.png){kind=icon}
返回
Accelerating Convolutional Neural Network-Based Hyperspectral Image Classification by Step Activation Quantization
.png){kind=icon}
PRE
AI
DOI：10.1109/TGRS.2021.3058321.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Convolutional neural networks (CNNs) have achieved excellent feature extraction capabilities in remotely sensed hyperspectral image (HSI) classification. This is due to their ability to learn representative spatial and spectral features. However, it is difficult for conventional computers to classify HSIs quickly enough for practical use in many applications, mainly because of the large number of calculations and parameters needed by deep learning-based methods. Although several weight quantization methods achieved remarkable results in network compression, the network acceleration effect is still not significant because a full exploration of the potential of network acceleration brought by network weight quantization is still absent from the literature. In this article, a new step activation quantization method is proposed to constrain the input of the network layer of the CNN so that the data can be represented by low-bit integers. As a result, floating-point operations can be replaced with integer operations to greatly accelerate the forward (inference) step of the network. Specifically, nonlinear uniform quantization is adopted in this work to restrain the input of the CNN in the forward inference of the step activation quantization layer, and two functions (constant and tanh-like) are used in the backpropagation step to avoid gradient vanishing and noise. Our newly proposed step activation quantization acceleration method is applied to a CNN for HSI with two well-known benchmark data sets and the experimental results demonstrate that the proposed method is very effective in terms of both memory savings and computation acceleration, with only a slight decrease in classification accuracy. Specifically, our method reduces memory requirements in and obtains aroundspeedup with regard to the original real-valued network version.
Keyword:
Quantization (signal)
Convolution
Feature extraction
Acceleration
Hyperspectral imaging
Training
Memory management
Activation quantization
convolutional neural networks (CNNs)
hyperspectral image (HSI) classification
model acceleration and compression
weight quantification
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
8.6
论文数:
2.2W
被引数:
10.7W
机构
引用论文
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Principal manifolds and nonlinear dimensionality reduction via tangent space alignment基于切线空间对齐的主流形和非线性降维
OAAI
OAAI分享收藏Mechanism of carbonate mineralization induced by microbes: Taking Curvibacter lanceolatus strain HJ-1 as an example.png)
Micron
MicronIF0
PREAI
分享收藏Density and Thermal Conductivity Measurements for Silicon Melt by Electromagnetic Levitation under a Static Magnetic Field在静态磁场下通过电磁悬浮测量硅熔体的密度和热导率
PREAI
分享收藏Spectral and Spatial Classification of Hyperspectral Data Using SVMs and Morphological Profiles
PREAI
分享收藏
查看更多内容