English

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

Computer Vision and Pattern Recognition 2021-10-29 v1

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.

Keywords

Cite

@article{arxiv.2110.14830,
  title  = {ODMTCNet: An Interpretable Multi-view Deep Neural Network Architecture for Image Feature Representation},
  author = {Lei Gao and Zheng Guo and Ling Guan},
  journal= {arXiv preprint arXiv:2110.14830},
  year   = {2021}
}

Comments

Submitted to IEEE TPAMI

R2 v1 2026-06-24T07:15:06.638Z