Deep ring-block-wise network for hyperspectral image classification
Deep learning has achieved many successes in the field of the hyperspectral image (HSI) classification. Most of existing deep learning-based methods have no consideration of feature distribution, which may yield lowly separable and discriminative features. From the perspective of spatial geometry, o...
Saved in:
Main Authors: | , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/170571 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-170571 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1705712023-09-19T06:55:01Z Deep ring-block-wise network for hyperspectral image classification Xing, Changda Zhao, Jianlong Wang, Zhisheng Wang, Meiling School of Computer Science and Engineering Engineering::Computer science and engineering Block Hyperspectral Image Deep learning has achieved many successes in the field of the hyperspectral image (HSI) classification. Most of existing deep learning-based methods have no consideration of feature distribution, which may yield lowly separable and discriminative features. From the perspective of spatial geometry, one excellent feature distribution form requires to satisfy both properties, i.e., block and ring. The block means that in a feature space, the distance of intraclass samples is close and the one of interclass samples is far. The ring represents that all class samples are overall distributed in a ring topology. Accordingly, in this article, we propose a novel deep ring-block-wise network (DRN) for the HSI classification, which takes full consideration of feature distribution. To obtain the good distribution used for high classification performance, in this DRN, a ring-block perception (RBP) layer is built by integrating the self-representation and ring loss into a perception model. By such way, the exported features are imposed to follow the requirements of both block and ring, so as to be more separably and discriminatively distributed compared with traditional deep networks. Besides, we also design an optimization strategy with alternating update to obtain the solution of this RBP layer model. Extensive results on the Salinas, Pavia Centre, Indian Pines, and Houston datasets have demonstrated that the proposed DRN method achieves the better classification performance in contrast to the state-of-the-art approaches. This work was supported in part by the National Natural Science Foundation of China under Grant 62101247 and Grant 62106104, in part by the project funded by the China Postdoctoral Science Foundation under Grant 2022T150320, and in part by the Special Fund for Guiding Local Scientific and Technological Development of the Central Government in Shenzhen under Grant 2021Szvup063. 2023-09-19T06:55:01Z 2023-09-19T06:55:01Z 2023 Journal Article Xing, C., Zhao, J., Wang, Z. & Wang, M. (2023). Deep ring-block-wise network for hyperspectral image classification. IEEE Transactions On Neural Networks and Learning Systems. https://dx.doi.org/10.1109/TNNLS.2023.3274745 2162-237X https://hdl.handle.net/10356/170571 10.1109/TNNLS.2023.3274745 37220048 2-s2.0-85161024464 en IEEE Transactions on Neural Networks and Learning Systems © 2023 IEEE. All rights reserved. |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Computer science and engineering Block Hyperspectral Image |
spellingShingle |
Engineering::Computer science and engineering Block Hyperspectral Image Xing, Changda Zhao, Jianlong Wang, Zhisheng Wang, Meiling Deep ring-block-wise network for hyperspectral image classification |
description |
Deep learning has achieved many successes in the field of the hyperspectral image (HSI) classification. Most of existing deep learning-based methods have no consideration of feature distribution, which may yield lowly separable and discriminative features. From the perspective of spatial geometry, one excellent feature distribution form requires to satisfy both properties, i.e., block and ring. The block means that in a feature space, the distance of intraclass samples is close and the one of interclass samples is far. The ring represents that all class samples are overall distributed in a ring topology. Accordingly, in this article, we propose a novel deep ring-block-wise network (DRN) for the HSI classification, which takes full consideration of feature distribution. To obtain the good distribution used for high classification performance, in this DRN, a ring-block perception (RBP) layer is built by integrating the self-representation and ring loss into a perception model. By such way, the exported features are imposed to follow the requirements of both block and ring, so as to be more separably and discriminatively distributed compared with traditional deep networks. Besides, we also design an optimization strategy with alternating update to obtain the solution of this RBP layer model. Extensive results on the Salinas, Pavia Centre, Indian Pines, and Houston datasets have demonstrated that the proposed DRN method achieves the better classification performance in contrast to the state-of-the-art approaches. |
author2 |
School of Computer Science and Engineering |
author_facet |
School of Computer Science and Engineering Xing, Changda Zhao, Jianlong Wang, Zhisheng Wang, Meiling |
format |
Article |
author |
Xing, Changda Zhao, Jianlong Wang, Zhisheng Wang, Meiling |
author_sort |
Xing, Changda |
title |
Deep ring-block-wise network for hyperspectral image classification |
title_short |
Deep ring-block-wise network for hyperspectral image classification |
title_full |
Deep ring-block-wise network for hyperspectral image classification |
title_fullStr |
Deep ring-block-wise network for hyperspectral image classification |
title_full_unstemmed |
Deep ring-block-wise network for hyperspectral image classification |
title_sort |
deep ring-block-wise network for hyperspectral image classification |
publishDate |
2023 |
url |
https://hdl.handle.net/10356/170571 |
_version_ |
1779156337891999744 |