Searching for Accurate Binary Neural Architectures

2019/09/16 by Mingzhu Shen, Shen, Mingzhu, Kai Han +5
Computer Science · #Advanced Neural Network Applications #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Data Classification #Neural Networks and Applications

paper · pdf · doi:10.48550/arxiv.1909.07378

openalex publication_date 2019/09/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
• DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
• Neural Architecture Search with Reinforcement Learning
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal\n Networks
• Learning Multiple Layers of Features from Tiny Images

Related

• Binarizing MobileNet via Evolution-based Searching
• Towards Searching Efficient and Accurate Neural Network Architectures in Binary Classification Problems
• NASB: Neural Architecture Search for Binary Convolutional Neural Networks
• Training Competitive Binary Neural Networks from Scratch
• MeliusNet: Can Binary Neural Networks Achieve MobileNet-level Accuracy?