Binary neural networks: A survey
作者：
Highlights：
• We summarize the binary neural network methods and categorize them into the naive binarization and the optimized binarization.
• The binary neural networks are mainly optimized using techniques including minimizing quantization error, improving the loss function, and reducing the gradient error.
• We also discuss the hardware-friendly methods and the useful tricks of training binary neural networks.
• We present the common datasets and network structures of evaluation, and compare the performance on different tasks.
• We conclude and point out the future research trends.
摘要
•We summarize the binary neural network methods and categorize them into the naive binarization and the optimized binarization.•The binary neural networks are mainly optimized using techniques including minimizing quantization error, improving the loss function, and reducing the gradient error.•We also discuss the hardware-friendly methods and the useful tricks of training binary neural networks.•We present the common datasets and network structures of evaluation, and compare the performance on different tasks.•We conclude and point out the future research trends.
论文关键词：Binary neural network,Deep learning,Model compression,Network quantization,Model acceleration
论文评审过程：Received 6 August 2019, Revised 14 February 2020, Accepted 16 February 2020, Available online 21 February 2020, Version of Record 5 June 2020.
论文官网地址：https://doi.org/10.1016/j.patcog.2020.107281
