scholarly journals Image Completion using Deep Convolutional Generative Adversarial Networks

2019 ◽  
Vol 8 (4) ◽  
pp. 593-598
Keyword(s):  
Image Processing ◽  
Deep Learning ◽  
High Frequency ◽  
State Of The Art ◽  
Super Resolution ◽  
Generative Adversarial Networks ◽  
Data Sets ◽  
Traditional Methods ◽  
Adversarial Networks ◽  
Realistic Images

Deep learning recently became the state-of-the-art in many pattern recognition tasks. Advance-ment of computational power and big datasets brings opportunity to use deep learning methods for image processing. We have used deep convolutional generative adversarial networks (DCGAN) to do various image processing tasks such as deconvolution , denoising and super-resolution. With DCGAN we can use a single architecture to perform different image processing tasks . While the results sometimes shows slightly lower PSNR for DCGAN compared to traditional methods but it tries to achieve competitive psnr scores. Thus , it allows to view quite appealing then other methods While it can learn from big data-sets very efficiently and allows itself to add high-frequency details automatically which traditional methods can’t. The architectgure in DCGAN is based on two neural networks of generator and discriminator which both tries to deceive each other and allows it to generate more appealing and realistic images from the datasets.

scholarly journals A Hyperspectral Image Classification Method Based on Multi-Discriminator Generative Adversarial Networks

Sensors ◽  
2019 ◽  
Vol 19 (15) ◽  
pp. 3269 ◽  
Author(s):  
Hongmin Gao ◽  
Dan Yao ◽  
Mingxia Wang ◽  
Chenming Li ◽  
Haiyun Liu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Hyperspectral Image ◽  
Hyperspectral Data ◽  
Generative Adversarial Networks ◽  
Data Sets ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
The One ◽  
Hyperspectral Remote Sensing Images

Hyperspectral remote sensing images (HSIs) have great research and application value. At present, deep learning has become an important method for studying image processing. The Generative Adversarial Network (GAN) model is a typical network of deep learning developed in recent years and the GAN model can also be used to classify HSIs. However, there are still some problems in the classification of HSIs. On the one hand, due to the existence of different objects with the same spectrum phenomenon, if only according to the original GAN model to generate samples from spectral samples, it will produce the wrong detailed characteristic information. On the other hand, the gradient disappears in the original GAN model and the scoring ability of a single discriminator limits the quality of the generated samples. In order to solve the above problems, we introduce the scoring mechanism of multi-discriminator collaboration and complete semi-supervised classification on three hyperspectral data sets. Compared with the original GAN model with a single discriminator, the adjusted criterion is more rigorous and accurate and the generated samples can show more accurate characteristics. Aiming at the pattern collapse and diversity deficiency of the original GAN generated by single discriminator, this paper proposes a multi-discriminator generative adversarial networks (MDGANs) and studies the influence of the number of discriminators on the classification results. The experimental results show that the introduction of multi-discriminator improves the judgment ability of the model, ensures the effect of generating samples, solves the problem of noise in generating spectral samples and can improve the classification effect of HSIs. At the same time, the number of discriminators has different effects on different data sets.

Analysis and application of generative-adeversarial networks for producing high quality images

Ergodesign ◽  
2020 ◽  
Vol 2020 (4) ◽  
pp. 167-176
Author(s):  
Yuriy Malakhov ◽  
Aleksandr Androsov ◽  
Andrey Averchenkov
Keyword(s):  
Deep Learning ◽  
Super Resolution ◽  
Generative Adversarial Networks ◽  
Learning Models ◽  
High Quality ◽  
Adversarial Networks ◽  
Network Operation

The article discusses generative adversarial networks for obtaining high quality images. Models, architecture and comparison of network operation are presented. The features of building deep learning models in the process of performing the super-resolution task, as well as methods associated with improving performance, are considered.

An Image Turing Test on Realistic Gastroscopy Images Generated by using the Progressive Growing of Generative Adversarial Networks (Preprint)

2020 ◽  
Author(s):  
Keewon Shin ◽  
Jung Su Lee ◽  
Ji Young Lee ◽  
Hyunsu Lee ◽  
Jeongseok Kim ◽  
...  
Keyword(s):  
Deep Learning ◽  
Anomaly Detection ◽  
Sensitivity And Specificity ◽  
Turing Test ◽  
Generative Adversarial Networks ◽  
Anatomical Landmarks ◽  
Adversarial Networks ◽  
Significant Difference ◽  
The Mean ◽  
Realistic Images

