Non-Negative Latent Factorization Autoencoder for Interpretable Hyperspectral Anomaly Detection
Remote Sensing · 03.11.2026 · 18 (21) · 3781
DOI: 10.3390/rs18213781 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 03.11.2026. Verfasst von Chenyu Shao und 4 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Hyperspectral anomaly detection (HAD) requires effective background modeling while limiting the reconstruction of rare anomalous spectra. Conventional non-negative matrix factorization provides an interpretable endmember–abundance representation but offers limited flexibility for estimating background representations under complex spectral variability, whereas reconstruction-oriented autoencoders provide flexible nonlinear inference but often lack an explicit mixing-model structure. To bridge these two paradigms, we propose a Non-negative Latent Factorization Autoencoder (NLFA) for anomaly-oriented background modeling. NLFA employs a nonlinear encoder to estimate simplex-constrained abundance-like latent coefficients and a linear mixing model (LMM)-consistent linear decoder to represent the dominant background through endmember-like spectral bases. A column-sparse residual is jointly optimized with the latent factorization so that spectral components insufficiently explained by the learned background are retained for anomaly detection, while local spatial smoothness and endmember-diversity constraints regularize the background representation. Experiments on eight benchmark hyperspectral datasets show that NLFA achieves competitive detection performance.
Zitieren
APA
Shao, C., Fang, Z., Song, H., Li, G., & Zheng, J. (2026). Non-Negative Latent Factorization Autoencoder for Interpretable Hyperspectral Anomaly Detection. Remote Sensing, 18(21), 3781. https://doi.org/10.3390/rs18213781
Vancouver
Shao C, Fang Z, Song H, Li G, Zheng J. Non-Negative Latent Factorization Autoencoder for Interpretable Hyperspectral Anomaly Detection. Remote Sensing. 2026;18(21):3781. doi:10.3390/rs18213781
BibTeX
@article{Shao2026,
author = {Shao, Chenyu and Fang, Zhenyu and Song, Heping and Li, Gen and Zheng, Jiangbin},
title = {Non-Negative Latent Factorization Autoencoder for Interpretable Hyperspectral Anomaly Detection},
journal = {Remote Sensing},
year = {2026},
volume = {18},
number = {21},
pages = {3781},
doi = {10.3390/rs18213781}
}
EUVIMED