A Multiscale Deep Middle-level Feature Fusion Network for Hyperspectral Classification
Recently, networks consider spectral-spatial information in multiscale inputs less, even though there are some networks that consider this factor, however these networks cannot guarantee to get optimal features, which are extracted from each scale input. Furthermore, these networks do not consider t...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-03-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/11/6/695 |
id |
doaj-408d690580af47e992bd66ba93cf2a3d |
---|---|
record_format |
Article |
spelling |
doaj-408d690580af47e992bd66ba93cf2a3d2020-11-24T21:49:07ZengMDPI AGRemote Sensing2072-42922019-03-0111669510.3390/rs11060695rs11060695A Multiscale Deep Middle-level Feature Fusion Network for Hyperspectral ClassificationZhaokui Li0Lin Huang1Jinrong He2School of Computer Science, Shenyang Aerospace University, Shenyang 110136, ChinaSchool of Computer Science, Shenyang Aerospace University, Shenyang 110136, ChinaCollege of Mathematics and Computer Science, Yan’an University, Yan’an 716000, ChinaRecently, networks consider spectral-spatial information in multiscale inputs less, even though there are some networks that consider this factor, however these networks cannot guarantee to get optimal features, which are extracted from each scale input. Furthermore, these networks do not consider the complementary and related information among different scale features. To address these issues, a multiscale deep middle-level feature fusion network (MMFN) is proposed in this paper for hyperspectral classification. In MMFN, the network fully fuses the strong complementary and related information among different scale features to extract more discriminative features. The training of network contains two stages: the first stage obtains the optimal models corresponding to different scale inputs and extracts the middle-level features under the corresponding scale model. It can guarantee the multiscale middle-level features are optimal. The second stage fuses the optimal multiscale middle-level features in the convolutional layer, and the subsequent residual blocks can learn the complementary and related information among different scale middle-level features. Moreover, the idea of identity mapping in residual learning can help the network obtain a higher accuracy when the network is deeper. The effectiveness of our method is proved on four HSI data sets and the experimental results show that our method outperforms the other state-of-the-art methods especially with small training samples.https://www.mdpi.com/2072-4292/11/6/695hyperspectral image classificationmultiscalemiddle-level feature fusiondeep network |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Zhaokui Li Lin Huang Jinrong He |
spellingShingle |
Zhaokui Li Lin Huang Jinrong He A Multiscale Deep Middle-level Feature Fusion Network for Hyperspectral Classification Remote Sensing hyperspectral image classification multiscale middle-level feature fusion deep network |
author_facet |
Zhaokui Li Lin Huang Jinrong He |
author_sort |
Zhaokui Li |
title |
A Multiscale Deep Middle-level Feature Fusion Network for Hyperspectral Classification |
title_short |
A Multiscale Deep Middle-level Feature Fusion Network for Hyperspectral Classification |
title_full |
A Multiscale Deep Middle-level Feature Fusion Network for Hyperspectral Classification |
title_fullStr |
A Multiscale Deep Middle-level Feature Fusion Network for Hyperspectral Classification |
title_full_unstemmed |
A Multiscale Deep Middle-level Feature Fusion Network for Hyperspectral Classification |
title_sort |
multiscale deep middle-level feature fusion network for hyperspectral classification |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2019-03-01 |
description |
Recently, networks consider spectral-spatial information in multiscale inputs less, even though there are some networks that consider this factor, however these networks cannot guarantee to get optimal features, which are extracted from each scale input. Furthermore, these networks do not consider the complementary and related information among different scale features. To address these issues, a multiscale deep middle-level feature fusion network (MMFN) is proposed in this paper for hyperspectral classification. In MMFN, the network fully fuses the strong complementary and related information among different scale features to extract more discriminative features. The training of network contains two stages: the first stage obtains the optimal models corresponding to different scale inputs and extracts the middle-level features under the corresponding scale model. It can guarantee the multiscale middle-level features are optimal. The second stage fuses the optimal multiscale middle-level features in the convolutional layer, and the subsequent residual blocks can learn the complementary and related information among different scale middle-level features. Moreover, the idea of identity mapping in residual learning can help the network obtain a higher accuracy when the network is deeper. The effectiveness of our method is proved on four HSI data sets and the experimental results show that our method outperforms the other state-of-the-art methods especially with small training samples. |
topic |
hyperspectral image classification multiscale middle-level feature fusion deep network |
url |
https://www.mdpi.com/2072-4292/11/6/695 |
work_keys_str_mv |
AT zhaokuili amultiscaledeepmiddlelevelfeaturefusionnetworkforhyperspectralclassification AT linhuang amultiscaledeepmiddlelevelfeaturefusionnetworkforhyperspectralclassification AT jinronghe amultiscaledeepmiddlelevelfeaturefusionnetworkforhyperspectralclassification AT zhaokuili multiscaledeepmiddlelevelfeaturefusionnetworkforhyperspectralclassification AT linhuang multiscaledeepmiddlelevelfeaturefusionnetworkforhyperspectralclassification AT jinronghe multiscaledeepmiddlelevelfeaturefusionnetworkforhyperspectralclassification |
_version_ |
1725889492009615360 |