Downscaling of Landsat LST with HotSat-1 data and generative adversarial networks

The generative adversarial neural network algorithm is used for in-depth research and analysis of sports training performance prediction, and the corresponding model is built and used for practical applications. To address the problems of gradient disappearance, training instability, lack of local consistency of repair results, and long training time in the image restoration algorithm based on generative adversarial networks, this paper proposes a multigenerative adversarial image restoration algorithm based on multigranularity reconstruction sampling. The algorithm changes the distribution initialization of the generative network and uses reconstruction sampling to ensure that the Lebesgue measure of the overlapping part of the generative sample space and the real sample space is not 0 to further stabilize the gradient, and it is demonstrated that reconstruction sampling can stabilize the training and gradient. In addition, segmentation invariance is used to shorten the training time while ensuring the quality of the restored images, and an algorithm adaptability metric is proposed to comprehensively evaluate the image restoration algorithm. Based on the results of the fusion model analysis, an attention-based mechanism for the student performance prediction model is proposed. First, deep student behavioral features are extracted using a generative adversarial deep neural network, and the salient features in the student behavioral features are selected using a maximum pooling method; then, the extracted features are used as the input of the generative adversarial deep neural network for student performance prediction. Finally, a temporal attention mechanism is introduced at the output of the generative adversarial deep neural network to assign attention weights to different weekly student behavioral features.

Image dehazing has always been a challenging topic in image processing. The development of deep learning methods, especially the generative adversarial networks (GAN), provides a new way for image dehazing. In recent years, many deep learning methods based on GAN have been applied to image dehazing. However, GAN has two problems in image dehazing. Firstly, For haze image, haze not only reduces the quality of the image but also blurs the details of the image. For GAN network, it is difficult for the generator to restore the details of the whole image while removing the haze. Secondly, GAN model is defined as a minimax problem, which weakens the loss function. It is difficult to distinguish whether GAN is making progress in the training process. Therefore, we propose a guided generative adversarial dehazing network (GGADN). Different from other generation adversarial networks, GGADN adds a guided module on the generator. The guided module verifies the network of each layer of the generator. At the same time, the details of the map generated by each layer are strengthened. Network training is based on the pre-trained VGG feature model and L1-regularized gradient prior which is developed by new loss function parameters. From the dehazing results of synthetic images and real images, the proposed method is better than the state-of-the-art dehazing methods.

Generative adversarial networks (GANs) introduced by Goodfellow et al. since their advent have had a number of improvements and applications in image generation tasks and unsupervised learning. Recurrent model and the conditional models are two derivations of GANs. In this paper, conditional recurrent GAN is proposed. By using conditional settings in recurrent GANs, they can be used to generate state-of-the-art images. The conditional and recurrent models are compared with the proposed model using the generative adversarial metric proposed by Im et al. where the discriminator of one model competes against the generator of another. The results show that the proposed model outperforms the other two models.

A generative adversarial inpainting network to enhance prediction of periodontal clinical attachment level

Single-pixel imaging is a promising image acquisition method that provides an alternative to traditional imaging methods using multi-pixel matrices. However, algorithmic image reconstruction from measurements of a single-pixel camera is a non-trivial computational task that can be solved by machine learning methods. In this work, we investigate the possibility of image reconstruction in the single-pixel imaging method using generative adversarial neural networks. Using computer simulation of a single-pixel camera, we study the efficiency of image reconstruction using two generative network architectures – a deep convolutional generative adversarial network and a generative least squares adversarial network. We find that the generative least squares adversarial network demonstrates a better image reconstruction quality compared to the deep convolutional generative adversarial network. However, when taking into account optical distortions, the deep convolutional adversarial network is more stable in learning to a higher quality compared to the generative least squares adversarial network. The results obtained in this work may serve as a basis for the development of software for the practical application of a single-pixel camera.

