# Transformer for Multitemporal Hyperspectral Image Unmixing

arXiv: https://arxiv.org/abs/2407.10427 · HTML: https://mlsanity.com/paper/2407.10427/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 71 references that are in the map.
- First posted on arXiv 15 Jul 2024.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [Deep Hyperspectral Unmixing using Transformer Network](https://mlsanity.com/paper/2203.17076/) (2022)
- [Binary Change Guided Hyperspectral Multiclass Change Detection](https://mlsanity.com/paper/2112.04493/) (2021)
- [Hyperspectral Image Unmixing with Endmember Bundles and Group Sparsity Inducing Mixed Norms](https://mlsanity.com/paper/1805.10232/) (2018)
- [Spectral Variability Aware Blind Hyperspectral Image Unmixing Based on Convex Geometry](https://mlsanity.com/paper/1904.03888/) (2019)
- [Entropic Descent Archetypal Analysis for Blind Hyperspectral Unmixing](https://mlsanity.com/paper/2209.11002/) (2022)
- [Dynamical spectral unmixing of multitemporal hyperspectral images](https://mlsanity.com/paper/1510.04238/) (2015)
- [Kalman Filtering and Expectation Maximization for Multitemporal Spectral Unmixing](https://mlsanity.com/paper/2001.00425/) (2020)
- [Dynamical Hyperspectral Unmixing with Variational Recurrent Neural Networks](https://mlsanity.com/paper/2303.10566/) (2023)
- [A Data Dependent Multiscale Model for Hyperspectral Unmixing With Spectral Variability](https://mlsanity.com/paper/1808.01047/) (2018)
- [Online Unmixing of Multitemporal Hyperspectral Images accounting for Spectral Variability](https://mlsanity.com/paper/1510.05893/) (2015)
- [Hyperspectral Pixel Unmixing with Latent Dirichlet Variational Autoencoder](https://mlsanity.com/paper/2203.01327/) (2022)
- [Illumination invariant hyperspectral image unmixing based on a digital surface model](https://mlsanity.com/paper/2007.11770/) (2020)
- [A Hierarchical Bayesian Model Accounting for Endmember Variability and Abrupt Spectral Changes to Unmix Multitemporal Hyperspectral Images](https://mlsanity.com/paper/1609.07792/) (2016)
- [Pixel-to-Abundance Translation: Conditional Generative Adversarial Networks Based on Patch Transformer for Hyperspectral Unmixing](https://mlsanity.com/paper/2312.13127/) (2023)
- [SAWU-Net: Spatial Attention Weighted Unmixing Network for Hyperspectral Images](https://mlsanity.com/paper/2304.11320/) (2023)

## Built on by (most cited first, 4 of 4)

- [FishBEV: Distortion-Resilient Bird's Eye View Segmentation with Surround-View Fisheye Cameras](https://mlsanity.com/paper/2509.13681/) (2025)
- [Multitemporal Latent Dynamical Framework for Hyperspectral Images Unmixing](https://mlsanity.com/paper/2505.20902/) (2025)
- [On the use of Graphs for Satellite Image Time Series](https://mlsanity.com/paper/2505.16685/) (2025)
- [A Copula-Guided Temporal Dependency Method for Multitemporal Hyperspectral Images Unmixing](https://mlsanity.com/paper/2509.11096/) (2025)

## Abstract (arXiv)

Multitemporal hyperspectral image unmixing (MTHU) holds significant importance in monitoring and analyzing the dynamic changes of surface. However, compared to single-temporal unmixing, the multitemporal approach demands comprehensive consideration of information across different phases, rendering it a greater challenge. To address this challenge, we propose the Multitemporal Hyperspectral Image Unmixing Transformer (MUFormer), an end-to-end unsupervised deep learning model. To effectively perform multitemporal hyperspectral image unmixing, we introduce two key modules: the Global Awareness Module (GAM) and the Change Enhancement Module (CEM). The Global Awareness Module computes self-attention across all phases, facilitating global weight allocation. On the other hand, the Change Enhancement Module dynamically learns local temporal changes by comparing endmember changes between adjacent phases. The synergy between these modules allows for capturing semantic information regarding endmember and abundance changes, thereby enhancing the effectiveness of multitemporal hyperspectral image unmixing. We conducted experiments on one real dataset and two synthetic datasets, demonstrating that our model significantly enhances the effect of multitemporal hyperspectral image unmixing.