Graph Embedding Interclass Relation-Aware Adaptive Network for Cross-Scene Classification of Multisource Remote Sensing Data
IEEE Transactions on Image Processing · 2024 · 33 · 4459-4474
DOI: 10.1109/tip.2024.3422881 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2024. Verfasst von Teng Yang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 32-mal zitiert (Crossref) und nennt 58 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Youth Innovation Team of Shaanxi Universities, China Postdoctoral Science Foundation.
Abstract (Originalsprache)
The unsupervised domain adaptation (UDA) based cross-scene remote sensing image classification has recently become an appealing research topic, since it is a valid solution to unsupervised scene classification by exploiting well-labeled data from another scene. Despite its good performance in reducing domain shifts, UDA in multisource data scenarios is hindered by several critical challenges. The first one is the heterogeneity inherent in multisource data complicates domain alignment. The second challenge is the incomplete representation of feature distribution caused by the neglect of the contribution from global information. The third challenge is the inaccuracies in alignment due to errors in establishing target domain conditional distributions. Since UDA does not guarantee the complete consistency of the distribution of the two domains, networks using simple classifiers are still affected by domain shifts, resulting in poor performance. In this paper, we propose a graph embedding interclass relation-aware adaptive network (GeIraA-Net) for unsupervised classification of multi-source remote sensing data, which facilitates knowledge transfer at the class level for two domains by leveraging aligned features to perceive inter-class relation. More specifically, a graph-based progressive hierarchical feature extraction network is constructed, capable of capturing both local and global features of multisource data, thereby consolidating comprehensive domain information within a unified feature space. To deal with the imprecise alignment of data distribution, a joint de-scrambling alignment strategy is designed to utilize the features obtained by a three-step pseudo-label generation module for more delicate domain calibration. Moreover, an adaptive inter-class topology based classifier is constructed to further improve the classification accuracy by making the classifier domain adaptive at the category level. The experimental results show that GeIraA-Net has significant advantages over the current state-of-the-art cross-scene classification methods.
Förderung
- National Natural Science Foundation of China
- Youth Innovation Team of Shaanxi Universities
- China Postdoctoral Science Foundation
- Young Talent Fund of Xi’an Association for Science and Technology
- Guangdong Basic and Applied Basic Research Foundation
Zitieren
APA
Yang, T., Xiao, S., Qu, J., Dong, W., Du, Q., & Li, Y. (2024). Graph Embedding Interclass Relation-Aware Adaptive Network for Cross-Scene Classification of Multisource Remote Sensing Data. IEEE Transactions on Image Processing, 33, 4459-4474. https://doi.org/10.1109/tip.2024.3422881
Vancouver
Yang T, Xiao S, Qu J, Dong W, Du Q, Li Y. Graph Embedding Interclass Relation-Aware Adaptive Network for Cross-Scene Classification of Multisource Remote Sensing Data. IEEE Transactions on Image Processing. 2024;33:4459-4474. doi:10.1109/tip.2024.3422881
BibTeX
@article{Yang2024,
author = {Yang, Teng and Xiao, Song and Qu, Jiahui and Dong, Wenqian and Du, Qian and Li, Yunsong},
title = {Graph Embedding Interclass Relation-Aware Adaptive Network for Cross-Scene Classification of Multisource Remote Sensing Data},
journal = {IEEE Transactions on Image Processing},
year = {2024},
volume = {33},
pages = {4459--4474},
doi = {10.1109/tip.2024.3422881}
}
EUVIMED