<p>Tropical Cyclones (TCs) are deadly but rare events that cause considerable loss of life and property damage every year. Traditional TC forecasting and tracking methods focus on numerical forecasting models, synoptic forecasting and statistical methods. However, in recent years there have been several studies investigating applications of Deep Learning (DL) methods for weather forecasting with encouraging results.</p><p>We aim to test the efficacy of several DL methods for TC nowcasting, particularly focusing on Generative Adversarial Neural Networks (GANs) and Recurrent Neural Networks (RNNs). The strengths of these network types align well with the given problem: GANs are particularly apt to learn the form of a dataset, such as the typical shape and intensity of a TC, and RNNs are useful for learning timeseries data, enabling a prediction to be made based on the past several timesteps.</p><p>The goal is to produce a DL based pipeline to predict the future state of a developing cyclone with accuracy that measures up to current methods.  We demonstrate our approach based on learning from high-resolution numerical simulations of TCs from the Indian and Pacific oceans and discuss the challenges and advantages of applying these DL approaches to large high-resolution numerical weather data.</p>

Imbalanced training data introduce important challenge into medical image analysis where a majority of the data belongs to a normal class and only few samples belong to abnormal classes. We propose to mitigate the class imbalance problem by introducing two generative adversarial network (GAN) architectures for class minority oversampling. Here, we explore balancing data distribution 1) by generating new sample from unsupervised GAN or 2) synthesize missing image modalities from semi-supervised GAN. We evaluated the effect of the synthetic unsupervised and semi-supervised GAN methods by use of 1,500 MR images for brain disease diagnosis, where the classification performance of a residual network was compared between unbalanced datasets, classic data augmentation, and the proposed new GAN-based methods.The evaluation results showed that the synthesized minority samples generated by GAN improved classification accuracy up to 18% in term of Dice score.

In this paper, we propose an improved hybrid approach for text generation that combines the strengths of generative adversarial networks (GANs) and recurrent neural networks (RNNs). The proposed model, named TextGen-GAN, uses a GAN to generate high-level semantic representations of text, which are then passed through an RNN decoder to produce coherent and diverse text. The suggested method produces superior results in terms of both quality and diversity when tested on a number of benchmark datasets. The obtained results show that the combination of GAN and RNN outperforms GAN alone, RNN only, baseline, and state-of-the-art models, demonstrating the effectiveness of the proposed hybrid approach.

GAN review: Models and medical image fusion applications

<p>High data collection costs and complicated data access regulations increase the demand for synthetic data. Generative Adversarial Networks (GANs) are a novel generative framework with great potential for high quality synthetic data generation. GANs formulate the true distribution of data implicitly, and the success of GANs are often measured based on the similarity of generated data to this true distribution. GANs were originally designed to work with continuous data. However, many important real-world datasets such as medical images involve discontinuous distributions. GAN training for discontinuous distributions is relatively more challenging, as the training procedure often suffers from instability and mode collapse issues. This dissertation focuses on designing novel GAN architectures to generate representative synthetic image data, and proposes new structures to alleviate GANs' mode collapse issue. As part of this thesis, novel applications of image data generation with GANs have been also investigated for important problems arising in the telecommunication industry and medical domain. Specifically, we first explore various GAN structures to generate engineered electromagnetic surfaces. We consider the continuous approximation of the data and explore the capabilities of feed-forward and convolutional GANs for synthetic data generation. Next, we introduce a novel GAN architecture to address the problem of mode collapse in GAN training. The proposed structure incorporates a third network that penalizes the generator for generating low diversity samples. Lastly, we study the challenging problem of object generation in 3D space using GANs, and we propose extensions to existing 3D GAN structures to generate connected 3D volumes. Additionally, we explore a more challenging version of this 3D volume generation problem by generating connected volumes packed with spheres. This research has applications in radiosurgery treatment planning, and the proposed 3D GAN structure can help generate rare, unseen 3D tumor volumes and information on how to treat these tumors. Accordingly, our analysis contributes to overcoming data scarcity issues (e.g., due to privacy considerations) for an important practical problem in the medical domain.</p>

