DTU-Net: A Multi-Scale Dilated Transformer Network for Nonlinear Hyperspectral Unmixing

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wang, ChenTong, Gao, Jincheng, Zhu, Fei, Halimi, Abderrahim, Richard, Cédric
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909526891954176
author Wang, ChenTong
Gao, Jincheng
Zhu, Fei
Halimi, Abderrahim
Richard, Cédric
author_facet Wang, ChenTong
Gao, Jincheng
Zhu, Fei
Halimi, Abderrahim
Richard, Cédric
contents Transformers have shown significant success in hyperspectral unmixing (HU). However, challenges remain. While multi-scale and long-range spatial correlations are essential in unmixing tasks, current Transformer-based unmixing networks, built on Vision Transformer (ViT) or Swin-Transformer, struggle to capture them effectively. Additionally, current Transformer-based unmixing networks rely on the linear mixing model, which lacks the flexibility to accommodate scenarios where nonlinear effects are significant. To address these limitations, we propose a multi-scale Dilated Transformer-based unmixing network for nonlinear HU (DTU-Net). The encoder employs two branches. The first one performs multi-scale spatial feature extraction using Multi-Scale Dilated Attention (MSDA) in the Dilated Transformer, which varies dilation rates across attention heads to capture long-range and multi-scale spatial correlations. The second one performs spectral feature extraction utilizing 3D-CNNs with channel attention. The outputs from both branches are then fused to integrate multi-scale spatial and spectral information, which is subsequently transformed to estimate the abundances. The decoder is designed to accommodate both linear and nonlinear mixing scenarios. Its interpretability is enhanced by explicitly modeling the relationships between endmembers, abundances, and nonlinear coefficients in accordance with the polynomial post-nonlinear mixing model (PPNMM). Experiments on synthetic and real datasets validate the effectiveness of the proposed DTU-Net compared to PPNMM-derived methods and several advanced unmixing networks.
format Preprint
id arxiv_https___arxiv_org_abs_2503_03465
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DTU-Net: A Multi-Scale Dilated Transformer Network for Nonlinear Hyperspectral Unmixing
Wang, ChenTong
Gao, Jincheng
Zhu, Fei
Halimi, Abderrahim
Richard, Cédric
Computer Vision and Pattern Recognition
Image and Video Processing
Transformers have shown significant success in hyperspectral unmixing (HU). However, challenges remain. While multi-scale and long-range spatial correlations are essential in unmixing tasks, current Transformer-based unmixing networks, built on Vision Transformer (ViT) or Swin-Transformer, struggle to capture them effectively. Additionally, current Transformer-based unmixing networks rely on the linear mixing model, which lacks the flexibility to accommodate scenarios where nonlinear effects are significant. To address these limitations, we propose a multi-scale Dilated Transformer-based unmixing network for nonlinear HU (DTU-Net). The encoder employs two branches. The first one performs multi-scale spatial feature extraction using Multi-Scale Dilated Attention (MSDA) in the Dilated Transformer, which varies dilation rates across attention heads to capture long-range and multi-scale spatial correlations. The second one performs spectral feature extraction utilizing 3D-CNNs with channel attention. The outputs from both branches are then fused to integrate multi-scale spatial and spectral information, which is subsequently transformed to estimate the abundances. The decoder is designed to accommodate both linear and nonlinear mixing scenarios. Its interpretability is enhanced by explicitly modeling the relationships between endmembers, abundances, and nonlinear coefficients in accordance with the polynomial post-nonlinear mixing model (PPNMM). Experiments on synthetic and real datasets validate the effectiveness of the proposed DTU-Net compared to PPNMM-derived methods and several advanced unmixing networks.
title DTU-Net: A Multi-Scale Dilated Transformer Network for Nonlinear Hyperspectral Unmixing
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2503.03465