Generative Adversarial Network Model Research Articles

Generative adversarial networks with attentional multimodal for human face synthesis

<p><span>Face synthesis and editing has increased cumulative consideration by the improvement of generative adversarial networks (GANs). The proposed attentional GAN-deep attentional multimodal similarity modal (AttnGAN-DAMSM) model focus on generating high-resolution images by removing discriminator components and generating realistic images from textual description. The attention model creates the attention map on the image and automatically retrieves the features to produce various sub-areas of the image. The DAMSM delivers fine-grained image-text identical loss to generative networks. This study, first describe text phrases and the model will generate a photorealistic high-resolution image composed of features with high accuracy. Next, model will fine-tune the selected features of face images and it will be left to the control of the user. The result shows that the proposed AttnGAN-DAMSM model delivers the performance metrics like structural similarity index measure (SSIM), feature similarity index measure (FSIM) and frechet inception distance (FID) using CelebA and CUHK face sketch (CUFS) dataset. For CelebFaces attribute (CelebA) dataset, the SSIM achieves 78.82% and for CUFS dataset, the SSIM achieves 81.45% which ensures accurate face synthesis and editing compared with existing methods such as GAN, SuperstarGAN and identity-sensitive GAN (IsGAN) models.</span></p>

Ultrasound breast images denoising using generative adversarial networks (GANs)

INTRODUCTION: Ultrasound in conjunction with mammography imaging, plays a vital role in the early detection and diagnosis of breast cancer. However, speckle noise affects medical ultrasound images and degrades visual radiological interpretation. Speckle carries information about the interactions of the ultrasound pulse with the tissue microstructure, which generally causes several difficulties in identifying malignant and benign regions. The application of deep learning in image denoising has gained more attention in recent years. OBJECTIVES: The main objective of this work is to reduce speckle noise while preserving features and details in breast ultrasound images using GAN models. METHODS: We proposed two GANs models (Conditional GAN and Wasserstein GAN) for speckle-denoising public breast ultrasound databases: BUSI, DATASET A, AND UDIAT (DATASET B). The Conditional GAN model was trained using the Unet architecture, and the WGAN model was trained using the Resnet architecture. The image quality results in both algorithms were measured by Peak Signal to Noise Ratio (PSNR, 35–40 dB) and Structural Similarity Index (SSIM, 0.90–0.95) standard values. RESULTS: The experimental analysis clearly shows that the Conditional GAN model achieves better breast ultrasound despeckling performance over the datasets in terms of PSNR = 38.18 dB and SSIM = 0.96 with respect to the WGAN model (PSNR = 33.0068 dB and SSIM = 0.91) on the small ultrasound training datasets. CONCLUSIONS: The observed performance differences between CGAN and WGAN will help to better implement new tasks in a computer-aided detection/diagnosis (CAD) system. In future work, these data can be used as CAD input training for image classification, reducing overfitting and improving the performance and accuracy of deep convolutional algorithms.

Fault identification of product design using fuzzy clustering generative adversarial network (FCGAN) model

Fault identification of product design using fuzzy clustering generative adversarial network (FCGAN) model

Fast high-fidelity flood inundation map generation by super-resolution techniques

Abstract Flooding is one of the most frequent natural hazards and causes more economic loss than all the other natural hazards. Fast and accurate flood prediction has significance in preserving lives, minimizing economic damage, and reducing public health risks. However, current methods cannot achieve speed and accuracy simultaneously. Numerical methods can provide high-fidelity results, but they are time-consuming, particularly when pursuing high accuracy. Conversely, neural networks can provide results in a matter of seconds, but they have shown low accuracy in flood map generation by all existing methods. This work combines the strengths of numerical methods and neural networks and builds a framework that can quickly and accurately model the high-fidelity flood inundation map with detailed water depth information. In this paper, we employ the U-Net and generative adversarial network (GAN) models to recover the lost physics and information from ultra-fast, low-resolution numerical simulations, ultimately presenting high-resolution, high-fidelity flood maps as the end results. In this study, both the U-Net and GAN models have proven their ability to reduce the computation time for generating high-fidelity results, reducing it from 7–8 h down to 1 min. Furthermore, the accuracy of both models is notably high.

