☆ 4.7 Review

A survey on GANs for computer vision: Recent research, analysis and taxonomy

COMPUTER SCIENCE REVIEW (2023)

Related references

Note: Only part of the references are listed.

Article Computer Science, Information Systems

MIEGAN: Mobile Image Enhancement via a Multi-Module Cascade Neural Network

Zhaoqing Pan et al.

Summary: This paper presents a novel mobile image enhancement method called MIEGAN, which is based on a generative adversarial network. It consists of a multi-module cascade generative network and an adaptive multi-scale discriminative network. The experiments on DSLR photo enhancement dataset and MIT-FiveK dataset have verified the effectiveness of the proposed method.

IEEE TRANSACTIONS ON MULTIMEDIA (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

An improved GAN with transformers for pedestrian trajectory prediction models

Zezheng Lv et al.

Summary: The paper introduces a novel Generative Adversarial Network model for predicting future pedestrian trajectories, capturing path uncertainty and generating more reasonable results. The method includes a generator with convolutional self-attention and Mish Feed-Forward Network, as well as a discriminator for classifying predicted and ground truth paths as socially acceptable.

INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS (2022)

Add to Collection

Article Agriculture, Multidisciplinary

FWDGAN-based data augmentation for tomato leaf disease identification

Mingxuan Li et al.

Summary: This paper proposes a FWDGAN method based on WDBlock for generating high-quality tomato leaf disease images. By combining ResNet and InceptionV1 for feature extraction, and using DSC-Discriminator, FWDGAN outperforms DCGAN in terms of data quality and parameter quantity.

COMPUTERS AND ELECTRONICS IN AGRICULTURE (2022)

Add to Collection

Article Agriculture, Multidisciplinary

GrapeGAN: Unsupervised image enhancement for improved grape leaf disease recognition

Haibin Jin et al.

Summary: This paper proposes a novel architecture called GrapeGAN for generating clearer and structurally complete grape leaf disease images. Experimental results demonstrate that GrapeGAN outperforms other models and efficiently detects grape leaf disease.

COMPUTERS AND ELECTRONICS IN AGRICULTURE (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Lightweight dynamic conditional GAN with pyramid attention for text-to-image synthesis

Lianli Gao et al.

Summary: The text-to-image synthesis task aims to generate high-resolution images, which can lead to increased network parameters and complexity. To address these issues, this paper proposes the LD-CGAN method, which achieves the generation of 64(2) and 128(2) images through effective information compensation.

PATTERN RECOGNITION (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

CEGAN: Classification Enhancement Generative Adversarial Networks for unraveling data imbalance problems

Sungho Suh et al.

Summary: The research introduces a classification enhancement generative adversarial networks (CEGAN) for improving prediction accuracy in data imbalanced conditions by enhancing the quality of generated synthetic minority data. Additionally, an ambiguity reduction method using the generated synthetic minority data is proposed. Results from five benchmark datasets demonstrate significant improvements in classification performance when approximating the real data distribution using CEGAN compared to standard data augmentation methods.

NEURAL NETWORKS (2021)

Add to Collection

Article Geosciences, Multidisciplinary

Stochastic Pix2pix: A New Machine Learning Method for Geophysical and Well Conditioning of Rule-Based Channel Reservoir Models

Wen Pan et al.

Summary: Accurately reproducing geological heterogeneity in subsurface models is critical but can be time-consuming and computationally intensive. Overfitting of data and slow convergence due to high dimensionality are common problems in modeling. To address these issues, a new machine learning approach is introduced to parameterize stochastic reservoir models into low-dimensional Gaussian random variables.

NATURAL RESOURCES RESEARCH (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Learning to synthesise the ageing brain without longitudinal data

Tian Xia et al.

Summary: This study introduces a deep learning-based method for simulating subject-specific brain ageing trajectories, conditioned on age and Alzheimer's Disease status, without relying on longitudinal data. The method synthesizes images based on age and AD status to address the challenging problem of preserving subject identity.

MEDICAL IMAGE ANALYSIS (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

MFF-GAN: An unsupervised generative adversarial network with adaptive and gradient joint constraints for multi-focus image fusion

Hao Zhang et al.

Summary: This paper introduces a new method for multi-focus image fusion, utilizing a generative adversarial network with adaptive and gradient joint constraints to address the issue of detail loss in existing methods. The proposed method demonstrates superiority in both subjective visual effect and quantitative metrics over the state-of-the-art, while also being approximately one order of magnitude faster.

