# Deep Deterministic Independent Component Analysis for Hyperspectral Unmixing

arXiv: https://arxiv.org/abs/2202.02951 · HTML: https://mlsanity.com/paper/2202.02951/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 32 references that are in the map.
- First posted on arXiv 7 Feb 2022.

## Builds on (most cited first, 10 of 10)

- [MINE: Mutual Information Neural Estimation](https://mlsanity.com/paper/1801.04062/) (2018)
- [Invariant Information Clustering for Unsupervised Image Classification and Segmentation](https://mlsanity.com/paper/1807.06653/) (2018)
- [Isolating Sources of Disentanglement in Variational Autoencoders](https://mlsanity.com/paper/1802.04942/) (2018)
- [Hyperspectral Unmixing: Ground Truth Labeling, Datasets, Benchmark Performances and Survey](https://mlsanity.com/paper/1708.05125/) (2017)
- [Learning Independent Features with Adversarial Nets for Non-linear ICA](https://mlsanity.com/paper/1710.05050/) (2017)
- [Measuring Dependence with Matrix-based Entropy Functional](https://mlsanity.com/paper/2101.10160/) (2021)
- [Multivariate Extension of Matrix-based Renyi's α-order Entropy Functional](https://mlsanity.com/paper/1808.07912/) (2018)
- [Gradient-based Training of Slow Feature Analysis by Differentiable Approximate Whitening](https://mlsanity.com/paper/1808.08833/) (2018)
- [Constrained Nonnegative Matrix Factorization for Blind Hyperspectral Unmixing incorporating Endmember Independence](https://mlsanity.com/paper/2003.01041/) (2020)
- [Learning gradient-based ICA by neurally estimating mutual information](https://mlsanity.com/paper/1904.09858/) (2019)

## Built on by (most cited first, 3 of 3)

- [An Independence-promoting Loss for Music Generation with Language Models](https://mlsanity.com/paper/2406.02315/) (2024)
- [Deep Deterministic Nonlinear ICA via Total Correlation Minimization with Matrix-Based Entropy Functional](https://mlsanity.com/paper/2601.00904/) (2025)
- [Supervised Stochastic Gradient Algorithms for Multi-Trial Source Separation](https://mlsanity.com/paper/2508.20618/) (2025)

## Abstract (arXiv)

We develop a new neural network based independent component analysis (ICA) method by directly minimizing the dependence amongst all extracted components. Using the matrix-based R'enyi's α-order entropy functional, our network can be directly optimized by stochastic gradient descent (SGD), without any variational approximation or adversarial training. As a solid application, we evaluate our ICA in the problem of hyperspectral unmixing (HU) and refute a statement that "ICA does not play a role in unmixing hyperspectral data", which was initially suggested by citenascimento2005does. Code and additional remarks of our DDICA is available at https://github.com/hongmingli1995/DDICA.