Unsupervised meta-learning with domain adaptation based on a multi-task reconstruction-classification network for few-shot hyperspectral image classification

Although the deep-learning method has achieved great success for hyperspectral image (HSI) classification, the few-shot HSI classification deserves sufficient study because it is difficult and expensive to acquire labeled samples. In fact, the meta-learning methods can improve the performance for fe...

Full description

Saved in:
Bibliographic Details
Main Authors: Yu Liu, Caihong Mu, Shanjiao Jiang, Yi Liu
Format: Article
Language:English
Published: KeAi Communications Co., Ltd. 2025-03-01
Series:Journal of Information and Intelligence
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2949715924000544
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849417321461841920
author Yu Liu
Caihong Mu
Shanjiao Jiang
Yi Liu
author_facet Yu Liu
Caihong Mu
Shanjiao Jiang
Yi Liu
author_sort Yu Liu
collection DOAJ
description Although the deep-learning method has achieved great success for hyperspectral image (HSI) classification, the few-shot HSI classification deserves sufficient study because it is difficult and expensive to acquire labeled samples. In fact, the meta-learning methods can improve the performance for few-shot HSI classification effectively. However, most of the existing meta-learning methods for HSI classification are supervised, which still heavily rely on the labeled data for meta-training. Moreover, there are many cross-scene classification tasks in the real world, and domain adaptation of unsupervised meta-learning has been ignored for HSI classification so far. To address the above issues, this paper proposes an unsupervised meta-learning method with domain adaptation based on a multi-task reconstruction-classification network (MRCN) for few-shot HSI classification. MRCN does not need any labeled data for meta-training, where the pseudo labels are generated by multiple spectral random sampling and data augmentation. The meta-training of MRCN jointly learns a shared encoding representation for two tasks and domains. On the one hand, we design an encoder-classifier to learn the classification task on the source-domain data. On the other hand, we devise an encoder-decoder to learn the reconstruction task on the target-domain data. The experimental results on four HSI datasets demonstrate that MRCN preforms better than several state-of-the-art methods with only two to five labeled samples per class. To the best of our knowledge, the proposed method is the first unsupervised meta-learning method that considers the domain adaptation for few-shot HSI classification.
format Article
id doaj-art-1c83763f0fca43eab6dbc3ee1f494833
institution Kabale University
issn 2949-7159
language English
publishDate 2025-03-01
publisher KeAi Communications Co., Ltd.
record_format Article
series Journal of Information and Intelligence
spelling doaj-art-1c83763f0fca43eab6dbc3ee1f4948332025-08-20T03:32:53ZengKeAi Communications Co., Ltd.Journal of Information and Intelligence2949-71592025-03-013210311210.1016/j.jiixd.2024.06.001Unsupervised meta-learning with domain adaptation based on a multi-task reconstruction-classification network for few-shot hyperspectral image classificationYu Liu0Caihong Mu1Shanjiao Jiang2Yi Liu3Guangzhou Institute of Technology, Xidian University, Guangzhou 510555, ChinaSchool of Artificial Intelligence, Xidian University, Xi'an 710071, ChinaGuangzhou Institute of Technology, Xidian University, Guangzhou 510555, ChinaSchool of Electronic Engineering, Xidian University, Xi'an 710071, China; Corresponding author.Although the deep-learning method has achieved great success for hyperspectral image (HSI) classification, the few-shot HSI classification deserves sufficient study because it is difficult and expensive to acquire labeled samples. In fact, the meta-learning methods can improve the performance for few-shot HSI classification effectively. However, most of the existing meta-learning methods for HSI classification are supervised, which still heavily rely on the labeled data for meta-training. Moreover, there are many cross-scene classification tasks in the real world, and domain adaptation of unsupervised meta-learning has been ignored for HSI classification so far. To address the above issues, this paper proposes an unsupervised meta-learning method with domain adaptation based on a multi-task reconstruction-classification network (MRCN) for few-shot HSI classification. MRCN does not need any labeled data for meta-training, where the pseudo labels are generated by multiple spectral random sampling and data augmentation. The meta-training of MRCN jointly learns a shared encoding representation for two tasks and domains. On the one hand, we design an encoder-classifier to learn the classification task on the source-domain data. On the other hand, we devise an encoder-decoder to learn the reconstruction task on the target-domain data. The experimental results on four HSI datasets demonstrate that MRCN preforms better than several state-of-the-art methods with only two to five labeled samples per class. To the best of our knowledge, the proposed method is the first unsupervised meta-learning method that considers the domain adaptation for few-shot HSI classification.http://www.sciencedirect.com/science/article/pii/S2949715924000544Unsupervised meta-learningDomain adaptationMulti-task learningReconstruction-classification network
spellingShingle Yu Liu
Caihong Mu
Shanjiao Jiang
Yi Liu
Unsupervised meta-learning with domain adaptation based on a multi-task reconstruction-classification network for few-shot hyperspectral image classification
Journal of Information and Intelligence
Unsupervised meta-learning
Domain adaptation
Multi-task learning
Reconstruction-classification network
title Unsupervised meta-learning with domain adaptation based on a multi-task reconstruction-classification network for few-shot hyperspectral image classification
title_full Unsupervised meta-learning with domain adaptation based on a multi-task reconstruction-classification network for few-shot hyperspectral image classification
title_fullStr Unsupervised meta-learning with domain adaptation based on a multi-task reconstruction-classification network for few-shot hyperspectral image classification
title_full_unstemmed Unsupervised meta-learning with domain adaptation based on a multi-task reconstruction-classification network for few-shot hyperspectral image classification
title_short Unsupervised meta-learning with domain adaptation based on a multi-task reconstruction-classification network for few-shot hyperspectral image classification
title_sort unsupervised meta learning with domain adaptation based on a multi task reconstruction classification network for few shot hyperspectral image classification
topic Unsupervised meta-learning
Domain adaptation
Multi-task learning
Reconstruction-classification network
url http://www.sciencedirect.com/science/article/pii/S2949715924000544
work_keys_str_mv AT yuliu unsupervisedmetalearningwithdomainadaptationbasedonamultitaskreconstructionclassificationnetworkforfewshothyperspectralimageclassification
AT caihongmu unsupervisedmetalearningwithdomainadaptationbasedonamultitaskreconstructionclassificationnetworkforfewshothyperspectralimageclassification
AT shanjiaojiang unsupervisedmetalearningwithdomainadaptationbasedonamultitaskreconstructionclassificationnetworkforfewshothyperspectralimageclassification
AT yiliu unsupervisedmetalearningwithdomainadaptationbasedonamultitaskreconstructionclassificationnetworkforfewshothyperspectralimageclassification