@Article{JCM-37-3,
author = {Yin, Penghang and Zhang, Shuai and Yingyong, Qi and Xin, Jack},
title = {Quantization and Training of Low Bit-Width Convolutional Neural Networks for Object Detection},
journal = {Journal of Computational Mathematics},
year = {2019},
volume = {37},
number = {3},
pages = {349--359},
abstract = {<p style="text-align: justify;">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.</p>},
issn = {1991-7139},
doi = {https://doi.org/10.4208/jcm.1803-m2017-0301},
url = {https://global-sci.com/article/84404/quantization-and-training-of-low-bit-width-convolutional-neural-networks-for-object-detection}
}