Generative Adversarial Networks: An Overview

2017/10/19 by Antonia Creswell, Tom White, Vincent Dumoulin +4 · 1 voice · 4,477 citations
Computer Science · #Advanced Image Processing Techniques #Adversarial system #Artificial intelligence #Computer science #Generative Adversarial Networks and Image Synthesis #Generative grammar #Image (mathematics) #Image and Signal Denoising Methods #Machine learning #Point (geometry) #Process (computing) #Variety (cybernetics) #cs.CV

paper · pdf · doi:10.1109/msp.2017.2765202

published in IEEE Signal Processing Magazine 35(1), 53-65 (Institute of Electrical and Electronics Engineers) · Accepted in the IEEE Signal Processing Magazine Special Issue on Deep Learning for Visual Understanding

arxiv created 2017/10/19 · openalex publication_date 2018/01/01 · arxiv updated 2018/02/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

Abstract

Generative adversarial networks (GANs) provide a way to learn deep representations without extensively annotated training data. They achieve this through deriving backpropagation signals through a competitive process involving a pair of networks. The representations that can be learned by GANs may be used in a variety of applications, including image synthesis, semantic image editing, style transfer, image super-resolution and classification. The aim of this review paper is to provide an overview of GANs for the signal processing community, drawing on familiar analogies and concepts where possible. In addition to identifying different methods for training and constructing GANs, we also point to remaining challenges in their theory and application.

