# Self-Diagnosing GAN: Diagnosing Underrepresented Samples in Generative Adversarial Networks

arXiv: https://arxiv.org/abs/2102.12033 · HTML: https://mlsanity.com/paper/2102.12033/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 62 references that are in the map.
- First posted on arXiv 24 Feb 2021.

## Builds on (most cited first, 30 of 43)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Improved Precision and Recall Metric for Assessing Generative Models](https://mlsanity.com/paper/1904.06991/) (2019)
- [InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets](https://mlsanity.com/paper/1606.03657/) (2016)
- [Which Training Methods for GANs do actually Converge?](https://mlsanity.com/paper/1801.04406/) (2018)
- [Generative Image Inpainting with Contextual Attention](https://mlsanity.com/paper/1801.07892/) (2018)
- [Training Region-based Object Detectors with Online Hard Example Mining](https://mlsanity.com/paper/1604.03540/) (2016)
- [Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics](https://mlsanity.com/paper/2009.10795/) (2020)
- [Making Convolutional Networks Shift-Invariant Again](https://mlsanity.com/paper/1904.11486/) (2019)
- [Deep multi-scale video prediction beyond mean square error](https://mlsanity.com/paper/1511.05440/) (2015)
- [Unrolled Generative Adversarial Networks](https://mlsanity.com/paper/1611.02163/) (2016)
- [VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning](https://mlsanity.com/paper/1705.07761/) (2017)
- [Active Bias: Training More Accurate Neural Networks by Emphasizing High Variance Samples](https://mlsanity.com/paper/1704.07433/) (2017)
- [BEGAN: Boundary Equilibrium Generative Adversarial Networks](https://mlsanity.com/paper/1703.10717/) (2017)
- [When Do Curricula Work?](https://mlsanity.com/paper/2012.03107/) (2020)
- [PacGAN: The power of two samples in generative adversarial networks](https://mlsanity.com/paper/1712.04086/) (2017)
- [Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting](https://mlsanity.com/paper/1906.09531/) (2019)
- [Banach Wasserstein GAN](https://mlsanity.com/paper/1806.06621/) (2018)
- [Variational Approaches for Auto-Encoding Generative Adversarial Networks](https://mlsanity.com/paper/1706.04987/) (2017)

## Built on by (most cited first, 13 of 13)

- [EditGAN: High-Precision Semantic Image Editing](https://mlsanity.com/paper/2111.03186/) (2021)
- [Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence](https://mlsanity.com/paper/2111.01177/) (2021)
- [Data Valuation Without Training of a Model](https://mlsanity.com/paper/2301.00930/) (2023)
- [Assessing Sample Quality via the Latent Space of Generative Models](https://mlsanity.com/paper/2407.15171/) (2024)
- [Deep Data Augmentation for Weed Recognition Enhancement: A Diffusion Probabilistic Model and Transfer Learning Based Approach](https://mlsanity.com/paper/2210.09509/) (2022)
- [Towards Mode Balancing of Generative Models via Diversity Weights](https://mlsanity.com/paper/2304.11961/) (2023)
- [Breaking the Spurious Causality of Conditional Generation via Fairness Intervention with Corrective Sampling](https://mlsanity.com/paper/2212.02090/) (2022)
- [A Unified Framework for Generative Data Augmentation: A Comprehensive Survey](https://mlsanity.com/paper/2310.00277/) (2023)
- [Bt-GAN: Generating Fair Synthetic Healthdata via Bias-transforming Generative Adversarial Networks](https://mlsanity.com/paper/2404.13634/) (2024)
- [Unleashing the Potential of Synthetic Images: A Study on Histopathology Image Classification](https://mlsanity.com/paper/2409.16002/) (2024)
- [Will the Inclusion of Generated Data Amplify Bias Across Generations in Future Image Classification Models?](https://mlsanity.com/paper/2410.10160/) (2024)
- [infoVerse: A Universal Framework for Dataset Characterization with Multidimensional Meta-information](https://mlsanity.com/paper/2305.19344/) (2023)
- [Learning Nonparametric High-Dimensional Generative Models: The Empirical-Beta-Copula Autoencoder](https://mlsanity.com/paper/2309.09916/) (2023)

## Abstract (arXiv)

Despite remarkable performance in producing realistic samples, Generative Adversarial Networks (GANs) often produce low-quality samples near low-density regions of the data manifold, e.g., samples of minor groups. Many techniques have been developed to improve the quality of generated samples, either by post-processing generated samples or by pre-processing the empirical data distribution, but at the cost of reduced diversity. To promote diversity in sample generation without degrading the overall quality, we propose a simple yet effective method to diagnose and emphasize underrepresented samples during training of a GAN. The main idea is to use the statistics of the discrepancy between the data distribution and the model distribution at each data instance. Based on the observation that the underrepresented samples have a high average discrepancy or high variability in discrepancy, we propose a method to emphasize those samples during training of a GAN. Our experimental results demonstrate that the proposed method improves GAN performance on various datasets, and it is especially effective in improving the quality and diversity of sample generation for minor groups.