Jamming Waveform Generation Method Based on Generative Adversarial Network Model

Jamming Waveform Generation Method Based on Generative Adversarial Network Model

Research on Innovative Practice and Theoretical Exploration of Visual Communication Design for Future Media

Abstract The rapid development of the new media era has brought brand new opportunities for visual communication design, and the creation concept and expression of visual communication design have undergone obvious changes. In this paper, the ant colony algorithm is applied to automatically arrange graphic text in visual communication design to achieve the purpose of visual communication design innovation. Additionally, an image synthesis model based on generative adversarial networks is proposed for visual communication design, and examples are analyzed to analyze visual communication design in the context of future media. As a result of the study, the average loss values of the generator and discriminator of its generative adversarial network model are 9.894 and 2.319, respectively, and the Inception score (3.74) corresponding to the GAN is undoubtedly the highest, which has a high communication effect. This study enhances the effectiveness of visual communication design, promotes efficient communication and interaction with the audience, and promotes the innovative practice and theoretical exploration of visual communication design.

Automatic segmentation of 2D echocardiography ultrasound images by means of generative adversarial network.

Automated cardiac segmentation from two-dimensional (2D) echocardiographic images is a crucial step toward improving clinical diagnosis. Anatomical heterogeneity and inherent noise, however, present technical challenges and lower segmentation accuracy. The objective of this study is to propose a method for the automatic segmentation of the ventricular endocardium, the myocardium, and the left atrium, in order to accurately determine clinical indices. Specifically, we suggest using the recently introduced pixel-to-pixel Generative Adversarial Network (Pix2Pix GAN) model for accurate segmentation. To accomplish this, we integrate the backbone PatchGAN model for the discriminator and the UNET for the generator, for building the Pix2Pix GAN. The resulting model produces precisely segmented images, thanks to UNET's capability for precise segmentation and PatchGAN's capability for fine-grained discrimination. For the experimental validation, we use the Cardiac Acquisitions for Multi-structure Ultrasound Segmentation (CAMUS) dataset, which consists of echocardiographic images from 500 patients in 2-chamber (2CH) and 4-chamber (4CH) views at the end-diastolic (ED) and end-systolic (ES) phases. Similarly to state-of-the-art studies on the same dataset, we followed the same train-test splits. Our results demonstrate that the proposed GAN-based technique improves segmentation performance for clinical and geometrical parameters compared to the state-of-the-art methods. More precisely, throughout the ED and ES phases, the mean Dice values for the left ventricular endocardium reached 0.961 and 0.930 for 2CH, and 0.959 and 0.950 for 4CH, respectively. Furthermore, the average ejection fraction correlation and Mean Absolute Error obtained were 0.95 and 3.2ml for 2CH, and 0.98 and 2.1ml for 4CH, outperforming the state-of-the-art results.

Updated Primer on Generative Artificial Intelligence and Large Language Models in Medical Imaging for Medical Professionals.

The emergence of Chat Generative Pre-trained Transformer (ChatGPT), a chatbot developed by OpenAI, has garnered interest in the application of generative artificial intelligence (AI) models in the medical field. This review summarizes different generative AI models and their potential applications in the field of medicine and explores the evolving landscape of Generative Adversarial Networks and diffusion models since the introduction of generative AI models. These models have made valuable contributions to the field of radiology. Furthermore, this review also explores the significance of synthetic data in addressing privacy concerns and augmenting data diversity and quality within the medical domain, in addition to emphasizing the role of inversion in the investigation of generative models and outlining an approach to replicate this process. We provide an overview of Large Language Models, such as GPTs and bidirectional encoder representations (BERTs), that focus on prominent representatives and discuss recent initiatives involving language-vision models in radiology, including innovative large language and vision assistant for biomedicine (LLaVa-Med), to illustrate their practical application. This comprehensive review offers insights into the wide-ranging applications of generative AI models in clinical research and emphasizes their transformative potential.

