mlsanityData to 7 Oct 2026

Class Balancing GAN with a Classifier in the Loop

arXiv 2106.09402 ↗First posted 17 Jun 2021cs.LG cs.AI cs.CVcited by 17

Not on the map. Why?

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.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 25 of its 36 references that are in the map. First posted on arXiv 17 Jun 2021.

Builds on

25 of 36 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  3. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  4. 2016Improved Techniques for Training GANscited by 2,938
  5. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  6. 2017Improved Training of Wasserstein GANscited by 2,223
  7. 2014Conditional Generative Adversarial Netscited by 2,152
  8. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  9. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  10. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  11. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
  12. 2018Self-Attention Generative Adversarial Networkscited by 809
13 more
  1. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 704
  2. 2017Wasserstein GANcited by 635
  3. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 562
  4. 2018cGANs with Projection Discriminatorcited by 253
  5. 2018The relativistic discriminator: a key element missing from standard GANcited by 234
  6. 2017Modulating early visual processing by languagecited by 167
  7. 2019Classification Accuracy Score for Conditional Generative Modelscited by 134
  8. 2019Consistency Regularization for Generative Adversarial Networkscited by 134
  9. 2019Generative Adversarial Minority Oversamplingcited by 72
  10. 2019High-Fidelity Image Generation With Fewer Labelscited by 51
  11. 2019LOGAN: Latent Optimisation for Generative Adversarial Networkscited by 42
  12. 2019On Relativistic f-Divergencescited by 10
  13. 2020ContraGAN: Contrastive Learning for Conditional Image Generationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 3; 2024: 7; 2025: 2; 2026: 2.

17 papers.

Sort:

By area:

  1. 2023Class-Balancing Diffusion Modelscited by 47
  2. 2023Ultra-High-Resolution Detector Simulation with Intra-Event Aware GAN and Self-Supervised Relational Reasoningcited by 25
  3. 2024Label-Noise Robust Diffusion Modelscited by 16
  4. 2022Improving GANs for Long-Tailed Data through Group Spectral Regularizationcited by 14
  5. 2024DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasetscited by 14
  6. 2023NoisyTwins: Class-Consistent and Diverse Image Generation through StyleGANscited by 12
  7. 2022medXGAN: Visual Explanations for Medical Classifiers through a Generative Latent Spacecited by 10
  8. 2022RareGAN: Generating Samples for Rare Classescited by 9
  9. 2024Taming the Tail in Class-Conditional GANs: Knowledge Sharing via Unconditional Training at Lower Resolutionscited by 8
  10. 2024Training Class-Imbalanced Diffusion Model Via Overlap Optimizationcited by 5
  11. 2024Multilabel Classification for Lung Disease Detection: Integrating Deep Learning and Natural Language Processingcited by 1
  12. 2025Reweighted Flow Matching via Unbalanced OT for Label-free Long-tailed Generationcited by 1
5 more
  1. 2026Why Do Vision Language Models Struggle To Recognize Human Emotions?cited by 1
  2. 2024Learning from Limited and Imperfect Datacited by 0
  3. 2024Hybrid Data-Free Knowledge Distillationcited by 0
  4. 2025Learning from Limited and Imperfect Datacited by 0
  5. 2026Enhanced Low-Density Region Exploration in Classifier-Guided Diffusion Models Through Modified Reverse Diffusion Samplingcited by 0