Tensor object classification via multilinear discriminant analysis network

TL;DR

This paper introduces MLDANet, a deep learning model designed for classifying multidimensional tensor objects, leveraging multilinear discriminant analysis to improve recognition accuracy over existing methods.

Contribution

The paper proposes a novel multilinear discriminant analysis network (MLDANet) specifically for tensor object classification, combining MLDA with deep learning components.

Findings

MLDANet outperforms PCANet, LDANet, MPCA + LDA, and MLDA on UCF11 dataset.

The model effectively captures tensor data features for improved classification.

Experimental results demonstrate the superiority of MLDANet in recognizing tensor objects.

Abstract

This paper proposes a multilinear discriminant analysis network (MLDANet) for the recognition of multidimensional objects, known as tensor objects. The MLDANet is a variation of linear discriminant analysis network (LDANet) and principal component analysis network (PCANet), both of which are the recently proposed deep learning algorithms. The MLDANet consists of three parts: 1) The encoder learned by MLDA from tensor data. 2) Features maps ob-tained from decoder. 3) The use of binary hashing and histogram for feature pooling. A learning algorithm for MLDANet is described. Evaluations on UCF11 database indicate that the proposed MLDANet outperforms the PCANet, LDANet, MPCA + LDA, and MLDA in terms of classification for tensor objects.