Skip to content
Free planNo credit card requiredStart writing
AI for Research home
AI for Research home
Dashboard
Sign inGet started

Search 250 million research papers

Read the abstract, see who wrote it and who cites it, and get the citation in APA, MLA, Chicago or Harvard.

About 10,000 papers for “Generative adversarial network”

Generative Adversarial Network.

Chao Zeng (452370), Chengchao Wang (13851254), Xueqin Xiong (21567940) et al. · Figshare · 2025

<div> Monitoring the status of circular saw blades is an effective measure to ensure the production efficiency and safety of spent fuel assembly cutting. However, the prediction of wear during the cutting of stainless steel shells of spent fuel assemblies by circular saw blades is not entirely accurate in complicated working conditions. The main challenges include deficiency of data acquisition, signal features extracting complex process, and insufficient robustness of models. To enhance the precision of forecasting consequence, a circular saw blade wear prediction method combining generative adversarial network (GAN) and CNN-LSTM models is proposed. The main fault types during the cutting of stainless steel shells by circular saw blades should be identified in advance, and vibration signals of each fault state is able to be collected then. The collected data is supposed to be preprocessed through sampling overlapping, single-layer wavelet transform denoising, and normalization. GAN optimized by the Pearson correlation coefficient (PCC) has been utilized aiming to expand the data volume of each fault state to 300 samples and resulting in a total data volume of 2100 samples; A CNN-LSTM model based on dual feature fusion has been established to identify the wear status of circular saw blades, achieving an accuracy rate of 100%, higher than Long Short-Term Memory (LSTM) neural networks (86.2%) and Radial Basis Function Neural Networks (RBFNNs) (94.9%). This study effectively solves the problem of small sample sizes for circular saw blade wear data, and provides an efficient and accurate method for circular saw blade wear identification under complex working conditions, which has important practical significance for improving the safety and efficiency of spent fuel assembly cutting. </div>

Cited by 0Open access

Generative Adversarial Network

Orhan Gazi Yalçın · Apress eBooks · 2020

Generative adversarial networks (GANs) are a type of deep learning model designed by Ian Goodfellow and his colleagues in 2014.

Cited by 6

Enhancing generative adversarial network

Rajbeer Kaur, Amanpreet Kaur, Kirandeep Kaur · Global Journal of Engineering and Technology Advances · 2024

The paper provides a comprehensive review of various GAN methods from the perspectives of theory, and applications. GAN algorithms' mathematical representations, and structures are detailed. The commonalities and differences among these GANs methods are compared. Theoretical issues related to GANs are explored, and typical applications in various fields are showcased. Future scope of research problems for GANs are also discussed in the paper.

Cited by 0Open access

Controllable Generative Adversarial Network

Minhyeok Lee, Junhee Seok · IEEE Access · 2019

Recently introduced generative adversarial networks (GANs) have been shown numerous promising results to generate realistic samples. In the last couple of years, it has been studied to control features in synthetic samples generated by the GAN. Auxiliary classifier GAN (ACGAN), a conventional method to generate conditional samples, employs a classification layer in discriminator to solve the problem. However, in this paper, we demonstrate that the auxiliary classifier can hardly provide good guidance for training of the generator, where the classifier suffers from overfitting. Since the generator learns from classification loss, such a problem has a chance to hinder the training. To overcome this limitation, here, we propose a controllable GAN (ControlGAN) structure. By separating a feature classifier from the discriminator, the classifier can be trained with data augmentation technique, which can support to make a fine classifier. Evaluated with the CIFAR-10 dataset, ControlGAN outperforms AC-WGAN-GP which is an improved version of the ACGAN, where Inception score of the ControlGAN is 8.61 ± 0.10. Furthermore, we demonstrate that the ControlGAN can generate intermediate features and opposite features for interpolated input and extrapolated input labels that are not used in the training process. It implies that the ControlGAN can significantly contribute to the variety of generated samples.

