Multi-Discriminator Generative Adversarial Network for High Resolution Gray-Scale Satellite Image Colorization

Li, Feimo; Ma, Lei; Cai, Jing

doi:10.1109/igarss.2018.8517930

Cited by 12 publications

(13 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are also reports on applying blockchain technology to decentralized FL to improve the security [5], [31], [16]. Distributed GANs are proposed recently [32], [33]. It propose a single generator at the intermediary and distributed discriminators in [32].…”

Section: Related Workmentioning

confidence: 99%

Efficient Ring-topology Decentralized Federated Learning with Deep Generative Models for Industrial Artificial Intelligent

Zhao¹,

Hu²,

Xiao³

et al. 2021

Preprint

View full text Add to dashboard Cite

By leveraging deep learning based technologies, the data-driven based approaches have reached great success with the rapid increase of data generated of Industrial Indernet of Things(IIot). However, security and privacy concerns are obstacles for data providers in many sensitive data-driven industrial scenarios, such as healthcare and auto-driving. Many Federated Learning(FL) approaches have been proposed with DNNs for IIoT applications, these works still suffer from low usability of data due to data incompleteness, low quality, insufficient quantity, sensitivity, etc. Therefore, we propose a ring-topogy based decentralized federated learning(RDFL) scheme for Deep Generative Models(DGMs), where DGMs is a promising solution for solving the aforementioned data usability issues. Compare with existing IIoT FL works, our RDFL schemes provides communication efficiency and maintain training performance to boost DGMs in target IIoT tasks. A novel ring FL topology as well as a map-reduce based synchronizing method are designed in the proposed RDFL to improve decentralized FL performance and bandwidth utilization. In addition, InterPlanetary File System(IPFS) is introduced to further improve communication efficiency and FL security. Extensive experiments have been taken to demonstate the superiority of RDFL with either independent and identically distributed(IID) datasets or non-independent and identically distributed(Non-IID) datasets.

show abstract

Section: Related Workmentioning

confidence: 99%

Efficient Ring-topology Decentralized Federated Learning with Deep Generative Models for Industrial Artificial Intelligent

Zhao¹,

Hu²,

Xiao³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…One study has shown that the subjective quality of the SR results can be significantly increased by using the Generative Adversarial Network [17]. Following the introduction of GAN, various algorithms using GAN have been proposed in SR [18]- [23]. In [18], rather than MSE loss, VGG loss is used to improve the visual quality with adversarial loss.…”

Section: Related Workmentioning

confidence: 99%

Multi-Perspective Discriminators-Based Generative Adversarial Network for Image Super Resolution

2019

View full text Add to dashboard Cite

Recently, generative adversarial network-based image super resolution has been investigated, and it has been shown to lead to overwhelming improvements in subjective quality. However, it also leads to checkerboard artifacts and the unpleasing high-frequency (HF) components. In this paper, we propose a multi-discriminators-based image super resolution method that distinguishes those artifacts from various perspectives. First, the DCT perspective discriminator is proposed because the checkerboard artifacts are easily separated on the frequency domain. Second, the gradient perspective discriminator is proposed, because the unpleasing HF components can be discriminated on the gradient magnitude distribution. These proposed multi-perspective discriminators can easily identify artifacts, and they can help the generator reproduce artifact-less SR images. The experimental results show that the proposed SR-GAN with multiperspective discriminators achieves objective and subjective quality improvements in terms of PSNR, SSIM, PI and MOS, as compared to the conventional SR-GAN by reducing the aforementioned artifacts. INDEX TERMS Image super-resolution, deep learning for super resolution, SR GAN, multi-discriminators.

show abstract

“…The generative adversarial network (GAN) [36], shows an improvement in the subjective quality of the recovered images. Consequently, various networks have been proposed utilizing GAN in SR field [39], [41]- [45]. The authors in [39], propose to use the a combined loss function which contains two parts including the adversarial and content losses.…”

Section: Related Workmentioning

confidence: 99%

Spatial Transformer Generative Adversarial Network for Robust Image Super-Resolution

2019

View full text Add to dashboard Cite

Recently, there have been significant advances in image super-resolution based on generative adversarial networks (GANs) to achieve breakthroughs in generating more images with high subjective quality. However, there are remaining challenges needs to be met, such as simultaneously recovering the finer texture details for large upscaling factors and mitigating the geometric transformation effects. In this paper, we propose a novel robust super-resolution GAN (i.e. namely RSR-GAN) which can simultaneously perform both the geometric transformation and recovering the finer texture details. Specifically, since the performance of the generator depends on the discreminator, we propose a novel discriminator design by incorporating the spatial transformer module with residual learning to improve the discrimination of fake and true images through removing the geometric noise, in order to enhance the super-resolution of geometric corrected images. Finally, to further improve the perceptual quality, we introduce an additional DCT loss term into the existing loss function. Extensive experiments, measured by both PSNR and SSIM measurements, show that our proposed method achieves a high level of robustness against a number of geometric transformations, including rotation, translation, a combination of rotation and scaling effects, and a cobmination of rotaion, transalation and scaling effects. Benchmarked by the existing state-of-the-arts SR methods, our proposed delivers superior performances on a wide range of datasets which are publicly available and widely adopted across research communities.

show abstract

Multi-Discriminator Generative Adversarial Network for High Resolution Gray-Scale Satellite Image Colorization

Cited by 12 publications

References 3 publications

Efficient Ring-topology Decentralized Federated Learning with Deep Generative Models for Industrial Artificial Intelligent

Efficient Ring-topology Decentralized Federated Learning with Deep Generative Models for Industrial Artificial Intelligent

Multi-Perspective Discriminators-Based Generative Adversarial Network for Image Super Resolution

Spatial Transformer Generative Adversarial Network for Robust Image Super-Resolution

Contact Info

Product

Resources

About