DNGAE: Deep Neighborhood Graph Autoencoder for Robust Blind Hyperspectral Unmixing - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

DNGAE: Deep Neighborhood Graph Autoencoder for Robust Blind Hyperspectral Unmixing

Résumé

Recently, Deep Learning (DL)-based unmixing techniques have gained popularity owing to the robust learning of Deep Neural Networks (DNNs). In particular, the Autoencoder (AE) model, as a baseline network for unmixing, performs well in Hyperspectral Unmixing (HU) by automatically learning a new representation and recovering original data. However, patch-wise AE based architecture, which incorporates both spectral and spatial information through convolutional filters may blur the abundance maps due to the fixed kernel shape of the used window size. To cope with the above issue, we propose in this paper a novel methodology based on graph DL called DNGAE. Unlike the pixel-wise or patch-wise Convolutional AE (CAE), our proposed method incorporates the complementary spatial information based on graph spectral similarity. A neighborhood graph based on band correlations is firstly constructed. Then, our method attempts to aggregate similar spectra from the neighboring pixels of a target pixel. Consequently, this leads to better quality of both extracted endmembers and abundances. Extensive experiments performed on two real HSI benchmarks confirm the effectiveness of our proposed method compared to other DL models.
Fichier non déposé

Dates et versions

hal-04219597 , version 1 (27-09-2023)

Identifiants

Citer

Refka Hanachi, Akrem Sellami, Imed Riadh Farah, Mauro Dalla Mura. DNGAE: Deep Neighborhood Graph Autoencoder for Robust Blind Hyperspectral Unmixing. ICCCI 2023- 15th International Conference on Computational Collective Intelligence (ICCCI), Sep 2023, Budapest, Hungary. pp.84-96, ⟨10.1007/978-3-031-41456-5_7⟩. ⟨hal-04219597⟩
46 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More