Cited by 85Open access

Survey of generative adversarial network

Zhenglong Wang, ZHANG Baowen · SHILAP Revista de lepidopterología · 2021

Firstly, the basic theory, application scenarios and current state of research of GAN (generative adversarial network) were introduced, and the problems need to be improved were listed. Then, recent research, improvement mechanism and model features in 2 categories and 7 subcategories revolved around 3 points (improving model training efficiency, improving the quality of generated samples, and reducing the possibility of model collapse) were generalized and summarized. Finally, 3 future research directions were discussed.

Cited by 6Open access

Metric-based Generative Adversarial Network

Guoxian Dai, Jin Xie, Yi Fang · 2017

Existing methods of generative adversarial network (GAN) use different criteria to distinguish between real and fake samples, such as probability [9],energy [44] energy or other losses [30]. In this paper, by employing the merits of deep metric learning, we propose a novel metric-based generative adversarial network (MBGAN), which uses the distance-criteria to distinguish between real and fake samples. Specifically, the discriminator of MBGAN adopts a triplet structure and learns a deep nonlinear transformation, which maps input samples into a new feature space. In the transformed space, the distance between real samples is minimized, while the distance between real sample and fake sample is maximized. Similar to the adversarial procedure of existing GANs, a generator is trained to produce synthesized examples, which are close to real examples, while a discriminator is trained to maximize the distance between real and fake samples to a large margin. Meanwhile, instead of using a fixed margin, we adopt a data-dependent margin [30], so that the generator could focus on improving the synthesized samples with poor quality, instead of wasting energy on well-produce samples. Our proposed method is verified on various benchmarks, such as CIFAR-10, SVHN and CelebA, and generates high-quality samples.

Cited by 24

WAVESTYLEGAN: WAVELET-GENERATIVE ADVERSARIAL NETWORK

U. VARABEI, А. E. Malevich · HERALD OF POLOTSK STATE UNIVERSITY Series С FUNDAMENTAL SCIENCES · 2025

In this paper a novel generative adversarial network for images WaveStyleGAN that is based on StyleGAN-like architectures, was developed. Key features of the model suggested are processing of wavelet features of images, usage of self-modulated convolutions and modified blocks of Fast Fourier Convolutions in the discriminator. The changes implemented helped to reduce model complexity and its size when compared to the base models’ versions. The model was trained on a dataset of human faces FFHQ in 1024×1024 resolution. It was able to keep a high quality of generated images with considerable decrease in a number of training iterations. Additionally, inference time on CPU was reduced by up to 3 times when compared to the original model, which significantly expands its capabilities for deployments to environments which don’t provide access to computations on GPU.

Cited by 0Open access

HGAN: Hyperbolic Generative Adversarial Network

Diego Lazcano, Nicolas Fredes Franco, Werner Creixell · IEEE Access · 2021

Recently, Hyperbolic Spaces in the context of Non-Euclidean Deep Learning have gained popularity because of their ability to represent hierarchical data. We propose that it is possible to take advantage of the hierarchical characteristic present in the images by using hyperbolic neural networks in a GAN architecture. In this study, different configurations using fully connected hyperbolic layers in the GAN, WGAN, CGAN, and the mapping network of the StyleGAN2 are tested in what we call the HGAN, HWGAN, HCGAN, and HStyleGAN, respectively. Furthermore, we test multiple values of curvature and introduce an exponential way to train it. The results are measured using the Inception Score (IS) and the Fréchet Inception Distance (FID) over the MNIST dataset and with FID over CIFAR-10. Depending on the configuration and space curvature, better results are achieved for each proposed hyperbolic version than their euclidean counterpart.

Cited by 10Open access

Advances in generative adversarial network

Wanliang WANG, Zhuorong LI · SHILAP Revista de lepidopterología · 2018

Generative adversarial network (GAN) have swiftly become the focus of considerable research in generative models soon after its emergence,whose academic research and industry applications have yielded a stream of further progress along with the remarkable achievements of deep learning.A broad survey of the recent advances in generative adversarial network was provided.Firstly,the research background and motivation of GAN was introduced.Then the recent theoretical advances of GAN on modeling,architectures,training and evaluation metrics were reviewed.Its state-of-the-art applications and the extensively used open source tools for GAN were introduced.Finally,issues that require urgent solutions and works that deserve further investigation were discussed.

Cited by 4Open access