INFORMATION FUSION (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

MISS GAN: A Multi-IlluStrator style generative adversarial network for image to illustration translation

Noa Barzilay et al.

Summary: This paper introduces an unsupervised image-to-illustration translation method based on a multi-style framework that can generate styled yet content preserving illustrations. Compared to existing methods, this approach only requires training once to handle different illustrator styles and effectively uses style information from other images.

PATTERN RECOGNITION LETTERS (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Tackling mode collapse in multi-generator GANs with orthogonal vectors

Wei Li et al.

Summary: In this paper, a new approach named MGO-GAN is proposed to overcome mode collapse in GAN training by employing multiple generators, an encoder, and a discriminator. Experimental results show a significant performance improvement of MGO-GAN in terms of generated data quality and diversity.

PATTERN RECOGNITION (2021)

Add to Collection

Article Mathematics

Dynamics of Fourier Modes in Torus Generative Adversarial Networks

Angel Gonzalez-Prieto et al.

Summary: This study introduces a novel method for analyzing the convergence and stability in the training of Generative Adversarial Networks (GANs). By decomposing the objective function into its Fourier series and studying the dynamics of the truncated series, the research confirms that convergent orbits in GANs are small perturbations of periodic orbits. This theoretically justifies the slow and unstable training observed in GANs.

MATHEMATICS (2021)

Add to Collection

Article Biology

Synthesizing anonymized and labeled TOF-MRA patches for brain vessel segmentation using generative adversarial networks

Tabea Kossen et al.

Summary: Anonymization and data sharing are essential for privacy protection and acquiring large datasets in medical image analysis, especially in neuroimaging. Generative adversarial networks (GANs) show potential in providing anonymous images while maintaining predictive properties. Among the three GANs tested, WGAN-GP-SN showed the highest performance in generating synthetic data for vessel segmentation with U-net. Transfer learning with synthetic data demonstrated improved model performance, particularly for individual patients.

COMPUTERS IN BIOLOGY AND MEDICINE (2021)

Add to Collection

Article Instruments & Instrumentation

An improved DualGAN for near-infrared image colorization

Wei Liang et al.

Summary: This paper proposes an improved DualGAN architecture to address the colorization problem of near-infrared images by leveraging the advantages of deep learning and generative adversarial networks. The use of dual deep learning networks establishes a translation relationship between NIR and RGB images without the need for paired and labeled images. Additionally, a mixed loss function is designed to reduce the generation of incorrect images by the generators.

INFRARED PHYSICS & TECHNOLOGY (2021)

Add to Collection

Article Physics, Applied

Super-resolution generative adversarial network (SRGAN) enabled on-chip contact microscopy

Hao Zhang et al.

Summary: A deep learning-based contact imaging technique has been successfully demonstrated on a CMOS chip, achieving spatial resolution as high as 1 micron. By using super-resolution generative adversarial networks, the image quality is improved, allowing for sub-micron spatial resolution across the entire chip area. This contact imaging approach eliminates the need for lenses or multi-frame acquisition, making it powerful and cost-effective.

JOURNAL OF PHYSICS D-APPLIED PHYSICS (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Positional Encoding as Spatial Inductive Bias in GANs

Rui Xu et al.

Summary: In this study, we demonstrate the importance of implicit positional encoding in capturing global structures when using zero padding in convolutional generators, showing that zero padding may lead to spatial bias imbalance. Additionally, we propose a new multi-scale training strategy based on a more flexible positional encoding, which significantly enhances the state-of-the-art unconditional generator StyleGAN2 and improves the versatility of SinGAN for image manipulation.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Improved Training of Generative Adversarial Networks Using Decision Forests

Yan Zuo et al.

Summary: While Generative Adversarial Networks (GANs) are powerful generative models, they are difficult to train and suffer from optimization instability. Recent methods for addressing this issue have focused on improving the behavior of the discriminator in GANs through loss function modification, gradient regularization, and weight normalization. This study proposes a novel approach by embedding decision forests' discriminating capabilities within the GAN's discriminator, showing significant improvements in the Frechet-Inception Distance (FID) scores over existing GAN baselines.

2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION WACV 2021 (2021)

Add to Collection

Proceedings Paper Engineering, Multidisciplinary

A Review on Generative Adversarial Networks

Dilum Maduranga De Silva et al.

Summary: This review paper discusses the differences in existing generative adversarial network architectures and future research directions. The authors aim to use this knowledge to address research gaps identified in the existing literature.

