paper-with-me

홈 › Papers

Noise Robust Generative Adversarial Networks

2019-11-26 · CVPR 2020 6 · Takuhiro Kaneko, Tatsuya Harada

Generative adversarial networks (GANs) are neural networks that learn data distributions through adversarial training. In intensive studies, recent GANs have shown promising results for reproducing training images. However, in spite of noise, they reproduce images with fidelity. As an alternative, we propose a novel family of GANs called noise robust GANs (NR-GANs), which can learn a clean image generator even when training images are noisy. In particular, NR-GANs can solve this problem without having complete noise information (e.g., the noise distribution type, noise amount, or signal-noise relationship). To achieve this, we introduce a noise generator and train it along with a clean image generator. However, without any constraints, there is no incentive to generate an image and noise separately. Therefore, we propose distribution and transformation constraints that encourage the noise generator to capture only the noise-specific components. In particular, considering such constraints under different assumptions, we devise two variants of NR-GANs for signal-independent noise and three variants of NR-GANs for signal-dependent noise. On three benchmark datasets, we demonstrate the effectiveness of NR-GANs in noise robust image generation. Furthermore, we show the applicability of NR-GANs in image denoising. Our code is available at https://github.com/takuhirok/NR-GAN/.

📄 PDF Abstract BibTeX arXiv:1911.11776

Code (2)

takuhirok/NR-GAN 공식 구현 pytorch
Yotsuyubi/wave-nr-gan pytorch

Tasks

DenoisingImage DenoisingImage Generation

Similar Papers 제목 키워드 기반

AT-GAN: An Adversarial Generative Model for Non-constrained Adversarial Examples

2021-01-01 · Xiaosen Wang, Kun He, Chuanbiao Song, LiWei Wang 외

With the rapid development of adversarial machine learning, numerous adversarial attack methods have been proposed. Typical attacks are based on a search in the neighborhood of input image to generate a perturbed adversa…

Adversarial AttackTransfer Learning

Pre-trained Multiple Latent Variable Generative Models are good defenders against Adversarial Attacks

2024-12-04 · Dario Serez, Marco Cristani, Alessio Del Bue, Vittorio Murino 외

Attackers can deliberately perturb classifiers' input with subtle noise, altering final predictions. Among proposed countermeasures, adversarial purification employs generative networks to preprocess input images, filter…

Adversarial Purification

Generative Adversarial Networks with Decoder-Encoder Output Noise

2018-07-11 · Guoqiang Zhong, Wei Gao, Yongbin Liu, Youzhao Yang

In recent years, research on image generation methods has been developing fast. The auto-encoding variational Bayes method (VAEs) was proposed in 2013, which uses variational inference to learn a latent space from the im…

DecoderImage GenerationVariational Inference

Detecting Adversarial Data Using Perturbation Forgery

2025-01-01 · CVPR 2025 1 · Qian Wang, Chen Li, Yuchen Luo, Hefei Ling 외

As a defense strategy against adversarial attacks, adversarial detection aims to identify and filter out adversarial data from the data flow based on discrepancies in distribution and noise patterns between natural a…

Implicit Generative Modeling of Random Noise during Training for Adversarial Robustness

2018-07-05 · Priyadarshini Panda, Kaushik Roy

We introduce a Noise-based prior Learning (NoL) approach for training neural networks that are intrinsically robust to adversarial attacks. We find that the implicit generative modeling of random noise with the same loss…

Adversarial Robustness