Generative Adversarial Networks

Abstract

We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G. The training procedure for G is to maximize the probability of D making a mistake. This framework corresponds to a minimax two-player game. In the space of arbitrary functions G and D, a unique solution exists, with G recovering the training data distribution and D equal to 1/2 everywhere. In the case where G and D are defined by multilayer perceptrons, the entire system can be trained with backpropagation. There is no need for any Markov chains or unrolled approximate inference networks during either training or generation of samples. Experiments demonstrate the potential of the framework through qualitative and quantitative evaluation of the generated samples.

Cited by in corpus (222)

• Deep Neural Networks and Tabular Data: A Survey
• Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networks
• Mixed supervision for surface-defect detection: from weakly to fully supervised learning
• Data Augmentation Approaches in Natural Language Processing: A Survey
• Compute Trends Across Three Eras of Machine Learning
• AdvHat: Real-world adversarial attack on ArcFace Face ID system
• AI based Service Management for 6G Green Communications
• Combining EfficientNet and Vision Transformers for Video Deepfake Detection
• Speech Enhancement and Dereverberation with Diffusion-based Generative Models
• Weakly Supervised Adversarial Domain Adaptation for Semantic Segmentation in Urban Scenes
• A survey on Semi-, Self- and Unsupervised Learning for Image Classification
• Machine Learning for Stochastic Parameterization: Generative Adversarial Networks in the Lorenz '96 Model
• MD-GAN: Multi-Discriminator Generative Adversarial Networks for Distributed Datasets
• Applications of Deep Learning Techniques for Automated Multiple Sclerosis Detection Using Magnetic Resonance Imaging: A Review
• Pervasive AI for IoT applications: A Survey on Resource-efficient Distributed Artificial Intelligence
• Super-resolution-based Change Detection Network with Stacked Attention Module for Images with Different Resolutions
• Stagewise Unsupervised Domain Adaptation with Adversarial Self-Training for Road Segmentation of Remote Sensing Images
• Reconstructing Faces from fMRI Patterns using Deep Generative Neural Networks
• Deep learning based on Transformer architecture for power system short-term voltage stability assessment with class imbalance
• Mining gold from implicit models to improve likelihood-free inference
• From Handcrafted to Deep Features for Pedestrian Detection: A Survey
• Data-driven Machinery Fault Diagnosis: A Comprehensive Review
• Constrained crystals deep convolutional generative adversarial network for the inverse design of crystal structures
• The Born Supremacy: Quantum Advantage and Training of an Ising Born Machine
• Improving the Harmony of the Composite Image by Spatial-Separated Attention Module
• A Survey on Unsupervised Anomaly Detection Algorithms for Industrial Images
• The Dark Machines Anomaly Score Challenge: Benchmark Data and Model Independent Event Classification for the Large Hadron Collider
• Unsupervised Medical Image Translation Using Cycle-MedGAN
• AtlFast3: the next generation of fast simulation in ATLAS
• Fourier Imager Network (FIN): A deep neural network for hologram reconstruction with superior external generalization
• A survey on GANs for computer vision: Recent research, analysis and taxonomy
• Adaptive DropBlock Enhanced Generative Adversarial Networks for Hyperspectral Image Classification
• Deep generative models in inversion: a review and development of a new approach based on a variational autoencoder
• Ultra-High-Energy Cosmic Rays: The Intersection of the Cosmic and Energy Frontiers
• Towards quantum enhanced adversarial robustness in machine learning
• Machine learning-assisted design of material properties
• DSP: Dual Soft-Paste for Unsupervised Domain Adaptive Semantic Segmentation
• Face Deidentification with Generative Deep Neural Networks
• A review of Generative Adversarial Networks for Electronic Health Records: applications, evaluation measures and data sources
• Gradient-based deterministic inversion of geophysical data with Generative Adversarial Networks: is it feasible?
