Unmixing-Guided Convolutional Transformer for Spectral Reconstruction
Remote Sensing · 18.05.2023 · 15 (10) · 2619
DOI: 10.3390/rs15102619 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 18.05.2023. Verfasst von Shiyao Duan und 4 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundamental Research Funds for the Central Universities, state Key Laboratory of Geo-Information Engineering, science and technology on space intelligent control laboratory.
Abstract (Originalsprache)
Deep learning networks based on CNNs or transformers have made progress in spectral reconstruction (SR). However, many methods focus solely on feature extraction, overlooking the interpretability of network design. Additionally, models exclusively based on CNNs or transformers may lose other prior information, sacrificing reconstruction accuracy and robustness. In this paper, we propose a novel Unmixing-Guided Convolutional Transformer Network (UGCT) for interpretable SR. Specifically, transformer and ResBlock components are embedded in Paralleled-Residual Multi-Head Self-Attention (PMSA) to facilitate fine feature extraction guided by the excellent priors of local and non-local information from CNNs and transformers. Furthermore, the Spectral–Spatial Aggregation Module (S2AM) combines the advantages of geometric invariance and global receptive fields to enhance the reconstruction performance. Finally, we exploit a hyperspectral unmixing (HU) mechanism-driven framework at the end of the model, incorporating detailed features from the spectral library using LMM and employing precise endmember features to achieve a more refined interpretation of mixed pixels in HSI at sub-pixel scales. Experimental results demonstrate the superiority of our proposed UGCT, especially in the grss_d f c_2018 dataset, in which UGCT attains an RMSE of 0.0866, outperforming other comparative methods.
Förderung
- Fundamental Research Funds for the Central Universities
- state Key Laboratory of Geo-Information Engineering
- science and technology on space intelligent control laboratory
- Open Research Fund of CAS Key Laboratory of Spectral Imaging Technology
- Wuhu and Xidian University special fund for industry-university-research cooperation
- 111 Project
- Youth Innovation Team of Shaanxi Universities
Zitieren
APA
Duan, S., Li, J., Song, R., Li, Y., & Du, Q. (2023). Unmixing-Guided Convolutional Transformer for Spectral Reconstruction. Remote Sensing, 15(10), 2619. https://doi.org/10.3390/rs15102619
Vancouver
Duan S, Li J, Song R, Li Y, Du Q. Unmixing-Guided Convolutional Transformer for Spectral Reconstruction. Remote Sensing. 2023;15(10):2619. doi:10.3390/rs15102619
BibTeX
@article{Duan2023,
author = {Duan, Shiyao and Li, Jiaojiao and Song, Rui and Li, Yunsong and Du, Qian},
title = {Unmixing-Guided Convolutional Transformer for Spectral Reconstruction},
journal = {Remote Sensing},
year = {2023},
volume = {15},
number = {10},
pages = {2619},
doi = {10.3390/rs15102619}
}
EUVIMED