Prototypical Unknown-Aware Multiview Consistency Learning for Open-Set Cross-Domain Remote Sensing Image Classification
IEEE Transactions on Geoscience and Remote Sensing · 2024 · 62 · 1-16
DOI: 10.1109/tgrs.2024.3476151 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Geoscience and Remote Sensing, 2024. Verfasst von Xiaokang Zhang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 64 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Open Fund of Hubei Luojia Laboratory.
Abstract (Originalsprache)
Developing a cross-domain classification model for remote sensing images has drawn significant attention in the literature. By leveraging the open-set unsupervised domain adaptation (UDA) technique, the generalization performance of deep learning models has been improved with the capability to recognize unknown categories. However, it remains challenging to explore distribution patterns in the target domain using uncertain category-wise supervision from unlabeled datasets while reducing negative transfer caused by unknown samples. To develop a robust open-set UDA framework, this article presents prototypical unknown-aware multiview consistency learning (PUMCL) designed for remote sensing scene classification across heterogeneous domains. Specifically, it employs a consistency learning scheme with multiview and multilevel perturbations to improve feature learning from unlabeled target samples. An entropy separation strategy is utilized to facilitate open-set detection and recognition during adaptation, enabling unknown-aware feature alignment. Furthermore, the introduction of prototypical constraints optimizes pseudo-label generation through online denoising and promotes a compact category-wise feature subspace for improved class separation across domains. Experiments conducted on six cross-domain scenarios using AID, NWPU, and UCMD datasets demonstrate the method’s superior performance compared to nine state-of-the-art approaches, achieving a gain of 4.5% to 21.2% in mIoU. More importantly, it shows promising class separability with clear boundaries between different classes and compact clustering of unknown samples in the feature space. The source code will be available at https://github.com/zxk688.
Förderung
- National Natural Science Foundation of China
- Open Fund of Hubei Luojia Laboratory
Zitieren
APA
Zhang, X., Wu, W., Zhang, M., Yu, W., & Ghamisi, P. (2024). Prototypical Unknown-Aware Multiview Consistency Learning for Open-Set Cross-Domain Remote Sensing Image Classification. IEEE Transactions on Geoscience and Remote Sensing, 62, 1-16. https://doi.org/10.1109/tgrs.2024.3476151
Vancouver
Zhang X, Wu W, Zhang M, Yu W, Ghamisi P. Prototypical Unknown-Aware Multiview Consistency Learning for Open-Set Cross-Domain Remote Sensing Image Classification. IEEE Transactions on Geoscience and Remote Sensing. 2024;62:1-16. doi:10.1109/tgrs.2024.3476151
BibTeX
@article{Zhang2024,
author = {Zhang, Xiaokang and Wu, Wanjing and Zhang, Mi and Yu, Weikang and Ghamisi, Pedram},
title = {Prototypical Unknown-Aware Multiview Consistency Learning for Open-Set Cross-Domain Remote Sensing Image Classification},
journal = {IEEE Transactions on Geoscience and Remote Sensing},
year = {2024},
volume = {62},
pages = {1--16},
doi = {10.1109/tgrs.2024.3476151}
}
EUVIMED