Cited by

• DiffractioNet: Deep-learning seismic and GPR diffraction separation
• Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold
• Survey of Different Large Language Model Architectures: Trends, Benchmarks, and Challenges
• A Transdisciplinary Review of Deep Learning Research and Its Relevance for Water Resources Scientists
• Flexible generation of daily Earth system model projections across radiative forcing scenarios
• Physics-driven local-whole elastic deformation modeling for point cloud representation learning
• Generative Adversarial Networks (GANs): An Overview of Theoretical Model, Evaluation Metrics, and Recent Developments
• Multi-Mapping Image-to-Image Translation with Central Biasing Normalization
• Multiplexed vector beam conversion via complex structured matter
• R3Net: Random Weights, Rectifier Linear Units and Robustness for Artificial Neural Network
• AMAD: Adversarial Multiscale Anomaly Detection on High-Dimensional and Time-Evolving Categorical Data
• Generative adversarial network based on chaotic time series
• Fashion-3DLR: A Controllable 3D Garment Generation Using Pairwise Fashion Elements for Intelligent Design
• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
• Few-Shot Specific Emitter Identification via Integrated Complex Variational Mode Decomposition and Spatial Attention Transfer
• Flow matching Operators for Residual-Augmented Probabilistic Learning of Partial Differential Equations
• Generative Parametric Design (GPD): A framework for real-time geometry generation and on-the-fly multiparametric approximation
• Ideal Observer for Segmentation of Dead Leaves Images
• Data-driven geophysics: from dictionary learning to deep learning
• A Comprehensive Survey of Machine Learning Applied to Radar Signal Processing
• Performance and Efficiency of Climate In-Situ Data Reconstruction: Why Optimized IDW Outperforms kriging and Implicit Neural Representation
• Deep Learning for Environmentally Robust Speech Recognition: An Overview of Recent Developments
• Ranking-Enhanced Anomaly Detection Using Active Learning-Assisted Attention Adversarial Dual AutoEncoders
• Adversarial Training in Affective Computing and Sentiment Analysis: Recent Advances and Perspectives
• Synthetic Data: AI's New Weapon Against Android Malware
• Diffusion-based Surrogate Model for Time-varying Underwater Acoustic Channels
• Fluid Grey 2: How Well Does Generative Adversarial Network Learn Deeper Topology Structure in Architecture That Matches Images?
• Speech2Video: Cross-Modal Distillation for Speech to Video Generation
• Hierarchical Memorization in Large Language Models: Evidence from Citation Generation
• Dynamic Population Distribution Aware Human Trajectory Generation with Diffusion Model
• Deep Learning for Anomaly Detection: A Review
• Governance of Generative AI
• Synthesis of Realistic ECG using Generative Adversarial Networks
• An Introduction to Image Synthesis with Generative Adversarial Nets
• Sparse‐View Imaging for Lung Cancer Detection Based on Generative Adversarial Networks and Deep Learning Models
• Generative Adversarial Networks for Image and Video Synthesis: Algorithms and Applications
• Collaborating Foundation Models for Domain Generalized Semantic Segmentation
• Compression and reconstruction of flotation foam images based on generative adversarial networks
• Postprocessing East African Rainfall Forecasts Using a Generative Machine Learning Model
• Are Deep Learning-Generated Social Media Profiles Indistinguishable from Real Profiles?
• Spatio-temporal masked autoencoder-based phonetic segments classification from ultrasound
• AI in soil moisture remote sensing
• Foram3D: A pipeline for 3D synthetic data generation and rendering of foraminifera for image analysis and reconstruction
• A Review of End-to-End Precipitation Prediction Using Remote Sensing Data: from Divination to Machine Learning
• Towards Strong Certified Defense with Universal Asymmetric Randomization
• Image augmentation with invertible networks in interactive satellite image change detection
• Conveying Meaning through Gestures: An Investigation into Semantic Co-Speech Gesture Generation
• Spoof Face Detection Via Semi-Supervised Adversarial Training
• Movable and Reconfigurable Antennas for 6G: Unlocking Electromagnetic-Domain Design and Optimization
• Attribution Graphs and Causal Probing for Mechanistic Discovery and Bias Repair in Multimodal Generative Learning
• Label-frugal satellite image change detection with generative virtual exemplar learning
• High predictability potential of highly synchronized widespread floods in monsoon regions
• Opinion Paper: “So what if ChatGPT wrote it?” Multidisciplinary perspectives on opportunities, challenges and implications of generative conversational AI for research, practice and policy
• Real-time Prediction of Urban Sound Propagation with Conditioned Normalizing Flows
• DiffKnock: Diffusion-based Knockoff Statistics for Neural Networks Inference
• Systematic review on tool breakage monitoring techniques in machining operations
• Advancements in Generative AI: A Comprehensive Review of GANs, GPT, Autoencoders, Diffusion Model, and Transformers
• Machine learning for combinatorial optimization: A methodological tour d’horizon
