Journal
2019 SEVENTH INTERNATIONAL CONFERENCE ON ADVANCED CLOUD AND BIG DATA (CBD)
Volume -, Issue -, Pages 252-257Publisher
IEEE
DOI: 10.1109/CBD.2019.00053
Keywords
deep learning; modulate process; binary convolutional neural network; MBCliqueNet
Funding
- National Natural Science Foundation of China [61876037, 31800825, 61871117, 61871124, 61773117, 31571001, 61572258]
- National Key Research and Development Program of China [2017YFC0107903, 2017YFC0109202, 2018ZX10201002-003]
- Short-Term Recruitment Program of Foreign Experts [WQ20163200398]
Ask authors/readers for more resources
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available