Searching for Accurate Binary Neural Architectures

09/16/2019
by   Mingzhu Shen, et al.
0

Binary neural networks have attracted tremendous attention due to the efficiency for deploying them on mobile devices. Since the weak expression ability of binary weights and features, their accuracy is usually much lower than that of full-precision (i.e. 32-bit) models. Here we present a new frame work for automatically searching for compact but accurate binary neural networks. In practice, number of channels in each layer will be encoded into the search space and optimized using the evolutionary algorithm. Experiments conducted on benchmark datasets and neural architectures demonstrate that our searched binary networks can achieve the performance of full-precision models with acceptable increments on model sizes and calculations.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/16/2020

MeliusNet: Can Binary Neural Networks Achieve MobileNet-level Accuracy?

Binary Neural Networks (BNNs) are neural networks which use binary weigh...
research
12/05/2018

Training Competitive Binary Neural Networks from Scratch

Convolutional neural networks have achieved astonishing results in diffe...
research
02/03/2020

Widening and Squeezing: Towards Accurate and Efficient QNNs

Quantization neural networks (QNNs) are very attractive to the industry ...
research
05/13/2020

Binarizing MobileNet via Evolution-based Searching

Binary Neural Networks (BNNs), known to be one among the effectively com...
research
01/16/2021

Evaluating Online and Offline Accuracy Traversal Algorithms for k-Complete Neural Network Architectures

Architecture sizes for neural networks have been studied widely and seve...
research
12/09/2018

Binary Input Layer: Training of CNN models with binary input data

For the efficient execution of deep convolutional neural networks (CNN) ...
research
10/16/2021

BNAS v2: Learning Architectures for Binary Networks with Empirical Improvements

Backbone architectures of most binary networks are well-known floating p...

Please sign up or login with your details

Forgot password? Click here to reset