• Non-Intrusive Reduced-Order Modeling Using Uncertainty-Aware Deep Neural Networks and Proper Orthogonal Decomposition: Application to Flood Modeling
• Generative Networks for Precision Enthusiasts
• Incomplete Multi-view Clustering via Cross-view Relation Transfer
• GANmapper: geographical data translation
• An Overview of Human Activity Recognition Using Wearable Sensors: Healthcare and Artificial Intelligence
• Leveraging Generative AI Models for Synthetic Data Generation in Healthcare: Balancing Research and Privacy
• Time-Series Classification in Smart Manufacturing Systems: An Experimental Evaluation of State-of-the-Art Machine Learning Algorithms
• Fast Facial Landmark Detection and Applications: A Survey
• A Comprehensive Survey on Integrating Large Language Models with Knowledge-Based Methods
• Decentralized Deep Learning for Multi-Access Edge Computing: A Survey on Communication Efficiency and Trustworthiness
• Learning Functional Priors and Posteriors from Data and Physics
• PI-VAE: Physics-Informed Variational Auto-Encoder for stochastic differential equations
• Fast simulation of muons produced at the SHiP experiment using Generative Adversarial Networks
• Learning curves of generic features maps for realistic datasets with a teacher-student model
• Dialectometric analysis of language variation in Twitter
• End-to-End Video-To-Speech Synthesis using Generative Adversarial Networks
• Computer Vision with Deep Learning for Plant Phenotyping in Agriculture: A Survey
• Generative Modeling of Turbulence
• Spatiotemporal Tensor Completion for Improved Urban Traffic Imputation
• Behind the leaves -- Estimation of occluded grapevine berries with conditional generative adversarial networks
• FFR_FD: Effective and Fast Detection of DeepFakes Based on Feature Point Defects
• A rate of convergence of Physics Informed Neural Networks for the linear second order elliptic PDEs
• Quantum Machine Learning for Finance
• Measurements of Higgs Bosons Decaying to Bottom Quarks from Vector Boson Fusion Production with the ATLAS Experiment at $\sqrt{s}=$ 13 TeV
• L2LFlows: Generating High-Fidelity 3D Calorimeter Images
• Multichannel Synthetic Preictal EEG Signals to Enhance the Prediction of Epileptic Seizures
• Generative Artificial Intelligence Meets Synthetic Aperture Radar: A Survey
• Cross-Forgery Analysis of Vision Transformers and CNNs for Deepfake Image Detection
• GANs and alternative methods of synthetic noise generation for domain adaption of defect classification of Non-destructive ultrasonic testing
• Using Deep Learning to Localize Gravitational Wave Sources
• Automated Defect Recognition of Castings defects using Neural Networks
• Deep Learning for Simultaneous Inference of Hydraulic and Transport Properties
• SynthEval: A Framework for Detailed Utility and Privacy Evaluation of Tabular Synthetic Data
• Masked Transformer for image Anomaly Localization
• Resolution enhancement and realistic speckle recovery with generative adversarial modeling of micro-optical coherence tomography
• Design Space Exploration and Explanation via Conditional Variational Autoencoders in Meta-model-based Conceptual Design of Pedestrian Bridges
• CaloScore v2: Single-shot Calorimeter Shower Simulation with Diffusion Models
• SymmetryGAN: Symmetry Discovery with Deep Learning
• Feature-aware conditional GAN for category text generation
• Systematic Review on Learning-based Spectral CT
• An AI-Assisted Design Method for Topology Optimization Without Pre-Optimized Training Data
• Fine-grained Solar Flare Forecasting Based on the Hybrid Convolutional Neural Networks
• The Evolution of Reinforcement Learning in Quantitative Finance: A Survey
• Hybrid quantum cycle generative adversarial network for small molecule generation
• An ordinal CNN approach for the assessment of neurological damage in Parkinson's disease patients
• Capitalization and Punctuation Restoration: a Survey
• MTS-DVGAN: Anomaly Detection in Cyber-Physical Systems using a Dual Variational Generative Adversarial Network
• A Study of the Generalizability of Self-Supervised Representations
• Thermal experiments for fractured rock characterization: theoretical analysis and inverse modeling
• Deep Generative Models for Detector Signature Simulation: A Taxonomic Review
• Human Activity Recognition with Low-Resolution Infrared Array Sensor Using Semi-supervised Cross-domain Neural Networks for Indoor Environment
• Neural Canonical Transformation with Symplectic Flows
• SoftHebb: Bayesian Inference in Unsupervised Hebbian Soft Winner-Take-All Networks
• Low-Resource Text Classification using Domain-Adversarial Learning
• EFTofLSS meets simulation-based inference: ${\sigma }_8$ from biased tracers
• EDMP: Ensemble-of-costs-guided Diffusion for Motion Planning
• CSC-Unet: A Novel Convolutional Sparse Coding Strategy Based Neural Network for Semantic Segmentation
• Laplace HypoPINN: Physics-Informed Neural Network for hypocenter localization and its predictive uncertainty
• Tight and Efficient Gradient Bounds for Parameterized Quantum Circuits
• Background Adaptive Faster R-CNN for Semi-Supervised Convolutional Object Detection of Threats in X-Ray Images
• RCRN: Real-world Character Image Restoration Network via Skeleton Extraction
