CVOct 28, 2021
ODMTCNet: An Interpretable Multi-view Deep Neural Network Architecture for Image Feature Representation
arXiv:2110.14830v14 citations
Originality Synthesis-oriented
AI Analysis
This work addresses image feature representation for computer vision applications, but it appears incremental as it combines existing methods without clear novel breakthroughs.
The paper tackled the problem of image feature representation by proposing ODMTCNet, an interpretable multi-view deep neural network architecture that integrates statistical machine learning principles with deep neural networks, but no concrete results or numbers are provided in the 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.