# Can We Find Neurons that Cause Unrealistic Images in Deep Generative Networks?

arXiv: https://arxiv.org/abs/2201.06346 · HTML: https://mlsanity.com/paper/2201.06346/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 37 references that are in the map.
- First posted on arXiv 17 Jan 2022.

## Builds on (most cited first, 19 of 19)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [Improved Precision and Recall Metric for Assessing Generative Models](https://mlsanity.com/paper/1904.06991/) (2019)
- [Stability](https://mlsanity.com/paper/1310.0150/) (2013)
- [Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis](https://mlsanity.com/paper/1911.09267/) (2019)
- [Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing](https://mlsanity.com/paper/2104.14754/) (2021)
- [A Latent Transformer for Disentangled Face Editing in Images and Videos](https://mlsanity.com/paper/2106.11895/) (2021)
- [SofGAN: A Portrait Image Generator with Dynamic Styling](https://mlsanity.com/paper/2007.03780/) (2020)
- [BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generation](https://mlsanity.com/paper/2110.11728/) (2021)
- [On the Units of GANs (Extended Abstract)](https://mlsanity.com/paper/1901.09887/) (2019)
- [Attentive Semantic Exploring for Manipulated Face Detection](https://mlsanity.com/paper/2005.02958/) (2020)
- [Dance In the Wild: Monocular Human Animation with Neural Dynamic Appearance Synthesis](https://mlsanity.com/paper/2111.05916/) (2021)
- [Automatic Correction of Internal Units in Generative Neural Networks](https://mlsanity.com/paper/2104.06118/) (2021)
- [A Benchmarking Initiative for Audio-Domain Music Generation Using the Freesound Loop Dataset](https://mlsanity.com/paper/2108.01576/) (2021)

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

- [Refining Diffusion Planner for Reliable Behavior Synthesis by Automatic Detection of Infeasible Plans](https://mlsanity.com/paper/2310.19427/) (2023)
- [Resisting Stochastic Risks in Diffusion Planners with the Trajectory Aggregation Tree](https://mlsanity.com/paper/2405.17879/) (2024)
- [When a Relation Tells More Than a Concept: Exploring and Evaluating Classifier Decisions with CoReX](https://mlsanity.com/paper/2405.01661/) (2024)

## Abstract (arXiv)

Even though Generative Adversarial Networks (GANs) have shown a remarkable ability to generate high-quality images, GANs do not always guarantee the generation of photorealistic images. Occasionally, they generate images that have defective or unnatural objects, which are referred to as 'artifacts'. Research to investigate why these artifacts emerge and how they can be detected and removed has yet to be sufficiently carried out. To analyze this, we first hypothesize that rarely activated neurons and frequently activated neurons have different purposes and responsibilities for the progress of generating images. In this study, by analyzing the statistics and the roles for those neurons, we empirically show that rarely activated neurons are related to the failure results of making diverse objects and inducing artifacts. In addition, we suggest a correction method, called 'Sequential Ablation', to repair the defective part of the generated images without high computational cost and manual efforts.