# Disentangled representations: towards interpretation of sex determination from hip bone

arXiv: https://arxiv.org/abs/2112.09414 · HTML: https://mlsanity.com/paper/2112.09414/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 56 references that are in the map.
- First posted on arXiv 17 Dec 2021.

## Builds on (most cited first, 30 of 30)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/1711.09020/) (2017)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [Semi-Supervised Learning with Deep Generative Models](https://mlsanity.com/paper/1406.5298/) (2014)
- [DualGAN: Unsupervised Dual Learning for Image-to-Image Translation](https://mlsanity.com/paper/1704.02510/) (2017)
- [Generating 3D faces using Convolutional Mesh Autoencoders](https://mlsanity.com/paper/1807.10267/) (2018)
- [Understanding Deep Networks via Extremal Perturbations and Smooth Masks](https://mlsanity.com/paper/1910.08485/) (2019)
- [Isolating Sources of Disentanglement in Variational Autoencoders](https://mlsanity.com/paper/1802.04942/) (2018)
- [Invertible Conditional GANs for image editing](https://mlsanity.com/paper/1611.06355/) (2016)
- [Fader Networks: Manipulating Images by Sliding Attributes](https://mlsanity.com/paper/1706.00409/) (2017)
- [Attribute2Image: Conditional Image Generation from Visual Attributes](https://mlsanity.com/paper/1512.00570/) (2015)
- [Auxiliary Deep Generative Models](https://mlsanity.com/paper/1602.05473/) (2016)
- [Learning Disentangled Representations with Semi-Supervised Deep Generative Models](https://mlsanity.com/paper/1706.00400/) (2017)
- [Understanding Neural Networks via Feature Visualization: A survey](https://mlsanity.com/paper/1904.08939/) (2019)
- [Simple and Effective VAE Training with Calibrated Decoders](https://mlsanity.com/paper/2006.13202/) (2020)
- [Learning Residual Images for Face Attribute Manipulation](https://mlsanity.com/paper/1612.05363/) (2016)
- [Variational AutoEncoder For Regression: Application to Brain Aging Analysis](https://mlsanity.com/paper/1904.05948/) (2019)
- [Capturing Label Characteristics in VAEs](https://mlsanity.com/paper/2006.10102/) (2020)
- [Testing the robustness of attribution methods for convolutional neural networks in MRI-based Alzheimer's disease classification](https://mlsanity.com/paper/1909.08856/) (2019)
- [Deep neural network or dermatologist?](https://mlsanity.com/paper/1908.06612/) (2019)
- [Assessing the validity of saliency maps for abnormality localization in medical imaging](https://mlsanity.com/paper/2006.00063/) (2020)
- [Learning Disentangled Representations with Reference-Based Variational Autoencoders](https://mlsanity.com/paper/1901.08534/) (2019)
- [Graph-Based Generative Representation Learning of Semantically and Behaviorally Augmented Floorplans](https://mlsanity.com/paper/2012.04735/) (2020)
- [Hubless keypoint-based 3D deformable groupwise registration](https://mlsanity.com/paper/1809.03951/) (2018)

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

- [Graph-Convolutional-Beta-VAE for Synthetic Abdominal Aorta Aneurysm Generation](https://mlsanity.com/paper/2506.13628/) (2025)

## Abstract (arXiv)

By highlighting the regions of the input image that contribute the most to the decision, saliency maps have become a popular method to make neural networks interpretable. In medical imaging, they are particularly well-suited to explain neural networks in the context of abnormality localization. However, from our experiments, they are less suited to classification problems where the features that allow to distinguish between the different classes are spatially correlated, scattered and definitely non-trivial. In this paper we thus propose a new paradigm for better interpretability. To this end we provide the user with relevant and easily interpretable information so that he can form his own opinion. We use Disentangled Variational Auto-Encoders which latent representation is divided into two components: the non-interpretable part and the disentangled part. The latter accounts for the categorical variables explicitly representing the different classes of interest. In addition to providing the class of a given input sample, such a model offers the possibility to transform the sample from a given class to a sample of another class, by modifying the value of the categorical variables in the latent representation. This paves the way to easier interpretation of class differences. We illustrate the relevance of this approach in the context of automatic sex determination from hip bones in forensic medicine. The features encoded by the model, that distinguish the different classes were found to be consistent with expert knowledge.