Multi-Scale Fusion Maximum Entropy Subspace Clustering for Hyperspectral Band Selection

A novel multi-scale fusion maximum entropy subspace clustering (MFMESC) for hyperspectral image (HSI) band selection is proposed in this paper. Subspace clustering is combined as a self-expression layer with stacked convolutional autoencoder, so that subspace clustering working in linear subspaces c...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE International Geoscience and Remote Sensing Symposium proceedings s. 779 - 782
Hlavní autoři: Ma, Haipeng, Wang, Yulei, Jiang, Liru, Song, Meiping, Yu, Chunyan, Zhao, Enyu
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 17.07.2022
Témata:
Benchmark testing
Data mining
Decoding
Entropy
Geoscience and remote sensing
hyperspectral band selection
Hyperspectral imaging
maximum entropy regularization
multi-scale fusion
stacked convolutional autoencoder
subspace clustering
ISSN:2153-7003
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:A novel multi-scale fusion maximum entropy subspace clustering (MFMESC) for hyperspectral image (HSI) band selection is proposed in this paper. Subspace clustering is combined as a self-expression layer with stacked convolutional autoencoder, so that subspace clustering working in linear subspaces can deal with complicated HSI data with nonlinear characteristics. Multiple fully-connected linear layers are inserted between the encoder layers and their corresponding decoder layers to promote learning more favorable representations for subspace clustering. A multi-scale fusion module is designed to guide the fusion of multi-scale information extracted from different layers to learn a more discriminative self-expression coefficient matrix. Furthermore, the maximum entropy regularization is introduced in the subspace clustering to promote the connectivity within each subspace. Experimental results demonstrate the superiority of the proposed model against state of-the-art methods.
ISSN:2153-7003
DOI:10.1109/IGARSS46834.2022.9884654