# Visual Explanations for Convolutional Neural Networks via Latent Traversal of Generative Adversarial Networks

arXiv: https://arxiv.org/abs/2111.00116 · HTML: https://mlsanity.com/paper/2111.00116/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 5 references that are in the map.
- First posted on arXiv 29 Oct 2021.

## Builds on (most cited first, 3 of 3)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Conditional Image Synthesis With Auxiliary Classifier GANs](https://mlsanity.com/paper/1610.09585/) (2016)
- [Twin Auxiliary Classifiers GAN](https://mlsanity.com/paper/1907.02690/) (2019)

## Built on by (most cited first, 2 of 2)

- [medXGAN: Visual Explanations for Medical Classifiers through a Generative Latent Space](https://mlsanity.com/paper/2204.05376/) (2022)
- [Sound Signal Synthesis with Auxiliary Classifier GAN, COVID-19 cough as an example](https://mlsanity.com/paper/2508.08892/) (2025)

## Abstract (arXiv)

Lack of explainability in artificial intelligence, specifically deep neural networks, remains a bottleneck for implementing models in practice. Popular techniques such as Gradient-weighted Class Activation Mapping (Grad-CAM) provide a coarse map of salient features in an image, which rarely tells the whole story of what a convolutional neural network (CNN) learned. Using COVID-19 chest X-rays, we present a method for interpreting what a CNN has learned by utilizing Generative Adversarial Networks (GANs). Our GAN framework disentangles lung structure from COVID-19 features. Using this GAN, we can visualize the transition of a pair of COVID negative lungs in a chest radiograph to a COVID positive pair by interpolating in the latent space of the GAN, which provides fine-grained visualization of how the CNN responds to varying features within the lungs.