Quantization Networks

Jiwei Yang, Xu Shen, Jun Xing, Xinmei Tian, Houqiang Li, Bing Deng, Jianqiang Huang, Xian-sheng Hua; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 7308-7316

Abstract


Although deep neural networks are highly effective, their high computational and memory costs severely hinder their applications to portable devices. As a consequence, lowbit quantization, which converts a full-precision neural network into a low-bitwidth integer version, has been an active and promising research topic. Existing methods formulate the low-bit quantization of networks as an approximation or optimization problem. Approximation-based methods confront the gradient mismatch problem, while optimizationbased methods are only suitable for quantizing weights and can introduce high computational cost during the training stage. In this paper, we provide a simple and uniform way for weights and activations quantization by formulating it as a differentiable non-linear function. The quantization function is represented as a linear combination of several Sigmoid functions with learnable biases and scales that could be learned in a lossless and end-to-end manner via continuous relaxation of the steepness of Sigmoid functions. Extensive experiments on image classification and object detection tasks show that our quantization networks outperform state-of-the-art methods. We believe that the proposed method will shed new lights on the interpretation of neural network quantization.

Related Material


[pdf]
[bibtex]
@InProceedings{Yang_2019_CVPR,
author = {Yang, Jiwei and Shen, Xu and Xing, Jun and Tian, Xinmei and Li, Houqiang and Deng, Bing and Huang, Jianqiang and Hua, Xian-sheng},
title = {Quantization Networks},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}