Deep Multi-View Learning Using Neuron-Wise Correlation-Maximizing Regularizers

Created by Kui Jia, Jiehong Lin, Mingkui Tan and Dacheng Tao.

Introduction

This is the code released for our work "Deep Multi-View Learning Using Neuron-Wise Correlation-Maximizing Regularizers" published in TIP2019. In this work, we study the problem of learning deep representations from multi-view data in end-to-end networks. We take a regularization approach via multi-view learning criteria, and propose a novel, effective, and efficient neuron-wise correlation-maximizing regularizer. We implement our proposed regularizers collectively as a correlation-regularized network layer (CorrReg).

Implementations

• Torch
• Pytorch

Citation

If you find our work useful in your research, please consider citing:

@article{jia2019deep,
      title={Deep Multi-View Learning using Neuron-Wise Correlation-Maximizing Regularizers},
      author={Jia, Kui and Lin, Jiehong and Tan, Mingkui and Tao, Dacheng},
      journal={IEEE Transactions on Image Processing},
      year={2019},
      publisher={IEEE}
    }

Contact

kuijia@scut.edu.cn

lin.jiehong@mail.scut.edu.cn