.png){kind=icon}
返回
Kernel Quantization for Efficient Network Compression
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2022.3140773.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper presents a novel network compression framework, Kernel Quantization (KQ), targeting to efficiently convert any pre-trained full-precision convolutional neural network (CNN) model into a low-precision version without significant performance loss. Unlike existing methods struggling with weight bit-length, KQ has the potential in improving the compression ratio by considering the convolution kernel as the quantization unit. Inspired by the evolution from weight pruning to filter pruning, we propose to quantize in both kernel and weight level. Instead of representing each weight parameter with a low-bit index, we learn a kernel codebook and replace all kernels in the convolution layer with corresponding low-bit indexes. Thus, KQ can represent the weight tensor in the convolution layer with low-bit indexes and a kernel codebook with limited size, which enables KQ to achieve significant compression ratio. Then, we conduct a 6-bit parameter quantization on the kernel codebook to further reduce redundancy. Extensive experiments on the ImageNet classification task prove that KQ needs 1.05 and 1.62 bits on average in VGG and ResNet18, respectively, to represent each parameter in the convolution layer and achieves the state-of-the-art compression ratio with little accuracy loss.
Keyword:
Quantization (signal)
Kernel
Convolution
Indexes
Image coding
Convolutional neural networks
Licenses
Kernel quantization
network compression
convolutional neural network
low-precision
low-bit
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
.png){kind=icon}
A Hierarchical Cardiac Rhythm Classification Methodology Based on Electrocardiogram Fiducial Points一种基于心电图基准点的分层心律分类方法
OAAI
OAAI分享收藏Structural study of lanthanides(III) in aqueous nitrate and chloride solutions by EXAFS通过EXAFS对硝酸盐和氯化物水溶液中镧系元素 (III) 的结构研究
PREAI
分享收藏Sequential Deep Trajectory Descriptor for Action Recognition With Three-Stream CNN用于三流CNN动作识别的序列深度轨迹描述符OAAI
OAAI分享收藏Identification of pediatric respiratory diseases using a fine-grained diagnosis system使用细粒度诊断系统识别儿科呼吸系统疾病OAAI
OAAI分享收藏
查看更多内容