Multiscale Spectral-Spatial Unmixing Network With Boltzmann-Inspired Adaptive Temperature

Hyperspectral unmixing aims to decompose mixed pixels into endmembers with corresponding abundances. However, while several existing convolutional autoencoder methods usually use fixed convolutional kernels, making it difficult to capture the global context. In addition, due to the huge solution spa...

Full description

Saved in:
Bibliographic Details
Published in:IEEE journal of selected topics in applied earth observations and remote sensing Vol. 18; pp. 20085 - 20097
Main Authors: Wang, Zhixiang, Xu, Jindong, Wei, Guangyi, Wang, Jie, Yan, Yu
Format: Journal Article
Language:English
Published: Piscataway IEEE 2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Autoencoders
Boltzmann distribution
Constraints
convolutional autoencoder (AE)
Convolutional codes
Decoding
Distance
Energy distribution
Euclidean geometry
Feature extraction
Hyperspectral imaging
hyperspectral unmixing (HU)
Image reconstruction
Kernel
multiscale spectral–spatial attention
Particle energy
Pixels
Representation learning
Solution space
Sparsity
Spectral bands
Temperature distribution
Temperature effects
temperature matrix
ISSN:1939-1404, 2151-1535
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Hyperspectral unmixing aims to decompose mixed pixels into endmembers with corresponding abundances. However, while several existing convolutional autoencoder methods usually use fixed convolutional kernels, making it difficult to capture the global context. In addition, due to the huge solution space of unmixing, existing methods usually adopt a consistent sparsity constraint and lack adaptivity. To overcome the above-mentioned limitations, we propose a multiscale spectral-spatial unmixing network with Boltzmann-inspired adaptive temperature. First, the spectral attention block and spatial attention block are designed to capture the dependence between spectral bands and enhance spatial feature extraction, respectively. These are integrated into multiscale spectral-spatial attention blocks with varying convolution kernels, which enable the network to focus on local and global image structures at the same time. Moreover, inspired by the Boltzmann distribution, we introduce a temperature matrix T in the softmax activation to regulate the output sparsity, similar to the effect of temperature on the particle energy distribution. The Euclidean distance and cosine distance between adjacent pixels are used to construct the similarity matrix to capture the spectral difference caused by the amplitude change, and then the T matrix is constructed. The softmax layer is divided by the resulting T matrix, so as to impose sparsity constraints of varying strengths on different areas. Evaluations on simulated and real datasets demonstrate the proposed approach's superiority over state-of-the-art methods.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1939-1404
2151-1535
DOI:10.1109/JSTARS.2025.3594155