BACKGROUND An Image Turing Test on Realistic Gastroscopy Images Generated by using the Progressive Growing of Generative Adversarial Networks(PGGAN) OBJECTIVE This study aims to present a method for generating gastroscopy images using a deep learning-based progressive growing of generative adversarial networks (PGGAN) as the first step for anomaly detection. METHODS We trained the PGGAN with a total 107,060 normal gastroscopy images to generate highly realistic images 512 x 512 pixels in size. For the evaluation, image Turing tests were conducted on 200 images, including 100 real and 100 synthesized images, by 19 endoscopists. The endoscopists were divided into three groups based on their years of clinical experience (0 to 5, 5 to 10, and 10 or more). RESULTS For the image Turing test, the mean accuracy, sensitivity, and specificity of the 19 endoscopists were 61.3%, 70.3%, and 52.4%, respectively. The mean accuracy of the three endoscopist groups was 62.4 (0 to 5 yrs.), 59.8 (5 to 10 yrs.), and 59.1 % (10 or more yrs.), which was not considered a significant difference. There were no statistically significant differences in the location of the stomach. However, in sensitivity to anatomical landmarks, the sensitivity to the pylorus was higher (P = 0.002). CONCLUSIONS Images generated by PGGAN showed highly realistic depictions that were difficult to distinguish, regardless of expertise, and could be used for anomaly detection in the future.

A novel image super-resolution reconstruction algorithm based on improved GANs and gradient penalty

2019 ◽  
Vol 12 (3) ◽  
pp. 400-413 ◽  
Author(s):  
Shuangshuang Liu ◽  
Xiaoling Li
Keyword(s):  
Super Resolution ◽  
Reconstruction Algorithm ◽  
Wasserstein Distance ◽  
Generative Adversarial Networks ◽  
Data Sets ◽  
Feature Maps ◽  
Content Type ◽  
Adversarial Networks ◽  
Image Super Resolution ◽  
Learning Architectures

Purpose Conventional image super-resolution reconstruction by the conventional deep learning architectures suffers from the problems of hard training and gradient disappearing. In order to solve such problems, the purpose of this paper is to propose a novel image super-resolution algorithm based on improved generative adversarial networks (GANs) with Wasserstein distance and gradient penalty. Design/methodology/approach The proposed algorithm first introduces the conventional GANs architecture, the Wasserstein distance and the gradient penalty for the task of image super-resolution reconstruction (SRWGANs-GP). In addition, a novel perceptual loss function is designed for the SRWGANs-GP to meet the task of image super-resolution reconstruction. The content loss is extracted from the deep model’s feature maps, and such features are introduced to calculate mean square error (MSE) for the loss calculation of generators. Findings To validate the effectiveness and feasibility of the proposed algorithm, a lot of compared experiments are applied on three common data sets, i.e. Set5, Set14 and BSD100. Experimental results have shown that the proposed SRWGANs-GP architecture has a stable error gradient and iteratively convergence. Compared with the baseline deep models, the proposed GANs models have a significant improvement on performance and efficiency for image super-resolution reconstruction. The MSE calculated by the deep model’s feature maps gives more advantages for constructing contour and texture. Originality/value Compared with the state-of-the-art algorithms, the proposed algorithm obtains a better performance on image super-resolution and better reconstruction results on contour and texture.

scholarly journals Model Specialization for the Use of ESRGAN on Satellite and Airborne Imagery

2021 ◽  
Vol 13 (20) ◽  
pp. 4044
Author(s):  
Étienne Clabaut ◽  
Myriam Lemelin ◽  
Mickaël Germain ◽  
Yacine Bouroubi ◽  
Tony St-Pierre
Keyword(s):  
Remote Sensing ◽  
Deep Learning ◽  
Texture Analysis ◽  
Spatial Resolution ◽  
Super Resolution ◽  
Learning Model ◽  
Generative Adversarial Networks ◽  
Remote Sensing Images ◽  
Adversarial Networks ◽  
Deep Learning Model

Training a deep learning model requires highly variable data to permit reasonable generalization. If the variability in the data about to be processed is low, the interest in obtaining this generalization seems limited. Yet, it could prove interesting to specialize the model with respect to a particular theme. The use of enhanced super-resolution generative adversarial networks (ERSGAN), a specific type of deep learning architecture, allows the spatial resolution of remote sensing images to be increased by “hallucinating” non-existent details. In this study, we show that ESRGAN create better quality images when trained on thematically classified images than when trained on a wide variety of examples. All things being equal, we further show that the algorithm performs better on some themes than it does on others. Texture analysis shows that these performances are correlated with the inverse difference moment and entropy of the images.

scholarly journals Conditional Generative Adversarial Networks for Commonsense Machine Comprehension

2017 ◽  
Author(s):  
Bingning Wang ◽  
Kang Liu ◽  
Jun Zhao
Keyword(s):  
Reading Comprehension ◽  
Deep Learning ◽  
State Of The Art ◽  
Training Data ◽  
Generative Adversarial Networks ◽  
Feature Engineering ◽  
Language Understanding ◽  
Story Reading ◽  
Testing Period ◽  
Adversarial Networks

Recently proposed Story Cloze Test [Mostafazadeh et al., 2016] is a commonsense machine comprehension application to deal with natural language understanding problem. This dataset contains a lot of story tests which require commonsense inference ability. Unfortunately, the training data is almost unsupervised where each context document followed with only one positive sentence that can be inferred from the context. However, in the testing period, we must make inference from two candidate sentences. To tackle this problem, we employ the generative adversarial networks (GANs) to generate fake sentence. We proposed a Conditional GANs in which the generator is conditioned by the context. Our experiments show the advantage of the CGANs in discriminating sentence and achieve state-of-the-art results in commonsense story reading comprehension task compared with previous feature engineering and deep learning methods.

