CTNet: an efficient coupled transformer network for robust hyperspectral unmixing

This study introduces the coupled transformer Network (CTNet), an architecture designed to enhance the robustness and effectiveness of hyperspectral unmixing (HSU) tasks, addressing key limitations of traditional autoencoder (AE) frameworks. Traditional AEs, consisting of an encoder and a decoder, e...

Full description

Saved in:
Bibliographic Details
Published in:International journal of remote sensing Vol. 45; no. 17; pp. 5679 - 5712
Main Authors: Meng, Fanlei, Sun, Haixin, Li, Jie, Xu, Tingfa
Format: Journal Article
Language:English
Published: London Taylor & Francis 01.09.2024
Taylor & Francis Ltd
Subjects:
Abundance
Artificial neural networks
Coders
Coupled transformer network
cross-attention
data collection
Effectiveness
Estimates
image analysis
Pixels
Reconstruction
robust hyperspectral unmixing
Robustness (mathematics)
spectral variability
transcription loss
Transformers
uncertainty
ISSN:0143-1161, 1366-5901, 1366-5901
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This study introduces the coupled transformer Network (CTNet), an architecture designed to enhance the robustness and effectiveness of hyperspectral unmixing (HSU) tasks, addressing key limitations of traditional autoencoder (AE) frameworks. Traditional AEs, consisting of an encoder and a decoder, effectively learn and reconstruct low-dimensional abundance relationships from high-dimensional hyperspectral data but often struggle with spectral variability (SV) and spatial correlations, which can lead to uncertainty in the resulting abundance estimates. CTNet improves upon these limitations by incorporating a two-stream half-Siamese network with an additional encoder trained on pseudo-pure pixels, and further integrates a cross-attention module to leverage global information. This configuration not only guides the AE towards more accurate abundance estimates by directly addressing SV, but also enhances the network's ability to capture complex spectral information. To minimize the typical reconstruction errors associated with AEs, a transcription loss constraint is applied, which preserves essential details and material-related information often lost during pixel-level reconstruction. Experimental validation on synthetic and three widely-used datasets confirms that CTNet outperforms several state-of-the-art methods, providing a more robust and effective solution for HSU challenges.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0143-1161
1366-5901
1366-5901
DOI:10.1080/01431161.2024.2371084