Software Defect Prediction via Generative Adversarial Networks and Pre-Trained Model

Software Defect Prediction via Generative Adversarial Networks and Pre-Trained Model

Improving synthetic media generation and detection using generative adversarial networks.

Synthetic images ar---e created using computer graphics modeling and artificial intelligence techniques, referred to as deepfakes. They modify human features by using generative models and deep learning algorithms, posing risks violations of social media regulations and spread false information. To address these concerns, the study proposed an improved generative adversarial network (GAN) model which improves accuracy while differentiating between real and fake images focusing on data augmentation and label smoothing strategies for GAN training. The study utilizes a dataset containing human faces and employs DCGAN (deep convolutional generative adversarial network) as the base model. In comparison with the traditional GANs, the proposed GAN outperform in terms of frequently used metrics i.e., Fréchet Inception Distance (FID) and accuracy. The model effectiveness is demonstrated through evaluation on the Flickr-Faces Nvidia dataset and Fakefaces d--ataset, achieving an FID score of 55.67, an accuracy of 98.82%, and an F1-score of 0.99 in detection. This study optimizes the model parameters to achieve optimal parameter settings. This study fine-tune the model parameters to reach optimal settings, thereby reducing risks in synthetic image generation. The article introduces an effective framework for both image manipulation and detection.

Innovative Application of Chinese Landscape Culture Painting Elements in AI Art Generation

Abstract In recent years, the swift advancement of artificial intelligence (AI) has significantly propelled the capabilities of data generation, a pivotal technology underpinning AI development. This has led to remarkable innovations across various domains, including images, text, and speech. In this study, we introduce a sophisticated image translation network tailored for AI-driven art generation of landscape painting elements. This network is enhanced by integrating a self-attention mechanism with orthogonal Jacobi regularization, aiming to elevate the quality of the generated artwork. Furthermore, we developed a landscape style transfer model using the image above translation network to encapsulate elements of Chinese landscape cultural paintings. This model emulates the artistic process employed by human artists, effectively capturing the essence of the content and infusing the intended style. The efficacy of the generated images is quantitatively assessed through Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) values. Comparative analysis of the style transfer outcomes across three models reveals that the Generative Adversarial Network (GAN) model exhibits the lowest PSNR and SSIM values. Although the CycleGAN model achieves commendable style transfer, its visual impact remains less pronounced in comparison to the Wasserstein GAN (WGAN). Subjective evaluations of image quality and style fidelity between the generated images and the input stylized images indicate that the WGAN outperforms other models. It achieves an average content evaluation score of 4.11 and a style score of 4.2 across nine style transformations, surpassing the average scores obtained by competing models.

Art design integrating visual relation and affective semantics based on Convolutional Block Attention Mechanism-generative adversarial network model.

Scene-based image semantic extraction and its precise sentiment expression significantly enhance artistic design. To address the incongruity between image features and sentiment features caused by non-bilinear pooling, this study introduces a generative adversarial network (GAN) model that integrates visual relationships with sentiment semantics. The GAN-based regularizer is utilized during training to incorporate target information derived from the contextual information into the process. This regularization mechanism imposes stronger penalties for inaccuracies in subject-object type predictions and integrates a sentiment corpus to generate more human-like descriptive statements. The capsule network is employed to reconstruct sentences and predict probabilities in the discriminator. To preserve crucial focal points in feature extraction, the Convolutional Block Attention Mechanism (CBAM) is introduced. Furthermore, two bidirectional long short-term memory (LSTM) modules are used to model both target and relational contexts, thereby refining target labels and inter-target relationships. Experimental results highlight the model's superiority over comparative models in terms of accuracy, BiLingual Evaluation Understudy (BLEU) score, and text preservation rate. The proposed model achieves an accuracy of 95.40% and the highest BLEU score of 16.79, effectively capturing both the label content and the emotional nuances within the image.

