主要组成部分分析网络(PCANet)是一个无人监督的深层网络,利用主要组成部分作为其交错层的过滤器。尽管这个网络很强大,但它由主要组成部分和空间共享等基本操作组成,这有两个根本性问题。首先,主要组成部分通过将信息转换成柱矢量来获取信息(我们称之为组合式视图),从而造成数据中空间信息的损失。第二,在CCANet中使用的普遍空间共享造成冗余,也无法容纳自然图像的空间统计。在这项研究中,我们首先提议以深网络为基础,称为Tensor集成网络(TFNet)。TFNet从数据的空间结构(我们称之为光观)中提取了特征特征特征特征特征(我们称之为“光观” ) 。然后我们表明,由CCANet和TFNet获得的信息是独特和非细微的,但个别的不够充分。这个现象需要开发拟议的混合网络,将信息发现与数据的两个观点结合起来。为了提高基于混合网络的特性的可辨别性能性能,我们提议在Atstria-tredistria-strial drib distrain laction ex-destrain extistrain ex-destrevent extigradudududustrat-st extidududududududududustr