@inproceedings{dfc084c13b7549f786557c637e24b599,
title = "Trainable Thresholds for Neural Network Quantization",
abstract = "Embedded computer vision applications for robotics, security cameras, and mobile phone apps require the usage of mobile neural network architectures like MobileNet-v2 or MNAS-Net in order to reduce RAM consumption and accelerate processing. An additional option for further resource consumption reduction is 8-bit neural network quantization. Unfortunately, the known methods for neural network quantization lead to significant accuracy reduction (more than 1.2%) for mobile architectures and require long training with quantization procedure. To overcome this limitation, we propose a method that allows to quantize mobile neural network without significant accuracy loss. Our approach is based on trainable quantization thresholds for each neural network filter, that allows to accelerate training with quantization procedure up{\^A} to 10 times in comparison with the standard techniques. Using the proposed technique, we quantize the modern mobile architectures of neural networks with the accuracy loss not exceeding 0.1%. Ready-for-use models and code are available at: https://github.com/agoncharenko1992/FAT-fast-adjustable-threshold.",
keywords = "Distillation, Machine learning, Neural networks, Quantization",
author = "Alexander Goncharenko and Andrey Denisov and Sergey Alyamkin and Evgeny Terentev",
year = "2019",
month = jan,
day = "1",
doi = "10.1007/978-3-030-20518-8_26",
language = "English",
isbn = "9783030205171",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer-Verlag GmbH and Co. KG",
pages = "302--312",
editor = "Ignacio Rojas and Gonzalo Joya and Andreu Catala",
booktitle = "Advances in Computational Intelligence - 15th International Work-Conference on Artificial Neural Networks, IWANN 2019, Proceedings",
address = "Germany",
note = "15th International Work-Conference on Artificial Neural Networks, IWANN 2019 ; Conference date: 12-06-2019 Through 14-06-2019",
}