• Challenges in AI-driven Biomedical Multimodal Data Fusion and Analysis
• Integrating phenotyping and modelling approaches StomaGAN: improving image-based analysis of stomata through generative adversarial networks
• Deep learning and generative artificial intelligence in aging research and healthy longevity medicine
• Deep learning‐ and image processing‐based methods for automatic estimation of leaf herbivore damage
• ReshapeGAN: Object Reshaping by Providing A Single Reference Image
• Integration- and separation-aware adversarial model for cerebrovascular segmentation from TOF-MRA
• Generative AI Meets Wireless Sensing: Towards Wireless Foundation Model
• Trust Region Algorithm for Stochastic Minimax Problems with Decision-Dependent Distributions
• Anomaly Detection in Industrial Control Systems Based on Cross-Domain Representation Learning
• A Fine-Grained 3D Radio Map Construction Paradigm with Ultra-Low Sampling Rates by Large Generative Models
• Self-Evolving LLMs via Continual Instruction Tuning
• Synthetic Data Generation for Fraud Detection using GANs
• Online Clustering of Seafloor Imagery for Interpretation during Long-Term AUV Operations
• Adversarial Augmentation and Active Sampling for Robust Cyber Anomaly Detection
• Editing in Style: Uncovering the Local Semantics of GANs
• CoPE: Conditional image generation using Polynomial Expansions
• Deep learning in automated ultrasonic NDE -- developments, axioms and opportunities
• Extremal learning: extremizing the output of a neural network in regression problems
• AI Simulation by Digital Twins: Systematic Survey, Reference Framework, and Mapping to a Standardized Architecture
• Practical Attacks on Voice Spoofing Countermeasures
• SpeechForensics: Audio-Visual Speech Representation Learning for Face Forgery Detection
• Edge General Intelligence Through World Models and Agentic AI: Fundamentals, Solutions, and Challenges
• Score-Guided Generative Adversarial Networks
• Case Studies of Generative Machine Learning Models for Dynamical Systems
• MPC-MPNet: Model-Predictive Motion Planning Networks for Fast, Near-Optimal Planning under Kinodynamic Constraints
• PIF-Net: Ill-Posed Prior Guided Multispectral and Hyperspectral Image Fusion via Invertible Mamba and Fusion-Aware LoRA
• Evaluating Use of Generative Artificial Intelligence in Clinical Pathology Practice: Opportunities and the Way Forward
• Unsupervised Learning of Anomaly Detection from Contaminated Image Data using Simultaneous Encoder Training
• A scoping study of crime facilitated by the metaverse
• The Six Fronts of the Generative Adversarial Networks
• Physical Artificial Intelligence: The Concept Expansion of Next-Generation Artificial Intelligence
• A Survey and Taxonomy of Adversarial Neural Networks for Text-to-Image Synthesis
• A review of small object detection based on deep learning
• Agentic Satellite-Augmented Low-Altitude Economy and Terrestrial Networks: A Survey on Generative Approaches
• A Survey on Deep Learning for Neuroimaging-based Brain Disorder Analysis
• Designing GANs: A Likelihood Ratio Approach
• Manifold-preserved GANs
• RadioDiff-3D: A 3D×3D Radio Map Dataset and Generative Diffusion Based Benchmark for 6G Environment-Aware Communication
• GANs for Medical Image Analysis
• A Survey on Generative Adversarial Networks: Variants, Applications, and\n Training
• Voice command generation using Progressive Wavegans
• Protecting Intellectual Property of Generative Adversarial Networks from Ambiguity Attack
• Generative Adversarial Network for Handwritten Text
• SeismoGen: Seismic Waveform Synthesis Using Generative Adversarial Networks
• Physics-Informed Neural Networks For Semiconductor Film Deposition: A Review
• Minimizing the Pretraining Gap: Domain-aligned Text-Based Person Retrieval
• Spatiotemporal deep learning models for detection of rapid intensification in cyclones
• Generative network complex (GNC) for drug discovery
• Enhancing Underwater Images Using Deep Learning with Subjective Image Quality Integration
• Attention-Guided Multi-Scale Local Reconstruction for Point Clouds via Masked Autoencoder Self-Supervised Learning
• UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image Generation
• Improving GANs by leveraging the quantum noise from real hardware
• Neural Measures for learning distributions of Random PDEs
• Decentralized Pliable Index Coding For Federated Learning In Intelligent Transportation Systems
• DiffFit: Disentangled Garment Warping and Texture Refinement for Virtual Try-On
• Competitive Distillation: A Simple Learning Strategy for Improving Visual Classification
• Shape Constrained Network for Eye Segmentation in the Wild
• Real-time Burst Photo Selection Using a Light-Head Adversarial Network
• Embedding-reparameterization procedure for manifold-valued latent variables in generative models
• A Content Transformation Block For Image Style Transfer
• Relaxed Wasserstein with Applications to GANs
• Improved Intelligibility of Dysarthric Speech using Conditional Flow Matching
• Efficient Blockchain-based Steganography via Backcalculating Generative Adversarial Network
• Synthetic ALS-EEG Data Augmentation for ALS Diagnosis Using Conditional WGAN with Weight Clipping
• Semantic Preserving Generative Adversarial Models
