Cycle-free CycleGAN using Invertible Generator for Unsupervised Low-Dose CT Denoising

• URL: http://arxiv.org/abs/2104.08538v1
• Date: Sat, 17 Apr 2021 13:23:36 GMT
• Title: Cycle-free CycleGAN using Invertible Generator for Unsupervised Low-Dose CT Denoising
• Authors: Taesung Kwon, Jong Chul Ye
• Abstract summary: CycleGAN provides high-performance, ultra-fast denoising for low-dose X-ray computed tomography (CT) images. CycleGAN requires two generators and two discriminators to enforce cycle consistency. We present a novel cycle-free Cycle-GAN architecture, which consists of a single generator and a discriminator but still guarantees cycle consistency.
• Score: 33.79188588182528
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recently, CycleGAN was shown to provide high-performance, ultra-fast denoising for low-dose X-ray computed tomography (CT) without the need for a paired training dataset. Although this was possible thanks to cycle consistency, CycleGAN requires two generators and two discriminators to enforce cycle consistency, demanding significant GPU resources and technical skills for training. A recent proposal of tunable CycleGAN with Adaptive Instance Normalization (AdaIN) alleviates the problem in part by using a single generator. However, two discriminators and an additional AdaIN code generator are still required for training. To solve this problem, here we present a novel cycle-free Cycle-GAN architecture, which consists of a single generator and a discriminator but still guarantees cycle consistency. The main innovation comes from the observation that the use of an invertible generator automatically fulfills the cycle consistency condition and eliminates the additional discriminator in the CycleGAN formulation. To make the invertible generator more effective, our network is implemented in the wavelet residual domain. Extensive experiments using various levels of low-dose CT images confirm that our method can significantly improve denoising performance using only 10% of learnable parameters and faster training time compared to the conventional CycleGAN.

Related papers

• DestripeCycleGAN: Stripe Simulation CycleGAN for Unsupervised Infrared Image Destriping [15.797480466799222]
  CycleGAN has been proven to be an advanced approach for unsupervised image restoration. We present a novel framework for single-frame infrared image destriping, named DestripeCycleGAN.
  arXiv  Detail & Related papers  (2024-02-14T11:22:20Z)
• Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Scheme [65.5405625485559]
  GAN compression aims to reduce tremendous computational overhead and memory usages when deploying GANs on resource-constrained edge devices. In this work, we revisit the role of discriminator in GAN compression and design a novel generator-discriminator cooperative compression scheme for GAN compression, termed GCC.
  arXiv  Detail & Related papers  (2021-10-27T13:54:55Z)
• A Two-stage Complex Network using Cycle-consistent Generative Adversarial Networks for Speech Enhancement [7.676549056780494]
  We propose a novel two-stage denoising system that combines a CycleGAN-based magnitude enhancing network and a complex spectral refining network. Experimental results on two public datasets demonstrate that the proposed approach consistently surpasses previous one-stage CycleGANs and other state-of-the-art SE systems.
  arXiv  Detail & Related papers  (2021-09-05T07:09:10Z)
• Total Generate: Cycle in Cycle Generative Adversarial Networks for Generating Human Faces, Hands, Bodies, and Natural Scenes [76.83075646527521]
  Cycle in Cycle Generative Adversarial Network (C2GAN) for human faces, hands, bodies, and natural scenes. Our proposed C2GAN is a cross-modal model exploring the joint exploitation of the input image data and guidance data in an interactive manner.
  arXiv  Detail & Related papers  (2021-06-21T06:20:16Z)
• Orthogonal Features Based EEG Signals Denoising Using Fractional and Compressed One-Dimensional CNN AutoEncoder [3.8580784887142774]
  This paper presents a fractional one-dimensional convolutional neural network (CNN) autoencoder for denoising the Electroencephalogram (EEG) signals. EEG signals often get contaminated with noise during the recording process, mostly due to muscle artifacts (MA)
  arXiv  Detail & Related papers  (2021-04-16T13:58:05Z)
• Learning Efficient GANs for Image Translation via Differentiable Masks and co-Attention Distillation [130.30465659190773]
  Generative Adversarial Networks (GANs) have been widely-used in image translation, but their high computation and storage costs impede the deployment on mobile devices. We introduce a novel GAN compression method, termed DMAD, by proposing a Differentiable Mask and a co-Attention Distillation. Experiments show DMAD can reduce the Multiply Accumulate Operations (MACs) of CycleGAN by 13x and that of Pix2Pix by 4x while retaining a comparable performance against the full model.
  arXiv  Detail & Related papers  (2020-11-17T02:39:19Z)
• Conditioning Trick for Training Stable GANs [70.15099665710336]
  We propose a conditioning trick, called difference departure from normality, applied on the generator network in response to instability issues during GAN training. We force the generator to get closer to the departure from normality function of real samples computed in the spectral domain of Schur decomposition.
  arXiv  Detail & Related papers  (2020-10-12T16:50:22Z)
• AdaIN-Switchable CycleGAN for Efficient Unsupervised Low-Dose CT Denoising [46.0231398013639]
  We propose a novel cycleGAN architecture using a single switchable generator. The proposed method outperforms the previous cycleGAN approaches while using only about half the parameters.
  arXiv  Detail & Related papers  (2020-08-13T08:30:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.