Skip to Main content Skip to Navigation
Conference papers

Modulated binary clique convolutional neural network

Abstract : Although Convolutional Neural Networks (CNNs) achieve effectiveness in various computer vision tasks, the significant requirement of storage of such networks hinders the deployment on computationally limited devices. In this paper, we propose a new compact and portable deep learning network named Modulated Binary Clique Convolutional Neural Network (MBCliqueNet) aiming to improve the portability of CNNs based on binarized filters while achieving comparable performance with the full-precision CNNs like Resnet. In MBCliqueNet, we introduce a novel modulated operation to approximate the unbinarized filters and gives an initialization method to speed up its convergence. We reduce the extra parameters caused by modulated operation with parameters sharing. As a result, the proposed MBCliqueNet can reduce the required storage space of convolutional filters by a factor of at least 32, in contrast to the full-precision model, and achieve better performance than other state-of-the-art binarized models. More importantly, our model compares even better with some full-precision models like Resnet on the dataset we used. © 2019 IEEE.
Document type :
Conference papers
Complete list of metadatas

https://hal-univ-rennes1.archives-ouvertes.fr/hal-02442592
Contributor : Laurent Jonchère <>
Submitted on : Thursday, January 16, 2020 - 3:32:28 PM
Last modification on : Friday, January 17, 2020 - 1:26:41 AM

Identifiers

Collections

Citation

J. Xia, J. Wu, F. Wu, Y. Kong, P. Zhang, et al.. Modulated binary clique convolutional neural network. 7th International Conference on Advanced Cloud and Big Data, CBD 2019, Sep 2019, Suzhou, China. pp.252-257, ⟨10.1109/CBD.2019.00053⟩. ⟨hal-02442592⟩

Share

Metrics

Record views

36