An Abundance-Guided Attention Network for Hyperspectral Unmixing
Top Cited Papers
- 19 January 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-14
Abstract
Hyperspectral unmixing is a vibrant research field that focuses on the task of decomposing mixed pixels into a collection of pure spectral signatures, known as endmembers, along with their corresponding fractional abundances. Conventional unmixing algorithms often need to combine two techniques, namely endmember extraction and abundance estimation, to accomplish the unmixing task. Recently, deep learning (DL) has succeeded in the field of hyperspectral unmixing due to its strong feature learning and data-fitting capabilities. By extracting the output and weight of a particular layer as abundance maps and endmember signatures, available DL methods can directly unmix hyperspectral images. However, to improve the performance of spectral unmixing, such available DL methods frequently employ the results of endmember extraction algorithms—in most cases, the well-known vertex component analysis (VCA)—as the initial weights, which leads to significant limitations in their performance: 1) the unmixing results are heavily dependent on the initialization given by VCA and 2) the randomness of VCA is passed to the unmixing network. In this article, we design a new method called abundance-guided spectral and spatial network (A2SN) that not only skips the weights to extract endmember features directly from the network, but also estimates the abundance maps and reconstructs images directly. In particular, the proposed A2SN employs different kernels to capture spectral and spatial information. We also propose an abundance-guided attention spectral and spatial attention network (A2SAN) for hyperspectral unmixing by integrating attention mechanisms into A2SN. As a result, A2SAN is a completely innovative unmixing method that employs attention and reconstruction directly for hyperspectral unmixing, rather than just as modules for information extraction. Most importantly, both A2SN and A2SAN use a weighted summation of the feature maps to reconstruct the image and increase the noise immunity of the network. Experimental results, conducted on both synthetic and real datasets, demonstrate the effectiveness and superiority of A2SN and A2SAN over state-of-the-art unmixing methods. Our full code is released at https://github.com/xuanwentao/A2SN-and-A2SAN for public evaluation.Keywords
Funding Information
- Consejería de Economía, Ciencia y Agenda Digital of the Junta de Extremadura and the European Regional Development Fund (ERDF) of the European Union (GR21040)
- Spanish Ministerio de Ciencia e Innovación (PID2019-110315RB-I00 (APRISA))
- Taishan Scholar Project
- China Scholarship Council (201906450027)
This publication has 59 references indexed in Scilit:
- AMCD: an accurate deep learning-based metallic corrosion detector for MAV-based real-time visual inspectionJournal of Ambient Intelligence and Humanized Computing, 2021
- Low rank and collaborative representation for hyperspectral anomaly detection via robust dictionary constructionISPRS Journal of Photogrammetry and Remote Sensing, 2020
- Deep Learning in Hyperspectral Unmixing: A Review2020
- Spectral-Spatial Hyperspectral Unmixing Using Multitask LearningIEEE Access, 2019
- Hyperspectral Unmixing Using a Neural Network AutoencoderIEEE Access, 2018
- A Novel Spectral-Unmixing-Based Green Algae Area Estimation Method for GOCI DataIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016
- Deep Residual Learning for Image Recognition2016
- A Review of Nonlinear Hyperspectral Unmixing MethodsIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014
- Hyperspectral Unmixing Overview: Geometrical, Statistical, and Sparse Regression-Based ApproachesIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2012
- How many principal components? stopping rules for determining the number of non-trivial axes revisitedComputational Statistics & Data Analysis, 2005