2021 6TH INTERNATIONAL CONFERENCE FOR CONVERGENCE IN TECHNOLOGY (I2CT) (2021)

Add to Collection

Article Computer Science, Theory & Methods

A survey on generative adversarial networks for imbalance problems in computer vision tasks

Vignesh Sampath et al.

Summary: This article discusses the importance of image and data acquisition, preprocessing, and pattern recognition in computer vision application development. Particularly, the occurrence of imbalance issues in complex real-world problems is inevitable. Research shows that techniques based on GANs are able to address these imbalances effectively and boost the performance of computer vision algorithms.

JOURNAL OF BIG DATA (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Exploring the Effects of Blur and Deblurring to Visual Object Tracking

Qing Guo et al.

Summary: In this study, a Blurred Video Tracking (BVT) benchmark was introduced to evaluate 25 different visual trackers, revealing that light motion blur may enhance tracking accuracy while heavy blur typically impairs performance. The research also showed that image deblurring can improve accuracy on heavily-blurred videos but may hinder performance on lightly-blurred ones. Furthermore, a new GAN-based scheme was proposed to enhance a tracker's robustness to motion blur, successfully improving the accuracy of 6 state-of-the-art trackers on motion-blurred videos.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2021)

Add to Collection

Letter Hospitality, Leisure, Sport & Tourism

Deepfake: a social construction of technology perspective

Andrei O. J. Kwok et al.

Summary: The emergence of deepfake videos as a new form of media manipulation has raised concerns due to its malicious use for fraud and misrepresentation. More research is needed to understand the Generative Adversarial Networks behind deepfake technology. There is a call for exploring the potential beneficial applications of deepfake technology despite existing skepticism.

CURRENT ISSUES IN TOURISM (2021)

Add to Collection

Article Computer Science, Information Systems

ProEGAN-MS: A Progressive Growing Generative Adversarial Networks for Electrocardiogram Generation

Haixu Yang et al.

Summary: This study proposed a ProGAN-based ECG sample generation model, ProEGAN-MS, to address data imbalance issues, demonstrating higher fidelity and diversity of the generated data compared to other GAN-based ECG augmentation methods.

IEEE ACCESS (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

On Data Augmentation for GAN Training

Ngoc-Trung Tran et al.

Summary: The study demonstrates that optimizing data augmentation in Generative Adversarial Networks can help the generator better learn the distribution of the original data, which is crucial for various fields such as medical applications.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

GANILLA: Generative adversarial networks for image to illustration translation

Samet Hicsonmez et al.

IMAGE AND VISION COMPUTING (2020)

Add to Collection

Article Radiology, Nuclear Medicine & Medical Imaging

Feasibility of new fat suppression for breast MRI using pix2pix

Mio Mori et al.

JAPANESE JOURNAL OF RADIOLOGY (2020)

Add to Collection

Article Computer Science, Information Systems

PlethAugment: GAN-Based PPG Augmentation for Medical Diagnosis in Low-Resource Settings

Dani Kiyasseh et al.

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS (2020)

Add to Collection

Editorial Material Computer Science, Artificial Intelligence

GPT-3: Its Nature, Scope, Limits, and Consequences

Luciano Floridi et al.

MINDS AND MACHINES (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

Loss Functions of Generative Adversarial Networks (GANs): Opportunities and Challenges

Zhaoqing Pan et al.

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE (2020)

Add to Collection

Article Computer Science, Information Systems

A SAR-to-Optical Image Translation Method Based on Conditional Generation Adversarial Network (cGAN)

Yu Li et al.

IEEE ACCESS (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

StackGAN plus plus : Realistic Image Synthesis with Stacked Generative Adversarial Networks

Han Zhang et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2019)

Add to Collection

Article Computer Science, Artificial Intelligence

L1-Norm Batch Normalization for Efficient Training of Deep Neural Networks

Shuang Wu et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2019)

Add to Collection

Review Chemistry, Multidisciplinary

Quantum Chemistry in the Age of Quantum Computing

Yudong Cao et al.

CHEMICAL REVIEWS (2019)

Add to Collection

Article Physics, Multidisciplinary

Variational Autoencoder Reconstruction of Complex Many-Body Physics

Ilia A. Luchnikov et al.

ENTROPY (2019)

Add to Collection

Article Acoustics

Emotional Voice Conversion Using Dual Supervised Adversarial Networks With Continuous Wavelet Transform F0 Features

Zhaojie Luo et al.

