Rethinking Binary Neural Network for Accurate Image Classification and Semantic Segmentation

11/22/2018
by   Bohan Zhuang, et al.
0

In this paper, we propose to train a network with both binary weights and binary activations, designed specifically for mobile devices with limited computation capacity and power consumption. Previous works on quantizing CNNs uncritically assume the same architecture with full-precision networks, which we term value approximation. Their objective is to preserve the floating-point information using a set of discrete values. However, we take a novel view---for best performance it is very likely that a different architecture may be better suited to deal with binary weights as well as binary activations. Thus we directly design such a highly accurate binary network structure, which is termed structure approximation. In particular, we propose a "network decomposition" strategy in which we divide the networks into groups and aggregate a set of homogeneous binary branches to implicitly reconstruct the full-precision intermediate feature maps. In addition, we also learn the connections between each group. We further provide a comprehensive comparison among all quantization categories. Experiments on ImageNet classification tasks demonstrate the superior performance of the proposed model, named Group-Net, over various popular architectures. In particular, we outperform the previous best binary neural network in terms of accuracy as well as saving huge computational complexity. Furthermore, the proposed Group-Net can effectively utilize task specific properties for strong generalization. In particular, we propose to extend Group-Net for lossless semantic segmentation. This is the first work proposed on solving dense pixels prediction based on BNNs in the literature. Actually, we claim that considering both value and structure approximation should be the future development direction of BNNs.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/22/2018

Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation

In this paper, we propose to train convolutional neural networks (CNNs) ...
research
08/08/2018

Training Compact Neural Networks with Binary Weights and Low Precision Activations

In this paper, we propose to train a network with binary weights and low...
research
09/22/2019

Structured Binary Neural Networks for Image Recognition

We propose methods to train convolutional neural networks (CNNs) with bo...
research
07/25/2018

Multi-Resolution Networks for Semantic Segmentation in Whole Slide Images

Digital pathology provides an excellent opportunity for applying fully c...
research
09/26/2019

Balanced Binary Neural Networks with Gated Residual

Binary neural networks have attracted numerous attention in recent years...
research
02/17/2020

Learning Architectures for Binary Networks

Backbone architectures of most binary networks are well-known floating p...
research
03/31/2020

Binary Neural Networks: A Survey

The binary neural network, largely saving the storage and computation, s...

Please sign up or login with your details

Forgot password? Click here to reset