.png){kind=icon}
返回
Iterative Random Training Sampling Convolutional Neural Network for Hyperspectral Image Classification
.png){kind=icon}
OA
AI
DOI：10.1109/TGRS.2023.3280205.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Convolutional neural network (CNN) has received considerable interest in hyperspectral image classification (HSIC) lately due to its excellent spectral-spatial feature extraction capability. To improve CNN, many approaches have been directed at exploring the infrastructure of its network by introducing different paradigms. This article takes a rather different approach by developing an iterative CNN that extends a CNN by including a feedback system to repeatedly process the same CNN in an iterative manner. Its idea is to take advantage of a recently developed iterative training sampling spectral-spatial classification (IRTS-SSC) that allows CNN to update its spatial information of classification maps through a feedback spatial fil- tering system via IRTS. The resulting CNN is called iterative random training sampling CNN (IRTS-CNN) with several unique features. First, IRTS-CNN combines CNN and IRTS-SSC into one paradigm, an architecture that has never been investigated in the past. Second, it implements a series of spatial filters to capture spatial information of classified data samples and further feeds this information back via an iterative process to expand the current input data cube for the next iteration. Third, it utilizes the expanded data cube to randomly reselect training samples and then to reimplement CNN iteratively. Last but not least, IRTS-CNN provides a general framework that can implement any arbitrary CNN as an initial classifier to improve its performance through an iterative process. Extensive experiments are conducted to demonstrate that IRTS-CNN indeed significantly improves CNN, specifically when only a small size of limited training samples is used.
Keyword:
Convolutional neural networks
Training
Iterative methods
Hyperspectral imaging
Three-dimensional displays
Convolution
Information filters
Convolutional neural network (CNN)
iterative random training sampling CNN (IRTS-CNN)
random training sampling (RTS)
期刊
IF:
8.6
论文数:
2.1W
被引数:
10.7W
机构
引用论文
Adsorption and Self-Assembly of Large Polycyclic Molecules on the Surfaces of TiO2 Single Crystals
OAAI
.png){kind=icon}
OAAI分享收藏LACK OF ASSOCIATION BETWEEN HERPESVIRUS DETECTION IN SALIVA AND GINGIVITIS IN HIV‑INFECTED CHILDRENOAAI
OAAI分享收藏Deep Pyramidal Residual Networks for Spectral-Spatial Hyperspectral Image Classification用于光谱-空间高光谱图像分类的深度金字塔残差网络OAAI
OAAI分享收藏A Survey on Spectral-Spatial Classification Techniques Based on Attribute Profiles基于属性剖面的光谱-空间分类技术综述
PREAI
分享收藏Regionalization, foreign direct investment and poverty reduction: Lessons from Vietnam in ASEAN
PREAI
分享收藏
查看更多内容