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING (2019)

Add to Collection

Article Computer Science, Artificial Intelligence

Pros and cons of GAN evaluation measures

Ali Borji

COMPUTER VISION AND IMAGE UNDERSTANDING (2019)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Enhanced Pix2pix Dehazing Network

Yanyun Qu et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Sphere Generative Adversarial Network Based on Geometric Moment Matching

Sung Woo Park et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

Add to Collection

Proceedings Paper Computer Science, Interdisciplinary Applications

Mocycle-GAN: Unpaired Video-to-Video Translation

Yang Chen et al.

PROCEEDINGS OF THE 27TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA (MM'19) (2019)

Add to Collection

Review Management

The Emergence of Deepfake Technology: A Review

Mika Westerlund

TECHNOLOGY INNOVATION MANAGEMENT REVIEW (2019)

Add to Collection

Article Computer Science, Information Systems

Recent Progress on Generative Adversarial Networks (GANs): A Survey

Zhaoqing Pan et al.

IEEE ACCESS (2019)

Add to Collection

Review Pharmacology & Pharmacy

Deep Learning for Drug Design: an Artificial Intelligence Paradigm for Drug Discovery in the Big Data Era

Yankang Jing et al.

AAPS JOURNAL (2018)

Add to Collection

Article Computer Science, Information Systems

Improved Boundary Equilibrium Generative Adversarial Networks

Yanchun Li et al.

IEEE ACCESS (2018)

Add to Collection

Review Biochemistry & Molecular Biology

Deep Learning in Drug Discovery and Medicine; Scratching the Surface

Dibyendu Dana et al.

MOLECULES (2018)

Add to Collection

Article Biochemical Research Methods

Speckle noise reduction in optical coherence tomography images based on edge-sensitive cGAN

Yuhui Ma et al.

BIOMEDICAL OPTICS EXPRESS (2018)

Add to Collection

Article Oncology

The cornucopia of meaningful leads: Applying deep adversarial autoencoders for new molecule development in oncology

Artur Kadurin et al.

ONCOTARGET (2017)

Add to Collection

Article Medicine, Research & Experimental

druGAN: An Advanced Generative Adversarial Autoencoder Model for de Novo Generation of New Molecules with Desired Molecular Properties in Silico

Artur Kadurin et al.

MOLECULAR PHARMACEUTICS (2017)

Add to Collection

Article Computer Science, Artificial Intelligence

RODEO: Robust DE-aliasing autoencOder for real-time medical image reconstruction

Janki Mehta et al.

PATTERN RECOGNITION (2017)

Add to Collection

Article Computer Science, Information Systems

A Survey of Image Synthesis and Editing with Generative Adversarial Networks

Xian Wu et al.

TSINGHUA SCIENCE AND TECHNOLOGY (2017)

Add to Collection

Review Automation & Control Systems

Generative Adversarial Networks: Introduction and Outlook

Kunfeng Wang et al.

IEEE-CAA JOURNAL OF AUTOMATICA SINICA (2017)

Add to Collection

Article Computer Science, Software Engineering

Interactive Reconstruction of Monte Carlo Image Sequences using a Recurrent Denoising Autoencoder

Chakravarty R. Alla Chaitanya et al.

ACM TRANSACTIONS ON GRAPHICS (2017)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization

Xun Huang et al.

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2017)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

Christian Ledig et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

Add to Collection

Article Automation & Control Systems

Diversified Sensitivity-Based Undersampling for Imbalance Classification Problems

Wing W. Y. Ng et al.

IEEE TRANSACTIONS ON CYBERNETICS (2015)

Add to Collection

Article Computer Science, Artificial Intelligence

SMOTE-RSB*: a hybrid preprocessing approach based on oversampling and undersampling for high imbalanced data-sets using SMOTE and rough sets theory

Enislay Ramentol et al.

KNOWLEDGE AND INFORMATION SYSTEMS (2012)

Add to Collection

Article Computer Science, Artificial Intelligence

A Survey of Monte Carlo Tree Search Methods

Cameron B. Browne et al.

IEEE TRANSACTIONS ON COMPUTATIONAL INTELLIGENCE AND AI IN GAMES (2012)

Add to Collection

Article Computer Science, Artificial Intelligence

Wavelet kernel learning

F. Yger et al.

PATTERN RECOGNITION (2011)

Add to Collection

Article Computer Science, Information Systems

Network Coding for Distributed Storage Systems

Alexandros G. Dimakis et al.

IEEE TRANSACTIONS ON INFORMATION THEORY (2010)

Add to Collection

Article Computer Science, Artificial Intelligence

Face Photo-Sketch Synthesis and Recognition

Xiaogang Wang et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2009)

Add to Collection

© Peeref 2019-2024. All rights reserved.