# Hyperspectral Pixel Unmixing with Latent Dirichlet Variational Autoencoder

arXiv: https://arxiv.org/abs/2203.01327 · HTML: https://mlsanity.com/paper/2203.01327/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 172 references that are in the map.
- First posted on arXiv 2 Mar 2022.

## Builds on (most cited first, 13 of 13)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Variational Inference: A Review for Statisticians](https://mlsanity.com/paper/1601.00670/) (2016)
- [Pyro: Deep Universal Probabilistic Programming](https://mlsanity.com/paper/1810.09538/) (2018)
- [Variational Autoencoders for Learning Nonlinear Dynamics of Physical Systems](https://mlsanity.com/paper/2012.03448/) (2020)
- [Dirichlet Variational Autoencoder](https://mlsanity.com/paper/1901.02739/) (2019)
- [Dirichlet Graph Variational Autoencoder](https://mlsanity.com/paper/2010.04408/) (2020)
- [Hyperspectral Unmixing: Ground Truth Labeling, Datasets, Benchmark Performances and Survey](https://mlsanity.com/paper/1708.05125/) (2017)
- [Deep Generative Endmember Modeling: An Application to Unsupervised Spectral Unmixing](https://mlsanity.com/paper/1902.05528/) (2019)
- [Hyperspectral Image Unmixing with Endmember Bundles and Group Sparsity Inducing Mixed Norms](https://mlsanity.com/paper/1805.10232/) (2018)
- [A Plug-and-Play Priors Framework for Hyperspectral Unmixing](https://mlsanity.com/paper/2012.13074/) (2020)
- [Spectral Unmixing: A Derivation of the Extended Linear Mixing Model from the Hapke Model](https://mlsanity.com/paper/1903.12089/) (2019)
- [Differentiable Programming for Hyperspectral Unmixing using a Physics-based Dispersion Model](https://mlsanity.com/paper/2007.05996/) (2020)

## Built on by (most cited first, 5 of 5)

- [A Comprehensive Survey for Hyperspectral Image Classification: The Evolution from Conventional to Transformers and Mamba Models](https://mlsanity.com/paper/2404.14955/) (2024)
- [Transformer for Multitemporal Hyperspectral Image Unmixing](https://mlsanity.com/paper/2407.10427/) (2024)
- [SpACNN-LDVAE: Spatial Attention Convolutional Latent Dirichlet Variational Autoencoder for Hyperspectral Pixel Unmixing](https://mlsanity.com/paper/2311.10701/) (2023)
- [Latent Dirichlet Transformer VAE for Hyperspectral Unmixing with Bundled Endmembers](https://mlsanity.com/paper/2511.17757/) (2025)
- [WS-Net: Weak-Signal Representation Learning and Gated Abundance Reconstruction for Hyperspectral Unmixing via State-Space and Weak Signal Attention Fusion](https://mlsanity.com/paper/2603.09037/) (2026)

## Abstract (arXiv)

We present a method for hyperspectral pixel it unmixing. The proposed method assumes that (1) it abundances can be encoded as Dirichlet distributions and (2) spectra of it endmembers can be represented as multivariate Normal distributions. The method solves the problem of abundance estimation and endmember extraction within a variational autoencoder setting where a Dirichlet bottleneck layer models the abundances, and the decoder performs endmember extraction. The proposed method can also leverage transfer learning paradigm, where the model is only trained on synthetic data containing pixels that are linear combinations of one or more endmembers of interest. In this case, we retrieve endmembers (spectra) from the United States Geological Survey Spectral Library. The model thus trained can be subsequently used to perform pixel unmixing on "real data" that contains a subset of the endmembers used to generated the synthetic data. The model achieves state-of-the-art results on several benchmarks: Cuprite, Urban Hydice and Samson. We also present new synthetic dataset, OnTech-HSI-Syn-21, that can be used to study hyperspectral pixel unmixing methods. We showcase the transfer learning capabilities of the proposed model on Cuprite and OnTech-HSI-Syn-21 datasets. In summary, the proposed method can be applied for pixel unmixing a variety of domains, including agriculture, forestry, mineralogy, analysis of materials, healthcare, etc. Additionally, the proposed method eschews the need for labelled data for training by leveraging the transfer learning paradigm, where the model is trained on synthetic data generated using the endmembers present in the "real" data.