Enhancing Cross-Domain Remote Sensing Scene Classification by Multi-Source Subdomain Distribution Alignment Network

Multi-source domain adaptation (MSDA) in remote sensing (RS) scene classification has recently gained significant attention in the visual recognition community. It leverages multiple well-labeled source domains to train a model capable of achieving strong generalization on the target domain with lit...

Full description

Saved in:
Bibliographic Details
Main Authors: Yong Wang, Zhehao Shu, Yinzhi Feng, Rui Liu, Qiusheng Cao, Danping Li, Lei Wang
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/7/1302
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850212826896924672
author Yong Wang
Zhehao Shu
Yinzhi Feng
Rui Liu
Qiusheng Cao
Danping Li
Lei Wang
author_facet Yong Wang
Zhehao Shu
Yinzhi Feng
Rui Liu
Qiusheng Cao
Danping Li
Lei Wang
author_sort Yong Wang
collection DOAJ
description Multi-source domain adaptation (MSDA) in remote sensing (RS) scene classification has recently gained significant attention in the visual recognition community. It leverages multiple well-labeled source domains to train a model capable of achieving strong generalization on the target domain with little to no labeled data from the target domain. However, the distribution shifts among multiple source domains make it more challenging to align the distributions between the target domain and all source domains concurrently. Moreover, relying solely on global alignment risks losing fine-grained information for each class, especially in the task of RS scene classification. To alleviate these issues, we present a Multi-Source Subdomain Distribution Alignment Network (MSSDANet), which introduces novel network structures and loss functions for subdomain-oriented MSDA. By adopting a two-level feature extraction strategy, this model attains better global alignment between the target domain and multiple source domains, as well as alignment at the subdomain level. First, it includes a pre-trained convolutional neural network (CNN) as a common feature extractor to fully exploit the shared invariant features across one target and multiple source domains. Secondly, a dual-domain feature extractor is used after the common feature extractor, which maps the data from each pair of target and source domains to a specific dual-domain feature space and performs subdomain alignment. Finally, a dual-domain feature classifier is employed to make predictions by averaging the outputs from multiple classifiers. Accompanied by the above network, two novel loss functions are proposed to boost the classification performance. Discriminant Semantic Transfer (DST) loss is exploited to force the model to effectively extract semantic information among target and source domain samples, while Class Correlation (CC) loss is introduced to reduce the feature confusion from different classes within the target domain. It is noteworthy that our MSSDANet is developed in an unsupervised manner for domain adaptation, indicating that no label information from the target domain is required during training. Extensive experiments on four common RS image datasets demonstrate that the proposed method achieves state-of-the-art performance for cross-domain RS scene classification. Specifically, in the dual-source and three-source settings, MSSDANet outperforms the second-best algorithm in terms of overall accuracy (OA) by 2.2% and 1.6%, respectively.
format Article
id doaj-art-e033b34762bd42e38d30f90710794647
institution OA Journals
issn 2072-4292
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-e033b34762bd42e38d30f907107946472025-08-20T02:09:14ZengMDPI AGRemote Sensing2072-42922025-04-01177130210.3390/rs17071302Enhancing Cross-Domain Remote Sensing Scene Classification by Multi-Source Subdomain Distribution Alignment NetworkYong Wang0Zhehao Shu1Yinzhi Feng2Rui Liu3Qiusheng Cao4Danping Li5Lei Wang6School of Electronic Engineering, Xidian University, Xi’an 710071, ChinaGuangzhou Institute of Technology, Xidian University, Guangzhou 510555, ChinaSchool of Electronic Engineering, Xidian University, Xi’an 710071, ChinaSchool of Electronic Engineering, Xidian University, Xi’an 710071, ChinaSchool of Electronic Engineering, Xidian University, Xi’an 710071, ChinaSchool of Telecommunications Engineering, Xidian University, Xi’an 710071, ChinaSchool of Electronic Engineering, Xidian University, Xi’an 710071, ChinaMulti-source domain adaptation (MSDA) in remote sensing (RS) scene classification has recently gained significant attention