Deep Ensembles for Hyperspectral Image Data Classification and Unmixing
Hyperspectral images capture very detailed information about scanned objects and, hence, can be used to uncover various characteristics of the materials present in the analyzed scene. However, such image data are difficult to transfer due to their large volume, and generating new ground-truth datase...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-10-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/13/20/4133 |
_version_ | 1797513183112462336 |
---|---|
author | Jakub Nalepa Michal Myller Lukasz Tulczyjew Michal Kawulok |
author_facet | Jakub Nalepa Michal Myller Lukasz Tulczyjew Michal Kawulok |
author_sort | Jakub Nalepa |
collection | DOAJ |
description | Hyperspectral images capture very detailed information about scanned objects and, hence, can be used to uncover various characteristics of the materials present in the analyzed scene. However, such image data are difficult to transfer due to their large volume, and generating new ground-truth datasets that could be utilized to train supervised learners is costly, time-consuming, very user-dependent, and often infeasible in practice. The research efforts have been focusing on developing algorithms for hyperspectral data classification and unmixing, which are two main tasks in the analysis chain of such imagery. Although in both of them, the deep learning techniques have bloomed as an extremely effective tool, designing the deep models that generalize well over the unseen data is a serious practical challenge in emerging applications. In this paper, we introduce the deep ensembles benefiting from different architectural advances of convolutional base models and suggest a new approach towards aggregating the outputs of base learners using a supervised fuser. Furthermore, we propose a model augmentation technique that allows us to synthesize new deep networks based on the original one by injecting Gaussian noise into the model’s weights. The experiments, performed for both hyperspectral data classification and unmixing, show that our deep ensembles outperform base spectral and spectral-spatial deep models and classical ensembles employing voting and averaging as a fusing scheme in both hyperspectral image analysis tasks. |
first_indexed | 2024-03-10T06:13:04Z |
format | Article |
id | doaj.art-2ef62cfebb514bc28220b9c3162ccd12 |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-10T06:13:04Z |
publishDate | 2021-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-2ef62cfebb514bc28220b9c3162ccd122023-11-22T19:54:41ZengMDPI AGRemote Sensing2072-42922021-10-011320413310.3390/rs13204133Deep Ensembles for Hyperspectral Image Data Classification and UnmixingJakub Nalepa0Michal Myller1Lukasz Tulczyjew2Michal Kawulok3Department of Algorithmics and Software, Faculty of Automatic Control, Electronics and Computer Science, Silesian University of Technology, Akademicka 16, 44-100 Gliwice, PolandDepartment of Algorithmics and Software, Faculty of Automatic Control, Electronics and Computer Science, Silesian University of Technology, Akademicka 16, 44-100 Gliwice, PolandDepartment of Algorithmics and Software, Faculty of Automatic Control, Electronics and Computer Science, Silesian University of Technology, Akademicka 16, 44-100 Gliwice, PolandDepartment of Algorithmics and Software, Faculty of Automatic Control, Electronics and Computer Science, Silesian University of Technology, Akademicka 16, 44-100 Gliwice, PolandHyperspectral images capture very detailed information about scanned objects and, hence, can be used to uncover various characteristics of the materials present in the analyzed scene. However, such image data are difficult to transfer due to their large volume, and generating new ground-truth datasets that could be utilized to train supervised learners is costly, time-consuming, very user-dependent, and often infeasible in practice. The research efforts have been focusing on developing algorithms for hyperspectral data classification and unmixing, which are two main tasks in the analysis chain of such imagery. Although in both of them, the deep learning techniques have bloomed as an extremely effective tool, designing the deep models that generalize well over the unseen data is a serious practical challenge in emerging applications. In this paper, we introduce the deep ensembles benefiting from different architectural advances of convolutional base models and suggest a new approach towards aggregating the outputs of base learners using a supervised fuser. Furthermore, we propose a model augmentation technique that allows us to synthesize new deep networks based on the original one by injecting Gaussian noise into the model’s weights. The experiments, performed for both hyperspectral data classification and unmixing, show that our deep ensembles outperform base spectral and spectral-spatial deep models and classical ensembles employing voting and averaging as a fusing scheme in both hyperspectral image analysis tasks.https://www.mdpi.com/2072-4292/13/20/4133hyperspectral imagingdeep learningensemble learningsegmentationclassificationunmixing |
spellingShingle | Jakub Nalepa Michal Myller Lukasz Tulczyjew Michal Kawulok Deep Ensembles for Hyperspectral Image Data Classification and Unmixing Remote Sensing hyperspectral imaging deep learning ensemble learning segmentation classification unmixing |
title | Deep Ensembles for Hyperspectral Image Data Classification and Unmixing |
title_full | Deep Ensembles for Hyperspectral Image Data Classification and Unmixing |
title_fullStr | Deep Ensembles for Hyperspectral Image Data Classification and Unmixing |
title_full_unstemmed | Deep Ensembles for Hyperspectral Image Data Classification and Unmixing |
title_short | Deep Ensembles for Hyperspectral Image Data Classification and Unmixing |
title_sort | deep ensembles for hyperspectral image data classification and unmixing |
topic | hyperspectral imaging deep learning ensemble learning segmentation classification unmixing |
url | https://www.mdpi.com/2072-4292/13/20/4133 |
work_keys_str_mv | AT jakubnalepa deepensemblesforhyperspectralimagedataclassificationandunmixing AT michalmyller deepensemblesforhyperspectralimagedataclassificationandunmixing AT lukasztulczyjew deepensemblesforhyperspectralimagedataclassificationandunmixing AT michalkawulok deepensemblesforhyperspectralimagedataclassificationandunmixing |