Circulant Binary Convolutional Networks: Enhancing the Performance of 1-bit DCNNs with Circulant Back Propagation

10/24/2019
by   Chunlei Liu, et al.
12

The rapidly decreasing computation and memory cost has recently driven the success of many applications in the field of deep learning. Practical applications of deep learning in resource-limited hardware, such as embedded devices and smart phones, however, remain challenging. For binary convolutional networks, the reason lies in the degraded representation caused by binarizing full-precision filters. To address this problem, we propose new circulant filters (CiFs) and a circulant binary convolution (CBConv) to enhance the capacity of binarized convolutional features via our circulant back propagation (CBP). The CiFs can be easily incorporated into existing deep convolutional neural networks (DCNNs), which leads to new Circulant Binary Convolutional Networks (CBCNs). Extensive experiments confirm that the performance gap between the 1-bit and full-precision DCNNs is minimized by increasing the filter diversity, which further increases the representational ability in our networks. Our experiments on ImageNet show that CBCNs achieve 61.4 accuracy with ResNet18. Compared to the state-of-the-art such as XNOR, CBCNs can achieve up to 10 ability.

READ FULL TEXT

page 1

page 3

research
08/21/2019

RBCN: Rectified Binary Convolutional Networks for Enhancing the Performance of 1-bit DCNNs

Binarized convolutional neural networks (BCNNs) are widely used to impro...
research
11/25/2019

GBCNs: Genetic Binary Convolutional Networks for Enhancing the Performance of 1-bit DCNNs

Training 1-bit deep convolutional neural networks (DCNNs) is one of the ...
research
04/22/2019

Inner-Imaging Convolutional Networks

Despite the tremendous success in computer vision, deep convolutional ne...
research
11/30/2018

Projection Convolutional Neural Networks for 1-bit CNNs via Discrete Back Propagation

The advancement of deep convolutional neural networks (DCNNs) has driven...
research
08/17/2019

Bayesian Optimized 1-Bit CNNs

Deep convolutional neural networks (DCNNs) have dominated the recent dev...
research
08/04/2020

Controlling Information Capacity of Binary Neural Network

Despite the growing popularity of deep learning technologies, high memor...
research
05/03/2017

Gabor Convolutional Networks

Steerable properties dominate the design of traditional filters, e.g., G...

Please sign up or login with your details

Forgot password? Click here to reset