in the visual recognition community. It leverages multiple well-labeled source domains to train a model capable of achieving strong generalization on the target domain with little to no labeled data from the target domain. However, the distribution shifts among multiple source domains make it more challenging to align the distributions between the target domain and all source domains concurrently. Moreover, relying solely on global alignment risks losing fine-grained information for each class, especially in the task of RS scene classification. To alleviate these issues, we present a Multi-Source Subdomain Distribution Alignment Network (MSSDANet), which introduces novel network structures and loss functions for subdomain-oriented MSDA. By adopting a two-level feature extraction strategy, this model attains better global alignment between the target domain and multiple source domains, as well as alignment at the subdomain level. First, it includes a pre-trained convolutional neural network (CNN) as a common feature extractor to fully exploit the shared invariant features across one target and multiple source domains. Secondly, a dual-domain feature extractor is used after the common feature extractor, which maps the data from each pair of target and source domains to a specific dual-domain feature space and performs subdomain alignment. Finally, a dual-domain feature classifier is employed to make predictions by averaging the outputs from multiple classifiers. Accompanied by the above network, two novel loss functions are proposed to boost the classification performance. Discriminant Semantic Transfer (DST) loss is exploited to force the model to effectively extract semantic information among target and source domain samples, while Class Correlation (CC) loss is introduced to reduce the feature confusion from different classes within the target domain. It is noteworthy that our MSSDANet is developed in an unsupervised manner for domain adaptation, indicating that no label information from the target domain is required during training. Extensive experiments on four common RS image datasets demonstrate that the proposed method achieves state-of-the-art performance for cross-domain RS scene classification. Specifically, in the dual-source and three-source settings, MSSDANet outperforms the second-best algorithm in terms of overall accuracy (OA) by 2.2% and 1.6%, respectively.https://www.mdpi.com/2072-4292/17/7/1302domain adaptationcross-domain scene classificationdeep learningremote sensing
spellingShingle Yong Wang
Zhehao Shu
Yinzhi Feng
Rui Liu
Qiusheng Cao
Danping Li
Lei Wang
Enhancing Cross-Domain Remote Sensing Scene Classification by Multi-Source Subdomain Distribution Alignment Network
Remote Sensing
domain adaptation
cross-domain scene classification
deep learning
remote sensing
title Enhancing Cross-Domain Remote Sensing Scene Classification by Multi-Source Subdomain Distribution Alignment Network
title_full Enhancing Cross-Domain Remote Sensing Scene Classification by Multi-Source Subdomain Distribution Alignment Network
title_fullStr Enhancing Cross-Domain Remote Sensing Scene Classification by Multi-Source Subdomain Distribution Alignment Network
title_full_unstemmed Enhancing Cross-Domain Remote Sensing Scene Classification by Multi-Source Subdomain Distribution Alignment Network
title_short Enhancing Cross-Domain Remote Sensing Scene Classification by Multi-Source Subdomain Distribution Alignment Network
title_sort enhancing cross domain remote sensing scene classification by multi source subdomain distribution alignment network
topic domain adaptation
cross-domain scene classification
deep learning
remote sensing
url https://www.mdpi.com/2072-4292/17/7/1302
work_keys_str_mv AT yongwang enhancingcrossdomainremotesensingsceneclassificationbymultisourcesubdomaindistributionalignmentnetwork
AT zhehaoshu enhancingcrossdomainremotesensingsceneclassificationbymultisourcesubdomaindistributionalignmentnetwork
AT yinzhifeng enhancingcrossdomainremotesensingsceneclassificationbymultisourcesubdomaindistributionalignmentnetwork
AT ruiliu enhancingcrossdomainremotesensingsceneclassificationbymultisourcesubdomaindistributionalignmentnetwork
AT qiushengcao enhancingcrossdomainremotesensingsceneclassificationbymultisourcesubdomaindistributionalignmentnetwork
AT danpingli enhancingcrossdomainremotesensingsceneclassificationbymultisourcesubdomaindistributionalignmentnetwork
AT leiwang enhancingcrossdomainremotesensingsceneclassificationbymultisourcesubdomaindistributionalignmentnetwork