ODMTCNet: An Interpretable Multi-view Deep Neural Network Architecture for Image Feature Representation

2021/10/28 by Gao, Lei, Guo, Zheng, Guan, Ling
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2110.14830

Abstract

This work proposes an interpretable multi-view deep neural network architecture, namely optimal discriminant multi-view tensor convolutional network (ODMTCNet), by integrating statistical machine learning (SML) principles with the deep neural network (DNN) architecture.

Related

• A Battle of Network Structures: An Empirical Study of CNN, Transformer, and MLP
• Multi-Subspace Neural Network for Image Recognition
• A survey of the recent architectures of deep convolutional neural networks
• D-PCN: Parallel Convolutional Networks for Image Recognition via a Discriminator
• Convolutional Neural Networks In Convolution