Label-Noise Robust Generative Adversarial Networks

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/.

Accepted to CVPR 2019 (Oral). Project page: https://takuhirok.github.io/rGAN/

References in corpus (19)

• Conditional Generative Adversarial Nets
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Spectral Normalization for Generative Adversarial Networks
• Self-Attention Generative Adversarial Networks
• On Calibration of Modern Neural Networks
• Semi-Supervised Learning with Deep Generative Models
• Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels
• Energy-based Generative Adversarial Network
• Learning to Reweight Examples for Robust Deep Learning
• Which Training Methods for GANs do actually Converge?
• A Learned Representation For Artistic Style
• Training Deep Neural Networks on Noisy Labels with Bootstrapping
• Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels
• A Closer Look at Memorization in Deep Networks
• Modulating early visual processing by language
• Learning What and Where to Draw
• Video-to-Video Synthesis
• Geometric GAN

Cited by in corpus (2)

• Label-Noise Robust Multi-Domain Image-to-Image Translation
• Generative-Discriminative Complementary Learning