# Class Balancing GAN with a Classifier in the Loop

arXiv: https://arxiv.org/abs/2106.09402 · HTML: https://mlsanity.com/paper/2106.09402/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 36 references that are in the map.
- First posted on arXiv 17 Jun 2021.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [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)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [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)
- [LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop](https://mlsanity.com/paper/1506.03365/) (2015)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [Self-Attention Generative Adversarial Networks](https://mlsanity.com/paper/1805.08318/) (2018)
- [Large-Scale Long-Tailed Recognition in an Open World](https://mlsanity.com/paper/1904.05160/) (2019)
- [Wasserstein GAN](https://mlsanity.com/paper/1701.07875/) (2017)
- [Conditional Image Synthesis With Auxiliary Classifier GANs](https://mlsanity.com/paper/1610.09585/) (2016)
- [cGANs with Projection Discriminator](https://mlsanity.com/paper/1802.05637/) (2018)
- [The relativistic discriminator: a key element missing from standard GAN](https://mlsanity.com/paper/1807.00734/) (2018)
- [Modulating early visual processing by language](https://mlsanity.com/paper/1707.00683/) (2017)
- [Classification Accuracy Score for Conditional Generative Models](https://mlsanity.com/paper/1905.10887/) (2019)
- [Consistency Regularization for Generative Adversarial Networks](https://mlsanity.com/paper/1910.12027/) (2019)
- [Generative Adversarial Minority Oversampling](https://mlsanity.com/paper/1903.09730/) (2019)
- [High-Fidelity Image Generation With Fewer Labels](https://mlsanity.com/paper/1903.02271/) (2019)
- [LOGAN: Latent Optimisation for Generative Adversarial Networks](https://mlsanity.com/paper/1912.00953/) (2019)
- [On Relativistic f-Divergences](https://mlsanity.com/paper/1901.02474/) (2019)
- [ContraGAN: Contrastive Learning for Conditional Image Generation](https://mlsanity.com/paper/2006.12681/) (2020)

## Built on by (most cited first, 17 of 17)

- [Class-Balancing Diffusion Models](https://mlsanity.com/paper/2305.00562/) (2023)
- [Ultra-High-Resolution Detector Simulation with Intra-Event Aware GAN and Self-Supervised Relational Reasoning](https://mlsanity.com/paper/2303.08046/) (2023)
- [Label-Noise Robust Diffusion Models](https://mlsanity.com/paper/2402.17517/) (2024)
- [Improving GANs for Long-Tailed Data through Group Spectral Regularization](https://mlsanity.com/paper/2208.09932/) (2022)
- [DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets](https://mlsanity.com/paper/2404.02900/) (2024)
- [NoisyTwins: Class-Consistent and Diverse Image Generation through StyleGANs](https://mlsanity.com/paper/2304.05866/) (2023)
- [medXGAN: Visual Explanations for Medical Classifiers through a Generative Latent Space](https://mlsanity.com/paper/2204.05376/) (2022)
- [RareGAN: Generating Samples for Rare Classes](https://mlsanity.com/paper/2203.10674/) (2022)
- [Taming the Tail in Class-Conditional GANs: Knowledge Sharing via Unconditional Training at Lower Resolutions](https://mlsanity.com/paper/2402.17065/) (2024)
- [Training Class-Imbalanced Diffusion Model Via Overlap Optimization](https://mlsanity.com/paper/2402.10821/) (2024)
- [Multilabel Classification for Lung Disease Detection: Integrating Deep Learning and Natural Language Processing](https://mlsanity.com/paper/2412.11452/) (2024)
- [Reweighted Flow Matching via Unbalanced OT for Label-free Long-tailed Generation](https://mlsanity.com/paper/2509.25713/) (2025)
- [Why Do Vision Language Models Struggle To Recognize Human Emotions?](https://mlsanity.com/paper/2604.15280/) (2026)
- [Learning from Limited and Imperfect Data](https://mlsanity.com/paper/2411.07229/) (2024)
- [Hybrid Data-Free Knowledge Distillation](https://mlsanity.com/paper/2412.13525/) (2024)
- [Learning from Limited and Imperfect Data](https://mlsanity.com/paper/2507.21205/) (2025)
- [Enhanced Low-Density Region Exploration in Classifier-Guided Diffusion Models Through Modified Reverse Diffusion Sampling](https://mlsanity.com/paper/2606.13347/) (2026)

## Abstract (arXiv)

Generative Adversarial Networks (GANs) have swiftly evolved to imitate increasingly complex image distributions. However, majority of the developments focus on performance of GANs on balanced datasets. We find that the existing GANs and their training regimes which work well on balanced datasets fail to be effective in case of imbalanced (i.e. long-tailed) datasets. In this work we introduce a novel theoretically motivated Class Balancing regularizer for training GANs. Our regularizer makes use of the knowledge from a pre-trained classifier to ensure balanced learning of all the classes in the dataset. This is achieved via modelling the effective class frequency based on the exponential forgetting observed in neural networks and encouraging the GAN to focus on underrepresented classes. We demonstrate the utility of our regularizer in learning representations for long-tailed distributions via achieving better performance than existing approaches over multiple datasets. Specifically, when applied to an unconditional GAN, it improves the FID from 13.03 to 9.01 on the long-tailed iNaturalist-2019 dataset.