# HSIC-InfoGAN: Learning Unsupervised Disentangled Representations by Maximising Approximated Mutual Information

arXiv: https://arxiv.org/abs/2208.03563 · HTML: https://mlsanity.com/paper/2208.03563/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 26 references that are in the map.
- First posted on arXiv 6 Aug 2022.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Normalizing Flows for Probabilistic Modeling and Inference](https://mlsanity.com/paper/1912.02762/) (2019)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets](https://mlsanity.com/paper/1606.03657/) (2016)
- [Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1804.04732/) (2018)
- [MINE: Mutual Information Neural Estimation](https://mlsanity.com/paper/1801.04062/) (2018)
- [Conditional Image Synthesis With Auxiliary Classifier GANs](https://mlsanity.com/paper/1610.09585/) (2016)
- [Contrastive learning of global and local features for medical image segmentation with limited annotations](https://mlsanity.com/paper/2006.10511/) (2020)
- [Toward Multimodal Image-to-Image Translation](https://mlsanity.com/paper/1711.11586/) (2017)
- [Diffusion Causal Models for Counterfactual Estimation](https://mlsanity.com/paper/2202.10166/) (2022)
- [The HSIC Bottleneck: Deep Learning without Back-Propagation](https://mlsanity.com/paper/1908.01580/) (2019)
- [Unsupervised Learning of Compositional Energy Concepts](https://mlsanity.com/paper/2111.03042/) (2021)
- [Disentangled Representation Learning in Cardiac Image Analysis](https://mlsanity.com/paper/1903.09467/) (2019)
- [Learning Disentangled Representations in the Imaging Domain](https://mlsanity.com/paper/2108.12043/) (2021)
- [Semi-supervised Meta-learning with Disentanglement for Domain-generalised Medical Image Segmentation](https://mlsanity.com/paper/2106.13292/) (2021)
- [Disentangled Representations for Domain-generalized Cardiac Segmentation](https://mlsanity.com/paper/2008.11514/) (2020)
- [Controllable cardiac synthesis via disentangled anatomy arithmetic](https://mlsanity.com/paper/2107.01748/) (2021)

## Built on by (most cited first, 1 of 1)

- [ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models](https://mlsanity.com/paper/2605.24011/) (2026)

## Abstract (arXiv)

Learning disentangled representations requires either supervision or the introduction of specific model designs and learning constraints as biases. InfoGAN is a popular disentanglement framework that learns unsupervised disentangled representations by maximising the mutual information between latent representations and their corresponding generated images. Maximisation of mutual information is achieved by introducing an auxiliary network and training with a latent regression loss. In this short exploratory paper, we study the use of the Hilbert-Schmidt Independence Criterion (HSIC) to approximate mutual information between latent representation and image, termed HSIC-InfoGAN. Directly optimising the HSIC loss avoids the need for an additional auxiliary network. We qualitatively compare the level of disentanglement in each model, suggest a strategy to tune the hyperparameters of HSIC-InfoGAN, and discuss the potential of HSIC-InfoGAN for medical applications.