Analysis and application of generative-adeversarial networks for producing high quality images

Ergodesign ◽  
2020 ◽  
Vol 2020 (4) ◽  
pp. 165-176
Author(s):  
Yuriy Malakhov ◽  
Aleksandr Androsov ◽  
Andrey Averchenkov
Keyword(s):  
Deep Learning ◽  
Super Resolution ◽  
Generative Adversarial Networks ◽  
Learning Models ◽  
High Quality ◽  
Adversarial Networks ◽  
Network Operation

The article discusses generative adversarial networks for obtaining high quality images. Models, architecture and comparison of network operation are presented. The features of building deep learning models in the process of performing the super-resolution task, as well as methods associated with improving performance, are considered.

scholarly journals Generative Adversarial Networks

2021 ◽  
Vol 9 (8) ◽  
pp. 2307-2325
Author(s):  
Amey Thakur
Keyword(s):  
Deep Learning ◽  
Unsupervised Learning ◽  
Video Processing ◽  
Super Resolution ◽  
Image Synthesis ◽  
Background Information ◽  
Generative Adversarial Networks ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Adversarial Networks

Abstract: Deep learning's breakthrough in the field of artificial intelligence has resulted in the creation of a slew of deep learning models. One of these is the Generative Adversarial Network, which has only recently emerged. The goal of GAN is to use unsupervised learning to analyse the distribution of data and create more accurate results. The GAN allows the learning of deep representations in the absence of substantial labelled training information. Computer vision, language and video processing, and image synthesis are just a few of the applications that might benefit from these representations. The purpose of this research is to get the reader conversant with the GAN framework as well as to provide the background information on Generative Adversarial Networks, including the structure of both the generator and discriminator, as well as the various GAN variants along with their respective architectures. Applications of GANs are also discussed with examples. Keywords: Generative Adversarial Networks (GANs), Generator, Discriminator, Supervised and Unsupervised Learning, Discriminative and Generative Modelling, Backpropagation, Loss Functions, Machine Learning, Deep Learning, Neural Networks, Convolutional Neural Network (CNN), Deep Convolutional GAN (DCGAN), Conditional GAN (cGAN), Information Maximizing GAN (InfoGAN), Stacked GAN (StackGAN), Pix2Pix, Wasserstein GAN (WGAN), Progressive Growing GAN (ProGAN), BigGAN, StyleGAN, CycleGAN, Super-Resolution GAN (SRGAN), Image Synthesis, Image-to-Image Translation.

scholarly journals Audio-Based Drone Detection and Identification Using Deep Learning Techniques with Dataset Enhancement through Generative Adversarial Networks

Sensors ◽  
2021 ◽  
Vol 21 (15) ◽  
pp. 4953
Author(s):  
Sara Al-Emadi ◽  
Abdulla Al-Ali ◽  
Abdulaziz Al-Ali
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Recurrent Neural Network ◽  
Learning Algorithms ◽  
Generative Adversarial Networks ◽  
Generative Adversarial Network ◽  
Adversarial Networks ◽  
Detection And Identification ◽  
Learning Techniques ◽  
The Impact

Drones are becoming increasingly popular not only for recreational purposes but in day-to-day applications in engineering, medicine, logistics, security and others. In addition to their useful applications, an alarming concern in regard to the physical infrastructure security, safety and privacy has arisen due to the potential of their use in malicious activities. To address this problem, we propose a novel solution that automates the drone detection and identification processes using a drone’s acoustic features with different deep learning algorithms. However, the lack of acoustic drone datasets hinders the ability to implement an effective solution. In this paper, we aim to fill this gap by introducing a hybrid drone acoustic dataset composed of recorded drone audio clips and artificially generated drone audio samples using a state-of-the-art deep learning technique known as the Generative Adversarial Network. Furthermore, we examine the effectiveness of using drone audio with different deep learning algorithms, namely, the Convolutional Neural Network, the Recurrent Neural Network and the Convolutional Recurrent Neural Network in drone detection and identification. Moreover, we investigate the impact of our proposed hybrid dataset in drone detection. Our findings prove the advantage of using deep learning techniques for drone detection and identification while confirming our hypothesis on the benefits of using the Generative Adversarial Networks to generate real-like drone audio clips with an aim of enhancing the detection of new and unfamiliar drones.

Sign in / Sign up

Export Citation Format

Share Document