# Visualize and Paint GAN Activations

arXiv: https://arxiv.org/abs/2405.15636 · HTML: https://mlsanity.com/paper/2405.15636/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 12 references that are in the map.
- First posted on arXiv 24 May 2024.

## Builds on (most cited first, 6 of 6)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [What do Vision Transformers Learn? A Visual Exploration](https://mlsanity.com/paper/2212.06727/) (2022)
- [GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentation](https://mlsanity.com/paper/1809.01587/) (2018)
- [Model Stitching and Visualization How GAN Generators can Invert Networks in Real-Time](https://mlsanity.com/paper/2302.02181/) (2023)

## Abstract (arXiv)

We investigate how generated structures of GANs correlate with their activations in hidden layers, with the purpose of better understanding the inner workings of those models and being able to paint structures with unconditionally trained GANs. This gives us more control over the generated images, allowing to generate them from a semantic segmentation map while not requiring such a segmentation in the training data. To this end we introduce the concept of tileable features, allowing us to identify activations that work well for painting.