<h2>ABSTRACT</h2> <p><strong>Objectives:</strong> To provide insight into deep generative models and review the most prominent and efficient deep generative models, including Variational Auto-encoder (VAE) and Generative Adversarial Networks (GANs). <strong>Methods:</strong> We provide a comprehensive overview of VAEs and GANs along with their advantages and disadvantages. This paper also surveys the recently introduced Attention-based GANs and the most recently introduced Transformer based GANs. <strong>Findings:</strong> GANs have been intensively researched because of their significant advantages over VAE. Furthermore, GANs are powerful generative models that have been widely employed in a variety of fields. Though GANs have a number of advantages over VAEs, but, despite their immense popularity and success, training GANs is still difficult and has experienced a lot of setbacks. These failures include mode collapse, where the generator produces the same set of outputs for various inputs, ultimately resulting in the loss of diversity; non-convergence due to oscillatory and diverging behaviors of the generator and discriminator during the training phase; and vanishing or exploding gradients, where learning either ceases to occur or occurs very slowly. Recently, some attention-based GANs and Transformer-based GANs have also been proposed for high-fidelity image generation. <strong>Novelty:</strong> Unlike previous survey articles, which often focus on all DGMs and dive into their complicated aspects, this work focuses on the most prominent DGMs, VAEs, and GANs and provides a theoretical understanding of them. Furthermore, because GAN is now the most extensively used DGM being studied by the academic community, the literature on it needs to be explored more. Moreover, while numerous articles on GANs are available, none have analyzed the most recent attention-based GANs and Transformer-based GANs. So, in this study, we review the recently introduced attention-based GANs and Transformer-based GANs, the literature related to which has not been reviewed by any survey paper.</p> <p><strong>Keywords:</strong> Variational Autoencoder; Generative Adversarial Networks; Autoencoder; Transformer; Self-Attention</p>

<p>High data collection costs and complicated data access regulations increase the demand for synthetic data. Generative Adversarial Networks (GANs) are a novel generative framework with great potential for high quality synthetic data generation. GANs formulate the true distribution of data implicitly, and the success of GANs are often measured based on the similarity of generated data to this true distribution. GANs were originally designed to work with continuous data. However, many important real-world datasets such as medical images involve discontinuous distributions. GAN training for discontinuous distributions is relatively more challenging, as the training procedure often suffers from instability and mode collapse issues. This dissertation focuses on designing novel GAN architectures to generate representative synthetic image data, and proposes new structures to alleviate GANs' mode collapse issue. As part of this thesis, novel applications of image data generation with GANs have been also investigated for important problems arising in the telecommunication industry and medical domain. Specifically, we first explore various GAN structures to generate engineered electromagnetic surfaces. We consider the continuous approximation of the data and explore the capabilities of feed-forward and convolutional GANs for synthetic data generation. Next, we introduce a novel GAN architecture to address the problem of mode collapse in GAN training. The proposed structure incorporates a third network that penalizes the generator for generating low diversity samples. Lastly, we study the challenging problem of object generation in 3D space using GANs, and we propose extensions to existing 3D GAN structures to generate connected 3D volumes. Additionally, we explore a more challenging version of this 3D volume generation problem by generating connected volumes packed with spheres. This research has applications in radiosurgery treatment planning, and the proposed 3D GAN structure can help generate rare, unseen 3D tumor volumes and information on how to treat these tumors. Accordingly, our analysis contributes to overcoming data scarcity issues (e.g., due to privacy considerations) for an important practical problem in the medical domain.</p>

Generative adversarial networks (GANs), which have emerged as one of the powerful frameworks for generating synthetic data, have proven remarkably capable across domains. This systematic review explores the rapidly evolving GAN landscape, particularly their applications for generating high-fidelity synthetic data that resemble real-world datasets' statistical properties. We comprehensively analyze recent literature to present the following key findings: 1. GANs' Capabilities: GANs have demonstrated significant potential across various fields, especially in creating synthetic data that mimic real-world datasets. 2. State-of-the-Art Architectures: Advanced GAN variants, such as Conditional GANs, Wasserstein GANs, and Cycle GANs, have shown great promise for transformation in sectors like healthcare, finance, and image processing. 3. Evaluation Methodologies: Metrics for assessing GAN-generated data include statistical similarity, downstream task performance, and privacy preservation, highlighting strengths and limitations in current evaluation paradigms. 4. Training Difficulties: GANs face challenges such as mode collapse, instability, and sensitivity to hyperparameters, which require further innovation and exploration. Additionally, we critically examine the methodologies used to evaluate the quality and utility of GAN-generated data. Metrics like statistical similarity, downstream task performance, and privacy preservation provide a broad view of current strengths and limitations. Besides synthetic data generation using GAN-based methods, this review discusses training difficulties and emerging directions aimed at mitigating issues like mode collapse, instability, and hyperparameter sensitivity. The findings emphasize significant progress in GAN-based synthetic data generation but underline the need for a robust, standardized evaluation framework and continued innovation in model architectures. 1. Robust Evaluation Framework: Developing a standardized evaluation framework for GAN-generated data is essential for advancing the field. 2. Model Architecture Innovation: Ongoing innovation in model architectures is necessary to overcome current limitations and enhance GAN performance. 3. Synthetic Data Generation: GANs hold great potential for generating synthetic data, which can address data privacy concerns, data scarcity, and data augmentation needs. This review aims to help researchers and practitioners understand the current state and future directions of GAN applications in synthetic data generation.