Real Time Quality Detection and Automatic Recognition of Concrete Structures: Image Processing Algorithm Based on Deep Learning

The safety and durability of concrete structure is an important issue in engineering quality management. In this paper, an image processing algorithm based on deep learning is proposed to realize real-time quality inspection and automatic defect identification of concrete structures. This algorithm uses the Convolutional Neural Network (CNN) to automatically extract the features of concrete surface quality images, and then identify the existence of defects, thus improving the detection efficiency and accuracy. In this paper, for this method, data samples with different specific structures are collected and manually labeled to the data set; then, a multi-layer CNN model with convolution layer, pool layer and full connection layer is designed to train the model, and then image enhancement technology is used to reduce information noise, and data enhancement technology is used to improve the problem-solving ability of the model. In addition, the strategy of Dropout is used to close some nodes to reduce parameters and prevent over-fitting, and the learning rate is adjusted to optimize the classification effect. In addition, this study constructs an all-weather real-time detection framework, including data acquisition, preprocessing, feature extraction, classification and identification and decision-making alarm system, to ensure the rapid positioning of the detection system. To sum up, the results of this study show that the deep learning image processing algorithm has good contrast performance in the field of real-time quality inspection of concrete structures. CNN model has better performance than GAN (Generative Adversarial Network) and LSTM (Long Short-Term Memory) models in detection time, defect identification resolution and detection accuracy. The maximum detection time is 366ms and the shortest is 213 ms. The successful development of this algorithm provides a new method for automatic detection of concrete structure quality, which has important application value in engineering practice. This research has a broad development prospect.

U-shaped convolutional transformer GAN with multi-resolution consistency loss for restoring brain functional time-series and dementia diagnosis.

The blood oxygen level-dependent (BOLD) signal derived from functional neuroimaging is commonly used in brain network analysis and dementia diagnosis. Missing the BOLD signal may lead to bad performance and misinterpretation of findings when analyzing neurological disease. Few studies have focused on the restoration of brain functional time-series data. In this paper, a novel U-shaped convolutional transformer GAN (UCT-GAN) model is proposed to restore the missing brain functional time-series data. The proposed model leverages the power of generative adversarial networks (GANs) while incorporating a U-shaped architecture to effectively capture hierarchical features in the restoration process. Besides, the multi-level temporal-correlated attention and the convolutional sampling in the transformer-based generator are devised to capture the global and local temporal features for the missing time series and associate their long-range relationship with the other brain regions. Furthermore, by introducing multi-resolution consistency loss, the proposed model can promote the learning of diverse temporal patterns and maintain consistency across different temporal resolutions, thus effectively restoring complex brain functional dynamics. We theoretically tested our model on the public Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, and our experiments demonstrate that the proposed model outperforms existing methods in terms of both quantitative metrics and qualitative assessments. The model's ability to preserve the underlying topological structure of the brain functional networks during restoration is a particularly notable achievement. Overall, the proposed model offers a promising solution for restoring brain functional time-series and contributes to the advancement of neuroscience research by providing enhanced tools for disease analysis and interpretation.

Artificial intelligence, racialization, and art resistance

Contemporary culture is shaped by information technology, in particular, artificial intelligence applications. One of the goals of this paper is to analyze how artistic practices could use machine learning algorithms as racial resistance. In addition, to remove from the black box how these applications work by relating the technical process that artists face. It will analyze the aesthetic and narrative perception around artificial intelligence, racism in the creation of data sets to train these algorithms and the possibilities that artificial intelligence opens to rethink concepts such as intelligence and imagination. This research is framed from the posthumanist subjectivity that uses critical imagination to question the classic and Eurocentric definition of human as a measure of what surrounds us. Finally, I will describe the work of the contemporary artist Linda Dounia and her interest in incorporating her experience as a Senegalese woman in the training of Generative Adversarial Networks models to reflect on her identity.

