Generative adversarial networks

2020/10/22 by Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza +5 · 104 citations
Computer Science · #Computational Physics and Python Applications #Explainable Artificial Intelligence (XAI) #Generative Adversarial Networks and Image Synthesis

paper · pdf · doi:10.1145/3422622

openalex publication_date 2020/10/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/31

Abstract

Generative adversarial networks are a kind of artificial intelligence algorithm designed to solve the generative modeling problem. The goal of a generative model is to study a collection of training examples and learn the probability distribution that generated them. Generative Adversarial Networks (GANs) are then able to generate more examples from the estimated probability distribution. Generative models based on deep learning are common, but GANs are among the most successful generative models (especially in terms of their ability to generate realistic high-resolution images). GANs have been successfully applied to a wide variety of tasks (mostly in research settings) but continue to present unique challenges and research opportunities because they are based on game theory while most other approaches to generative modeling are based on optimization.

Cited by

• Recent Advances and Applications of Machine Learning in Experimental Solid Mechanics: A Review
• Diffusion-based conditional ECG generation with structured state space models
• SRAGAN: Saliency regularized and attended generative adversarial network for Chinese ink-wash painting style transfer
• DGRM: Diffusion-GAN recommendation model to alleviate the mode collapse problem in sparse environments
• Survey of Different Large Language Model Architectures: Trends, Benchmarks, and Challenges
• Generating Synthetic Data for Medical Imaging
• Computational experiments with cellular-automata generated images reveal intrinsic limitations of convolutional neural networks on pattern recognition tasks
• A physics-informed GAN framework based on model-free data-driven computational mechanics
• G-VAE: Variational autoencoder-based adversarial attacks and defenses in industrial control systems
• Unsupervised learning enabled label-free single-pixel imaging for resilient information transmission through unknown dynamic scattering media
• cryoTIGER: deep-learning based tilt interpolation generator for enhanced reconstruction in cryo electron tomography
• Machine Learning Approaches in Polymer Science: Progress and Fundamental for a New Paradigm
• Learning from Multiple Noisy Augmented Data Sets for Better Cross-Lingual Spoken Language Understanding
• Infrared and Visible Image Fusion: From Data Compatibility to Task Adaption
• A survey of heterogeneous graph neural networks for cybersecurity anomaly detection
• Arbitrary Virtual Try-On Network: Characteristics Preservation and Trade-off between Body and Clothing
• Consensus Synergizes with Memory: A Simple Approach for Anomaly Segmentation in Urban Scenes
• Algorithm fashion designer? ascribed mind and perceived design expertise of AI versus human
• Governance of Generative AI
• Applications of machine learning in gravitational-wave research with current interferometric detectors
• Six Human-Centered Artificial Intelligence Grand Challenges
• 3D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunities
• Pixel-Wise Gamma Correction Mapping for Low-Light Image Enhancement
• Sparse‐View Imaging for Lung Cancer Detection Based on Generative Adversarial Networks and Deep Learning Models
• Robust Image Steganography via Color Conversion
• Machine learning-driven modeling framework for steam co-gasification applications
• A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions
• The ManifoldEM method for cryo-EM: a step-by-step breakdown accompanied by a modern Python implementation
• Deep semi-supervised learning for medical image segmentation: A review
• Latent diffusion model for conditional reservoir facies generation
• A Survey of Multimodal Controllable Diffusion Models
• About exchanging expectation and supremum for conditional Wasserstein GANs
• FMBoost: Boosting Latent Diffusion with Flow Matching
• Brain tumor image pixel segmentation and detection using an aggregation of GAN models with vision transformer
• Generative adversarial networks in electrocardiogram synthesis: Recent developments and challenges
• Using neural style transfer to study the evolution of animal signal design: A case study in an ornamented fish
• MapGenerator: a framework for learning a diffusion model for text promptable map generation
• The ontological quandary of deepfakes
• Multiomics Research: Principles and Challenges in Integrated Analysis
• Breaking the barrier of human-annotated training data for machine learning-aided plant research using aerial imagery
• A deep-learning tool for species-agnostic integration of cancer cell states
• Revealing a coherent cell state landscape across single cell datasets with CONCORD
• Application-driven validation of posteriors in inverse problems
• Toward an Integrated Machine Learning Model of a Proteomics Experiment
• Material dynamics analysis with deep generative model
• Including Aerobic Exercise Into Data-Based Virtual Twins for Glycemic Simulation
• Artificial intelligence in the forest products supply chain: current applications and open challenges
• FreqNet: A Frequency-domain Image Super-Resolution Network with Dicrete Cosine Transform
• Computational nanobody design through deep generative modeling and epitope landscape profiling
• Integrating phenotyping and modelling approaches StomaGAN: improving image-based analysis of stomata through generative adversarial networks
