Volume 37, Issue 3
Quantization and Training of Low Bit-Width Convolutional Neural Networks for Object Detection

Penghang Yin , Shuai Zhang , Yingyong Qi & Jack Xin

10.4208/jcm.1803-m2017-0301

J. Comp. Math., 37 (2019), pp. 349-359.

Preview Full PDF BiBTex 145 1432
  • Abstract

We present LBW-Net, an efficient optimization based method for quantization and training of the low bit-width convolutional neural networks (CNNs). Specifically, we quantize the weights to zero or powers of 2 by minimizing the Euclidean distance between full-precision weights and quantized weights during backpropagation (weight learning). We characterize the combinatorial nature of the low bit-width quantization problem. For 2-bit (ternary) CNNs, the quantization of N weights can be done by an exact formula in O(N log N) complexity. When the bit-width is 3 and above, we further propose a semi-analytical thresholding scheme with a single free parameter for quantization that is computationally inexpensive. The free parameter is further determined by network retraining and object detection tests. The LBW-Net has several desirable advantages over full-precision CNNs, including considerable memory savings, energy efficiency, and faster deployment. Our experiments on PASCAL VOC dataset [5] show that compared with its 32-bit floating-point counterpart, the performance of the 6-bit LBW-Net is nearly lossless in the object detection tasks, and can even do better in real world visual scenes, while empirically enjoying more than 4× faster deployment.

  • AMS Subject Headings

90C26, 90C10, 90C90.

Published online: 2018-09