Spectral–Spatial Masked Auto-Encoder with Central Pixel Reconstruction for Semi-Supervised Hyperspectral Image Classification
Remote Sensing · 14.05.2026 · 18 (10) · 1571
DOI: 10.3390/rs18101571 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 14.05.2026. Verfasst von Heng Wang und 4 weiteren Autor:innen. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Shandong Province, National Key Laboratory of Smart Farm Technology and Systems, Central Universities.
Abstract (Originalsprache)
Masked auto-encoders (MAEs) have been extensively employed in the field of semi-supervised hyperspectral image classification (HSIC). However, the developed models encounter significant challenges in learning separable representations, as they do not sufficiently prioritize the reconstruction of the central pixel, which hinders their ability to learn separable representations. To address this limitation, we propose spectral–spatial MAE with central pixel reconstruction (SSMAE-CR), a novel self-supervised framework tailored for HSIC. To capture more comprehensive representations, SSMAE-CR employs a dual-branch architecture comprising a spectral MAE with central pixel reconstruction (SpecMAE-CR) and a spatial MAE with central pixel reconstruction (SpatMAE-CR). SpecMAE-CR highlights the significance of central pixel reconstruction by measuring the deviation between the central pixels of reconstructed and original samples. To preserve the holism of the learned latent representations, SpatMAE-CR maps the central pixels of the reconstructed samples back to their original counterparts through the introduction of an additional linear layer. Rigorous comparative experiments conducted on four publicly available datasets fully demonstrate that SSMAE-CR outperforms state-of-the-art methods. Furthermore, we validate the effectiveness of SSMAE-CR by evaluating the mean intra-class and inter-class distances of the learned representations. Experimental results demonstrate that prioritizing central pixel reconstruction yields a statistically significant increase in the mean inter-class distance, suggesting enhanced class separability in the representation space.
Förderung
- Natural Science Foundation of Shandong Province
- National Key Laboratory of Smart Farm Technology and Systems
- Central Universities
Zitieren
APA
Wang, H., Hong, R., Wu, Y., Lin, D., & Wang, L. (2026). Spectral–Spatial Masked Auto-Encoder with Central Pixel Reconstruction for Semi-Supervised Hyperspectral Image Classification. Remote Sensing, 18(10), 1571. https://doi.org/10.3390/rs18101571
Vancouver
Wang H, Hong R, Wu Y, Lin D, Wang L. Spectral–Spatial Masked Auto-Encoder with Central Pixel Reconstruction for Semi-Supervised Hyperspectral Image Classification. Remote Sensing. 2026;18(10):1571. doi:10.3390/rs18101571
BibTeX
@article{Wang2026,
author = {Wang, Heng and Hong, Ruize and Wu, Yanxia and Lin, Dan and Wang, Liguo},
title = {Spectral–Spatial Masked Auto-Encoder with Central Pixel Reconstruction for Semi-Supervised Hyperspectral Image Classification},
journal = {Remote Sensing},
year = {2026},
volume = {18},
number = {10},
pages = {1571},
doi = {10.3390/rs18101571}
}
EUVIMED