• Going digital to boost safe and sustainable materials innovation markets. The digital safe-and-sustainability-by-design innovation approach of the PINK project
• Enhancing the emotional aspects of language education through generative artificial intelligence (GenAI): A qualitative investigation
• Multi-CGAN: Deep Generative Model-Based Multiproperty Antimicrobial Peptide Design
• Harnessing the power of artificial intelligence to advance cell therapy
• Comprehensive Underwater Object Tracking Benchmark Dataset and Underwater Image Enhancement With GAN
• Where is the disease? Semi-supervised pseudo-normality synthesis from an abnormal image
• NCVX: A User-Friendly and Scalable Package for Nonconvex Optimization in Machine Learning
• Molecular representation learning: cross-domain foundations and future Frontiers
• Knowing False Negatives: An Adversarial Training Method for Distantly Supervised Relation Extraction
• CNN-RNN and Data Augmentation Using Deep Convolutional Generative Adversarial Network for Environmental Sound Classification
• Evaluation of machine learning and deep learning models for the classification of a single extracellular vesicles spectral library
• The Modality-Congruent Carryover Effect: How Difficulty in Identifying (Deep)Fake News Impacts Self-Confidence in Truth Discernment and Susceptibility to Subsequent Disinformation
• Scalable Swin Transformer network for brain tumor segmentation from incomplete MRI modalities
• Machine culture
• Deep entity matching with adversarial active learning
• A Diffusion Model for POI Recommendation
• Advances and Challenges in Deep Lip Reading
• Towards a Robust Deep Neural Network in Texts: A Survey
• Densely connected normalizing flows
• Artificial intelligence and the image war: does exposing AI-generated images as fake limit the images’ influence on perceptions about wars and conflicts?
• IS-DGM: an improved steganography method based on a deep generative model and hyper logistic map encryption via social media networks
• A Comprehensive Survey on Source-Free Domain Adaptation
• UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation
• The Privacy-Utility Tradeoff of Robust Local Differential Privacy
• Playing repeated games with large language models
• Enhancing Gamma Knife Cone-beam Computed Tomography Image Quality Using Pix2pix Generative Adversarial Networks: A Deep Learning Approach
• 3D Human Shape Style Transfer
• Ghost Units Yield Biologically Plausible Backprop in Deep Neural\n Networks
• Advancement of Deep Learning in Pneumonia and Covid-19 Classification and Localization: A Qualitative and Quantitative Analysis
• Exchange means change: An unsupervised single-temporal change detection framework based on intra- and inter-image patch exchange
• The Confluence of Networks, Games and Learning
• The Utility of Deep Learning in Breast Ultrasonic Imaging: A Review. [europepmc]
• Artificial intelligence to deep learning: machine intelligence approach for drug discovery. [europepmc]
• Artificial intelligence and machine learning for medical imaging: A technology review. [europepmc]
• Towards Clinical Application of Artificial Intelligence in Ultrasound Imaging. [europepmc]
• Making Radiomics More Reproducible across Scanner and Imaging Protocol Variations: A Review of Harmonization Methods. [europepmc]
• Comprehensive Survey of Recent Drug Discovery Using Deep Learning. [europepmc]
• An Introduction to Machine Learning Approaches for Biomedical Research. [europepmc]
• Deep Learning on Histopathological Images for Colorectal Cancer Diagnosis: A Systematic Review. [europepmc]
• Bottom-up Coarse-Graining: Principles and Perspectives. [europepmc]
• Application of Computational Biology and Artificial Intelligence in Drug Design. [europepmc]
• Applications of machine learning in metabolomics: Disease modeling and classification. [europepmc]
• AlphaFold2 and its applications in the fields of biology and medicine. [europepmc]
• 2D medical image synthesis using transformer-based denoising diffusion probabilistic model. [europepmc]
• Generative Models as an Emerging Paradigm in the Chemical Sciences. [europepmc]
• Deep Learning Approaches for Data Augmentation in Medical Imaging: A Review. [europepmc]
• Advancing Computational Toxicology by Interpretable Machine Learning. [europepmc]
• Deep Learning for Medical Image-Based Cancer Diagnosis. [europepmc]
• Brain imaging with portable low-field MRI. [europepmc]
• Artificial Intelligence in Regenerative Medicine: Applications and Implications. [europepmc]
• Harnessing the power of synthetic data in healthcare: innovation, application, and privacy. [europepmc]
• How Artificial Intelligence Is Shaping Medical Imaging Technology: A Survey of Innovations and Applications. [europepmc]
• Generative artificial intelligence in drug discovery: basic framework, recent advances, challenges, and opportunities. [europepmc]
• Informing immunotherapy with multi-omics driven machine learning. [europepmc]
• Brain aging patterns in a large and diverse cohort of 49,482 individuals. [europepmc]
• Machine Learning for Toxicity Prediction Using Chemical Structures: Pillars for Success in the Real World. [europepmc]

Related

• Generative Adversarial Networks (GANs): What it can generate and What it cannot?
• Generative Adversarial Networks Bridging Art and Machine Intelligence
• Generative Adversarial Networks (GANs): An Overview of Theoretical Model, Evaluation Metrics, and Recent Developments
• NIPS 2016 Tutorial: Generative Adversarial Networks
• Generative Adversarial Networks: An Overview