Neural networks play a significant role in the field of image classification. When an input image is modified by adversarial attacks, the changes are imperceptible to the human eye, but it still leads to misclassification of the images. Researchers have demonstrated these attacks to make production self-driving cars misclassify Stop Road signs as 45 Miles Per Hour (MPH) road signs and a turtle being misclassified as AK47. Three primary types of defense approaches exist which can safeguard against such attacks i.e., Gradient Masking, Robust Optimization, and Adversarial Example Detection. Very few approaches use Generative Adversarial Networks (GAN) for Defense against Adversarial Attacks. In this paper, we create a new approach to defend against adversarial attacks, dubbed Chained Dual-Generative Adversarial Network (CD-GAN) that tackles the defense against adversarial attacks by minimizing the perturbations of the adversarial image using iterative oversampling and undersampling using GANs. CD-GAN is created using two GANs, i.e., CDGAN’s Sub-Resolution GAN and CDGAN’s Super-Resolution GAN. The first is CDGAN’s Sub-Resolution GAN which takes the original resolution input image and oversamples it to generate a lower resolution neutralized image. The second is CDGAN’s Super-Resolution GAN which takes the output of the CDGAN’s Sub-Resolution and undersamples, it to generate the higher resolution image which removes any remaining perturbations. Chained Dual GAN is formed by chaining these two GANs together. Both of these GANs are trained independently. CDGAN’s Sub-Resolution GAN is trained using higher resolution adversarial images as inputs and lower resolution neutralized images as output image examples. Hence, this GAN downscales the image while removing adversarial attack noise. CDGAN’s Super-Resolution GAN is trained using lower resolution adversarial images as inputs and higher resolution neutralized images as output images. Because of this, it acts as an Upscaling GAN while removing the adversarial attak noise. Furthermore, CD-GAN has a modular design such that it can be pre-fixed to any existing classifier without any retraining or extra effort, and can defend any classifier model against adversarial attack. In this way, it is a Generalized Defense against adversarial attacks, capable of defending any classifier model against any attacks. This enables the user to directly integrate CD-GAN with an existing production deployed classifier smoothly. CD-GAN iteratively removes the adversarial noise using a multi-step approach in a modular approach. It performs comparably to the state of the arts with mean accuracy of 33.67 while using minimal compute resources in training.

This article explores the application of Generative Adversarial Networks (GANs) in improving subsurface rock analysis. GANs generate realistic images of rock features, enhancing the accuracy and efficiency of estimating rock properties. The objective is to advance the field of subsurface rock analysis, offering insights into the potential of GAN techniques. The article reviews recent developments in data-driven rock reconstruction technology, specifically focusing on GANs. It highlights GANs’ ability to generate and estimate rock features like porosity and permeability. These GAN methods are complemented by discriminators to select or reject features, making them integral to the reconstruction model. The article provides a framework for engineers and researchers to effectively utilize these techniques for rock reconstruction, offering an assessment of their strengths and limitations. Digital rock reconstruction, aided by GANs, has promising implications for site selection and recovery. GANs enhance image resolution, improving the field of view and dynamism of parameters in rock analysis. However, GANs heavily rely on high-quality data, which poses a limitation. To address this, conditional GANs have been proposed. The article comprehensively reviews the latest developments in GAN methods for digital rock reconstruction, offering valuable insights for engineers and researchers using GANs for accurate subsurface rock analysis. It also proposes ways to enhance these methods and advance the field. The novelty of this article lies in its exploration of Generative Adversarial Networks (GANs) in the context of subsurface rock analysis. It emphasizes the potential of GAN techniques to generate realistic rock images and estimate properties like porosity and permeability. Additionally, the article discusses the integration of GANs into the digital rock concept, highlighting their role in improving predictive models and supporting decision-making in the oil and gas industry's resource extraction and production strategies.