# Robustness of Conditional GANs to Noisy Labels

arXiv: https://arxiv.org/abs/1811.03205 · HTML: https://mlsanity.com/paper/1811.03205/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Nov 2018.

## Built on by (most cited first, 27 of 27)

- [Regularizing Generative Adversarial Networks under Limited Data](https://mlsanity.com/paper/2104.03310/) (2021)
- [Provably End-to-end Label-Noise Learning without Anchor Points](https://mlsanity.com/paper/2102.02400/) (2021)
- [Video Summarization Using Deep Neural Networks: A Survey](https://mlsanity.com/paper/2101.06072/) (2021)
- [Sample Selection with Uncertainty of Losses for Learning with Noisy Labels](https://mlsanity.com/paper/2106.00445/) (2021)
- [Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Network](https://mlsanity.com/paper/2105.13001/) (2021)
- [Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrection](https://mlsanity.com/paper/2111.14932/) (2021)
- [Label-Noise Robust Diffusion Models](https://mlsanity.com/paper/2402.17517/) (2024)
- [Understanding Multimodal LLMs Under Distribution Shifts: An Information-Theoretic Approach](https://mlsanity.com/paper/2502.00577/) (2025)
- [PADDLES: Phase-Amplitude Spectrum Disentangled Early Stopping for Learning with Noisy Labels](https://mlsanity.com/paper/2212.03462/) (2022)
- [Near Optimal Private and Robust Linear Regression](https://mlsanity.com/paper/2301.13273/) (2023)
- [Slight Corruption in Pre-training Data Makes Better Diffusion Models](https://mlsanity.com/paper/2405.20494/) (2024)
- [Dual Projection Generative Adversarial Networks for Conditional Image Generation](https://mlsanity.com/paper/2108.09016/) (2021)
- [On Measuring Fairness in Generative Models](https://mlsanity.com/paper/2310.19297/) (2023)
- [Improved Input Reprogramming for GAN Conditioning](https://mlsanity.com/paper/2201.02692/) (2022)
- [Learning to segment fetal brain tissue from noisy annotations](https://mlsanity.com/paper/2203.14962/) (2022)
- [Guiding Noisy Label Conditional Diffusion Models with Score-based Discriminator Correction](https://mlsanity.com/paper/2508.19581/) (2025)
- [Do We Need to Penalize Variance of Losses for Learning with Label Noise?](https://mlsanity.com/paper/2201.12739/) (2022)
- [Tackling Instance-Dependent Label Noise with Dynamic Distribution Calibration](https://mlsanity.com/paper/2210.05126/) (2022)
- [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)
- [Synthetic Generation and Latent Projection Denoising of Rim Lesions in Multiple Sclerosis](https://mlsanity.com/paper/2505.23353/) (2025)
- [Training Flow Matching Models with Reliable Labels via Self-Purification](https://mlsanity.com/paper/2509.19091/) (2025)
- [Generative Modeling Helps Weak Supervision (and Vice Versa)](https://mlsanity.com/paper/2203.12023/) (2022)
- [Establishment of Neural Networks Robust to Label Noise](https://mlsanity.com/paper/2211.15279/) (2022)
- [Soft Curriculum for Learning Conditional GANs with Noisy-Labeled and Uncurated Unlabeled Data](https://mlsanity.com/paper/2307.08319/) (2023)
- [Close to Reality: Interpretable and Feasible Data Augmentation for Imbalanced Learning](https://mlsanity.com/paper/2603.13927/) (2026)

## Abstract (arXiv)

We study the problem of learning conditional generators from noisy labeled samples, where the labels are corrupted by random noise. A standard training of conditional GANs will not only produce samples with wrong labels, but also generate poor quality samples. We consider two scenarios, depending on whether the noise model is known or not. When the distribution of the noise is known, we introduce a novel architecture which we call Robust Conditional GAN (RCGAN). The main idea is to corrupt the label of the generated sample before feeding to the adversarial discriminator, forcing the generator to produce samples with clean labels. This approach of passing through a matching noisy channel is justified by corresponding multiplicative approximation bounds between the loss of the RCGAN and the distance between the clean real distribution and the generator distribution. This shows that the proposed approach is robust, when used with a carefully chosen discriminator architecture, known as projection discriminator. When the distribution of the noise is not known, we provide an extension of our architecture, which we call RCGAN-U, that learns the noise model simultaneously while training the generator. We show experimentally on MNIST and CIFAR-10 datasets that both the approaches consistently improve upon baseline approaches, and RCGAN-U closely matches the performance of RCGAN.