Label-Noise Robust Generative Adversarial Networks

2018/11/27 by Takuhiro Kaneko, Kaneko, Takuhiro, Yoshitaka Ushiku +3 · 5 citations
Computer Science · Physics and Astronomy · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Model Reduction and Neural Networks #Music and Audio Processing

paper · pdf · doi:10.48550/arxiv.1811.11165

openalex publication_date 2018/11/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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/.

Citations

• Auto-Encoding Variational Bayes
• Semi-Supervised Learning with Deep Generative Models
• Pixel Recurrent Neural Networks
• Generative Adversarial Text to Image Synthesis
• Energy-based Generative Adversarial Network
• A Learned Representation For Artistic Style
• Conditional Image Synthesis With Auxiliary Classifier GANs
• Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
• Globally and locally consistent image completion
• Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels
• Video-to-Video Synthesis
• Conditional Image Generation with PixelCNN Decoders
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Learning Multiple Layers of Features from Tiny Images

Cited by

• Robust Learning of Diffusion Models with Extremely Noisy Conditions
• Learning Robust Diffusion Models from Imprecise Supervision
• Training Flow Matching Models with Reliable Labels via Self-Purification
• A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities
• Guiding Noisy Label Conditional Diffusion Models with Score-based Discriminator Correction

Related

• GANs for learning from very high class conditional noisy labels
• Robust conditional GANs under missing or uncertain labels
• Robustness of Conditional GANs to Noisy Labels
• Noise Robust Generative Adversarial Networks
• On Stabilizing Generative Adversarial Training with Noise