Revolution in Image Data Collection: CycleGAN as a Dataset Generator

Computer vision, deep learning, and pattern recognition are just a few fields where image data collection has become crucial. The Cycle Generative Adversarial Network has become one of the most effective instruments in the recent revolution in image data collection. This research aims to comprehend the impact of CycleGAN on the collection of image datasets. CycleGAN, a variant of the Generative Adversarial Network model, has enabled the unprecedented generation of image datasets. CycleGAN can transform images from one domain to another without manual annotation by employing adversarial learning between the generator and discriminator. This means generating image datasets quickly and efficiently for various purposes, from object recognition to data augmentation. One of the most fascinating features of CycleGAN is its capacity to alter an image's style and characteristics. Using CycleGAN to generate unique and diverse datasets assists deep learning models in overcoming visual style differences. This is a significant development in understanding how machine learning models can comprehend visual art concepts. CycleGAN's use as a data set generator has altered the landscape of image data collection. CycleGAN has opened new doors in technological innovation and data science with its proficiency in generating diverse and unique datasets. This research will investigate in greater detail how CycleGAN revolutionized the collection of image datasets and inspired previously unconceived applications.

Attention-Based Generative Adversarial Network Model for RC Column Backbone Curve Identification

Attention-Based Generative Adversarial Network Model for RC Column Backbone Curve Identification

Regression generative adversarial network based on bounded losses for prediction of free calcium oxide in cement clinker

The data imbalance problem caused by multi-time scales phenomenon affects the prediction accuracy, validity and robustness of free calcium oxide (fCaO) content in cement clinker calcination process. Focusing on this problem, we propose an regression generative adversarial network model to predict fCaO content, which contains a generator, discriminator and predictor. Generator and discriminator are designed as bounded loss generative adversarial network to solve mode collapse problem and improve the stability. They learn actual data features in adversarial learning style and produce fake data to enlarge the scale and feature space of actual data to train predictor and finally achieve the prediction of fCaO content, which overcomes the problem of data imbalance. For performance assessment, we visually evaluate the validity of generated data from the perspective of univariate distribution and multivariate joint distribution and invent sequence change tendency consistency index (TCI) to evaluate the robustness of fCaO content prediction. Experiments implemented by cement production data demonstrate that the proposed model has advantages in accuracy, availability and robustness in fCaO content prediction, especially TCI is higher 22.69 percentage points than that of without data augmentation.

Transfer Learning-Based Generative Adversarial Network Model for Tropical Cyclone Wind Speed Reconstruction From SAR Images

Transfer Learning-Based Generative Adversarial Network Model for Tropical Cyclone Wind Speed Reconstruction From SAR Images

Customized design of amorphous solids by generative deep learning

<p>The design of advanced amorphous solids, such as metallic glasses, with targeted properties through artificial intelligence signifies a paradigmatic shift in physical metallurgy and materials technology. Here, we developed a machine learning architecture that facilitates the generation of metallic glasses with targeted multifunctional properties. Our architecture integrates the state-of-the-art unsupervised generative adversarial network model with supervised models, allowing the incorporation of general prior knowledge, derived from thousands of data points across a vast range of alloy compositions, into the creation of data points for a specific type of composition, which overcame the common issue of data scarcity typically encountered in the design of a given type of metallic glasses. Using our generative model, we have successfully designed copper-based metallic glasses, which display exceptionally high hardness or a remarkably low modulus. Notably, our architecture can not only explore uncharted regions in the targeted compositional space but also permits self-improvement after experimental validated data points are added to the initial dataset for subsequent cycles of data generation, hence paving the way for the customized design of amorphous solids without human intervention.</p>