.png){kind=icon}
.png){kind=icon}
Return
M3FuNet: An Unsupervised Multivariate Feature Fusion Network for Hyperspectral Image Classification
.png){kind=icon}
PRE
AI
DOI：10.1109/TGRS.2024.3380087.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Hyperspectral image (HSI) spectral-spatial joint feature (FE) extraction methods generally suffer from low feature retention and weak spatial-spectral dependence, which will lead to single-class feature confrontation (SCFC). To solve this problem, an unsupervised multivariate feature fusion network (M(3)FuNet) is developed in this article. In M(3)FuNet, multiscale supervector matrix correction (MSMC) and multiscale random convolution dispersion (MRCD) are used as the spectral and spatial feature extraction method, and the feature retention of spectral and spatial features is improved to achieve feature calibration by feature fusion and decision fusion, called multivariate feature fusion. The MSMC is employed to correct the supervector matrix to reduce the intraclass variance in superpixel homogeneous regions and overcome the phenomenon of supervector block drift (SvBD). The MRCD uses random convolution and Gaussian smoothing to extract deep spatial features. Because of the similar feature representation ability of the MSMC and MRCD, the obtained spectral-spatial joint features have high feature retention and strong spectral-spatial dependence. Finally, this M(3)FuNet is used for realizing the classification of HSI. Three common HSI datasets are used to validate the effectiveness of the M(3)FuNet. The experiment results show that the M(3)FuNet has a superior performance compared with several state-of-the-art (SOTA) HSI classification methods. The code of the proposed M(3)FuNet is available at https://github.com/aichou233/M(3)FuNet.
Keywords:
Feature extraction
Convolution
Iron
Data mining
Principal component analysis
Transformers
Smoothing methods
Gaussian smoothing
hyperspectral image classification (HSIC)
multivariate feature (FE) fusion
supervector matrix correction (SMC)
Journal
IF:
8.6
Papers:
2.1W
Citations:
10.7W
Organization
View more organizations