# Label-Noise Robust Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1811.11165 · HTML: https://mlsanity.com/paper/1811.11165/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Nov 2018.

## Built on by (most cited first, 22 of 22)

- [Regularizing Generative Adversarial Networks under Limited Data](https://mlsanity.com/paper/2104.03310/) (2021)
- [Multimodal Co-learning: Challenges, Applications with Datasets, Recent Advances and Future Directions](https://mlsanity.com/paper/2107.13782/) (2021)
- [Label-Noise Robust Diffusion Models](https://mlsanity.com/paper/2402.17517/) (2024)
- [CoPE: Conditional image generation using Polynomial Expansions](https://mlsanity.com/paper/2104.05077/) (2021)
- [A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities](https://mlsanity.com/paper/2210.08906/) (2022)
- [Slight Corruption in Pre-training Data Makes Better Diffusion Models](https://mlsanity.com/paper/2405.20494/) (2024)
- [Multi-Texture GAN: Exploring the Multi-Scale Texture Translation for Brain MR Images](https://mlsanity.com/paper/2102.07225/) (2021)
- [GLAMI-1M: A Multilingual Image-Text Fashion Dataset](https://mlsanity.com/paper/2211.14451/) (2022)
- [Guiding Noisy Label Conditional Diffusion Models with Score-based Discriminator Correction](https://mlsanity.com/paper/2508.19581/) (2025)
- [LNL+K: Enhancing Learning with Noisy Labels Through Noise Source Knowledge Integration](https://mlsanity.com/paper/2306.11911/) (2023)
- [Robust Learning of Diffusion Models with Extremely Noisy Conditions](https://mlsanity.com/paper/2510.10149/) (2025)
- [Dynamic-Pix2Pix: Noise Injected cGAN for Modeling Input and Target Domain Joint Distributions with Limited Training Data](https://mlsanity.com/paper/2211.08570/) (2022)
- [Fusing Conditional Submodular GAN and Programmatic Weak Supervision](https://mlsanity.com/paper/2312.10366/) (2023)
- [Training Flow Matching Models with Reliable Labels via Self-Purification](https://mlsanity.com/paper/2509.19091/) (2025)
- [Generation and Analysis of Feature-Dependent Pseudo Noise for Training Deep Neural Networks](https://mlsanity.com/paper/2105.10796/) (2021)
- [Generative Modeling Helps Weak Supervision (and Vice Versa)](https://mlsanity.com/paper/2203.12023/) (2022)
- [Robust Remote Sensing Scene Classification with Multi-View Voting and Entropy Ranking](https://mlsanity.com/paper/2301.05858/) (2023)
- [Soft Curriculum for Learning Conditional GANs with Noisy-Labeled and Uncurated Unlabeled Data](https://mlsanity.com/paper/2307.08319/) (2023)
- [ScarceGAN: Discriminative Classification Framework for Rare Class Identification for Longitudinal Data with Weak Prior](https://mlsanity.com/paper/2505.03811/) (2025)
- [Learning Robust Diffusion Models from Imprecise Supervision](https://mlsanity.com/paper/2510.03016/) (2025)
- [Analyzing Training-Free Corruption Detection for Object Detection Datasets](https://mlsanity.com/paper/2606.10666/) (2026)
- [RIVET: Robust Idempotent Voice Attribute Editing](https://mlsanity.com/paper/2606.19629/) (2026)

## Abstract (arXiv)

Generative adversarial networks (GANs) are a framework that learns a generative distribution through adversarial training. Recently, their class-conditional extensions (e.g., conditional GAN (cGAN) and auxiliary classifier GAN (AC-GAN)) have attracted much attention owing to their ability to learn the disentangled representations and to improve the training stability. However, their training requires the availability of large-scale accurate class-labeled data, which are often laborious or impractical to collect in a real-world scenario. To remedy this, we propose a novel family of GANs called label-noise robust GANs (rGANs), which, by incorporating a noise transition model, can learn a clean label conditional generative distribution even when training labels are noisy. In particular, we propose two variants: rAC-GAN, which is a bridging model between AC-GAN and the label-noise robust classification model, and rcGAN, which is an extension of cGAN and solves this problem with no reliance on any classifier. In addition to providing the theoretical background, we demonstrate the effectiveness of our models through extensive experiments using diverse GAN configurations, various noise settings, and multiple evaluation metrics (in which we tested 402 conditions in total). Our code is available at https://github.com/takuhirok/rGAN/.