• PRO: Projection Domain Synthesis for CT Imaging
• PolyGAN: High-Order Polynomial Generators
• Disentangling 3D from Large Vision-Language Models for Controlled Portrait Generation
• The Synthetic Mirror -- Synthetic Data at the Age of Agentic AI
• Deep learning approach for cardiovascular disease risk stratification and survival analysis on a Canadian cohort
• FREE: Fast and Robust Vision Language Models with Early Exits
• Latent Diffusion Model Based Denoising Receiver for 6G Semantic Communication: From Stochastic Differential Theory to Application
• Exploring Convolutional Neural Networks for Rice Grain Classification: An Explainable AI Approach
• Accelerated Gradient Methods Through Variable and Operator Splitting
• Stabilizing Generative Adversarial Networks: A Survey
• A Style-Aware Content Loss for Real-time HD Style Transfer
• Tarallo: Evading Behavioral Malware Detectors in the Problem Space
• Generative Adversarial Networks in Computer Vision: A Survey and Taxonomy
• Multi-Platform Methane Plume Detection via Model and Domain Adaptation
• Large Language Models for EEG: A Comprehensive Survey and Taxonomy
• Human Fall Detection using Transfer Learning-based 3D CNN
• Generative AI for Urban Design: A Stepwise Approach Integrating Human Expertise with Multimodal Diffusion Models
• MMGT: Motion Mask Guided Two-Stage Network for Co-Speech Gesture Video Generation
• When Autonomous Systems Meet Accuracy and Transferability through AI: A Survey
• Machine Learning for Naval Architecture, Ocean and Marine Engineering
• Adversarial Learning for Improved Onsets and Frames Music Transcription
• Mal-D2GAN: Double-Detector based GAN for Malware Generation
• GenPO: Generative Diffusion Models Meet On-Policy Reinforcement Learning
• SeaLion: Semantic Part-Aware Latent Point Diffusion Models for 3D Generation
• Learning to Repair Software Vulnerabilities with Generative Adversarial Networks
• Snore-GANs: Improving Automatic Snore Sound Classification with Synthesized Data
• Efficient GAN-Based Anomaly Detection
• Estimation with Uncertainty via Conditional Generative Adversarial Networks
• Generative Adversarial Reconstruction with Adaptive Thresholding for Obstructed Targets in Computational Microwave Imaging
• Deep learning-based synthetic-CT generation in radiotherapy and PET: a review
• Generative AI Literacy: Twelve Defining Competencies
• Peptide-based drug discovery through artificial intelligence: towards an autonomous design of therapeutic peptides
• An Efficient Stochastic First-Order Algorithm for Nonconvex--Strongly Concave Minimax Optimization beyond Lipschitz Smoothness
• 2D-3D Attention and Entropy for Pose Robust 2D Facial Recognition
• NIDA-CLIFGAN: Natural Infrastructure Damage Assessment through Efficient Classification Combining Contrastive Learning, Information Fusion and Generative Adversarial Networks
• DACAD: Domain Adaptation Contrastive Learning for Anomaly Detection in Multivariate Time Series
• Masked Subspace Clustering Methods
• AugMixCloak: A Defense against Membership Inference Attacks via Image Transformation
• Photovoltaic Defect Image Generator with Boundary Alignment Smoothing Constraint for Domain Shift Mitigation
• A Survey on Generative Diffusion Models
• A Character-based Diffusion Embedding Algorithm for Enhancing the Generation Quality of Generative Linguistic Steganographic Texts
• Generative Adversarial Networks for Financial Trading Strategies Fine-Tuning and Combination
• Low dose SPECT image denoising using a generative adversarial network
• A Survey of Interactive Generative Video
• State of the Art on Neural Rendering
• DesigNet: Learning to Draw Vector Graphics as Designers Do
• Mixture of Experts for Decentralized Generative AI and Reinforcement Learning in Wireless Networks: A Comprehensive Survey
• Particle-Guided Diffusion Models for Partial Differential Equations
• Generating Long-term Continuous Multi-type Generation Profiles
• UBLLIE: Unified Backlight and Low-Light Image Enhancement
• SDF-MAN: Semi-Supervised Disparity Fusion with Multi-Scale Adversarial Networks
• Graphusion: Latent Diffusion for Graph Generation
• Diffusion-based supervised learning of generative models for efficient sampling of multimodal distributions
• Can We Ignore Labels In Out of Distribution Detection?
• Reliable Confidence Intervals for Information Retrieval Evaluation Using Generative A.I.
• Noise Robustness and Experimental Demonstration of a Quantum Generative Adversarial Network for Continuous Distributions
• IMAGGarment: Fine-Grained Garment Generation for Controllable Fashion Design
• ArtistAuditor: Auditing Artist Style Pirate in Text-to-Image Generation Models
• Beyond geometric deformation: High-fidelity orthodontic profile synthesis via ControlNet-guided generative AI

Discussions

• Generative Adversarial Networks: An Overview [pdf] [hn, 90 points, 1 comments]

Related

• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
• Generative Adversarial Networks and Other Generative Models
• Generative Adversarial Networks (GANs): An Overview of Theoretical Model, Evaluation Metrics, and Recent Developments
• A Chronological Survey of Theoretical Advancements in Generative Adversarial Networks for Computer Vision
• Generative adversarial networks