NR-GAN: Noise Robust Generative Adversarial Networks (CVPR 2020)
This repository provides PyTorch implementation for noise robust GAN (NR-GAN). NR-GAN is unique in that it can learn a clean image generator even when only noisy images are available for training.
Note: In our previous studies, we have also proposed GANs for label noise. Please check them from the links below.
- Label-noise robust GAN (rGAN) (CVPR 2019)
- Classifier's posterior GAN (CP-GAN) (BMVC 2019)
Paper
Noise Robust Generative Adversarial Networks. Takuhiro Kaneko and Tatsuya Harada. In CVPR, 2020.
[Paper] [Project] [Slides] [Video]
Installation
Clone this repo:
git clone https://github.com/takuhirok/NR-GAN.git
cd NR-GAN/
First, install Python 3+. Then install PyTorch 1.3 and other dependencies by the following:
pip install -r requirements.txt
Training
To train a model, use the following script:
bash ./scripts/train.sh [dataset] [model] [output_directory_path]
Example
To train SI-NR-GAN-I (sinrgan1) on CIFAR-10 with additive Gaussian noise with a fixed standard deviation (cifar10ag25), run the following:
bash ./scripts/train.sh cifar10ag25 sinrgan1 outputs
The results are saved into outputs.
Note: In our experiments, we report the best model encountered during training to mitigate the performance fluctuation caused by GAN training instability.
Options
Regarding [dataset], choose one option among the following:
cifar10: No noisecifar10ag25: (A) Additive Gaussian noise with a fixed standard deviationcifar10ag5-50: (B) Additive Gaussian noise with a variable standard deviationcifar10lg25p16: (C) Local Gaussian noise with a fixed-size patchcifar10lg25p8-24: (D) Local Gaussian noise with a variable-size patchcifar10u50: (E) Uniform noisecifar10mix: (F) Mixture noisecifar10bg25k5: (G) Brown Gaussian noisecifar10abg25k5: (H) Sum of (A) and (G)cifar10mg25: (I) Multiplicative Gaussian noise with a fixed standard deviationcifar10mg5-50: (J) Multiplicative Gaussian noise with a variable standard deviationcifar10amg5_25: (K) Sum of few (A) and (I)cifar10amg25_25: (L) Sum of much (A) and (I)cifar10p30: (M) Poisson noise with a fixed total number of eventscifar10p10-50: (N) Poisson noise with a variable total number of eventscifar10pg30_5: (O) Sum of (M) and few (A)cifar10pg30_25: (P) Sum of (M) and much (A)
Regarding [model], choose one option among the following:
gan: GANambientgan: AmbientGANsinrgan1: SI-NR-GAN-Isinrgan2: SI-NR-GAN-IIsdnrgan1: SD-NR-GAN-Isdnrgan2: SD-NR-GAN-IIsdnrgan3: SD-NR-GAN-III
Examples of generated images
CIFAR-10 with additive Gaussian noise
cifar10ag25: (A) Additive Gaussian noise with a fixed standard deviation
AmbientGAN† is trained with the ground-truth noise model, while the other models are trained without full knowledge of the noise (i.e., the noise distribution type and noise amount).
CIFAR-10 with multiplicative Gaussian noise
cifar10mg25: (I) Multiplicative Gaussian noise with a fixed standard deviation
AmbientGAN† is trained with the ground-truth noise model, while the other models are trained without full knowledge of the noise (i.e., the noise distribution type, noise amount, and signal-noise relationship).
Citation
If you find this work useful for your research, please cite our paper.
@inproceedings{kaneko2020NR-GAN,
title={Noise Robust Generative Adversarial Networks},
author={Kaneko, Takuhiro and Harada, Tatsuya},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year={2020}
}
Related work
- A. Bora, E. Price, A. G. Dimakis. AmbientGAN: Generative Models from Lossy Measurements. In ICLR, 2018.
- T. Kaneko, Y. Ushiku, T. Harada. Label-Noise Robust Generative Adversarial Networks. In CVPR, 2019.
- T. Kaneko, Y. Ushiku, T. Harada. Class-Distinct and Class-Mutual Image Generation with GANs. In BMVC, 2019.
31 Dec 8, 2022
375 Dec 31, 2022
15 Feb 10, 2022
2.9k Dec 28, 2022
1 Dec 14, 2021
42 Nov 24, 2022
143 Jan 5, 2023
12 Dec 7, 2022
122 Dec 28, 2022
3 Dec 29, 2022
33 Nov 1, 2022
60 Dec 30, 2022
202 Dec 13, 2022
117 Nov 27, 2022
3k Jan 8, 2023
373 Jan 2, 2023
148 Nov 18, 2022
23 Jul 21, 2022