• Can AI be enabled to dynamical downscaling? A Latent Diffusion Model to mimic km-scale COSMO5.0\_CLM9 simulations
• Optimal Physical Preprocessing for Example-Based Super-Resolution
• High-dimensional and Permutation Invariant Anomaly Detection
• Deep Learning for Pancreas Segmentation: a Systematic Review
• Generative Adversarial Networks Applied to Synthetic Financial Scenarios Generation
• Precursor-of-Anomaly Detection for Irregular Time Series
• Uncertainty-Guided Mixup for Semi-Supervised Domain Adaptation without Source Data
• An EEG-Based Multi-Modal Emotion Database with Both Posed and Authentic Facial Actions for Emotion Analysis
• Materials Discovery with Extreme Properties via Reinforcement Learning-Guided Combinatorial Chemistry
• Latent Denoising Diffusion GAN: Faster sampling, Higher image quality
• Causal datasheet: An approximate guide to practically assess Bayesian networks in the real world
• Effective LHC measurements with matrix elements and machine learning
• Particle-based Fast Jet Simulation at the LHC with Variational Autoencoders
• DeTiME: Diffusion-Enhanced Topic Modeling using Encoder-decoder based LLM
• Generalised gravitational burst generation with Generative Adversarial Networks
• A generative model for molecule generation based on chemical reaction trees
• Few-Shot Speaker Identification Using Lightweight Prototypical Network with Feature Grouping and Interaction
• Robust deep learning for eye fundus images: Bridging real and synthetic data for enhancing generalization
• Event Detection in Micro-PMU Data: A Generative Adversarial Network Scoring Method
• (ASNA) An Attention-based Siamese-Difference Neural Network with Surrogate Ranking Loss function for Perceptual Image Quality Assessment
• Compressing PDF sets using generative adversarial networks
• BCGGAN: Ballistocardiogram artifact removal in simultaneous EEG-fMRI using generative adversarial network
• Generation of ice states through deep reinforcement learning
• Super-resolving Herschel imaging: a proof of concept using Deep Neural Networks
• Machine-Learning-Assisted Photonic Device Development: A Multiscale Approach from Theory to Characterization
• OmniLRS: A Photorealistic Simulator for Lunar Robotics
• Introducing Conceptual Geological Information into Bayesian Tomographic Imaging
• Solving smooth min-min and min-max problems by mixed oracle algorithms
• AI-assisted super-resolution cosmological simulations III: Time evolution
• Zeroth-Order Algorithms for Smooth Saddle-Point Problems
• Continual Contrastive Learning for Image Classification
• A Comparison of Adversarial Learning Techniques for Malware Detection
• Improving Neural Silent Speech Interface Models by Adversarial Training
• CNN-based event classification for alpha-decay events in nuclear emulsion
• Image Comes Dancing with Collaborative Parsing-Flow Video Synthesis
• MemoVis: A GenAI-Powered Tool for Creating Companion Reference Images for 3D Design Feedback
• Towards a robust and reliable deep learning approach for detection of compact binary mergers in gravitational wave data
• Explainable Representation Learning of Small Quantum States
• Mixed X-Ray Image Separation for Artworks with Concealed Designs
• Normalizing flows as an enhanced sampling method for atomistic supercooled liquids
• Emulating Sunyaev-Zeldovich Images of Galaxy Clusters using Auto-Encoders
• Transport away your problems: Calibrating stochastic simulations with optimal transport
• Generating Multi-scale Maps from Remote Sensing Images via Series Generative Adversarial Networks
• Utilizing variational autoencoders in the Bayesian inverse problem of photoacoustic tomography
• Testing the robustness of simulation-based gravitational-wave population inference
• Discriminative Hamiltonian Variational Autoencoder for Accurate Tumor Segmentation in Data-Scarce Regimes
• Fast and computationally efficient generative adversarial network algorithm for unmanned aerial vehicle-based network coverage optimization
• A Comprehensive Study on Medical Image Segmentation using Deep Neural Networks
• F3-Pruning: A Training-Free and Generalized Pruning Strategy towards Faster and Finer Text-to-Video Synthesis
• Foreground Removal of CO Intensity Mapping Using Deep Learning
• Probabilistic forecasting for geosteering in fluvial successions using a generative adversarial network
• A tomographic spherical mass map emulator of the KiDS-1000 survey using conditional generative adversarial networks
• Physics Validation of Novel Convolutional 2D Architectures for Speeding Up High Energy Physics Simulations
• Learning Social Navigation from Demonstrations with Conditional Neural Processes
• Handloom Design Generation Using Generative Networks
• Using a Conditional Generative Adversarial Network to Control the Statistical Characteristics of Generated Images for IACT Data Analysis
• Scalable Self-Supervised Representation Learning from Spatiotemporal Motion Trajectories for Multimodal Computer Vision
• A Lightweight Machine Learning Pipeline for LiDAR-simulation
• Hypernuclear event detection in the nuclear emulsion with Monte Carlo simulation and machine learning
• Reachability Embeddings: Scalable Self-Supervised Representation Learning from Mobility Trajectories for Multimodal Geospatial Computer Vision
• Sensing Anomalies as Potential Hazards: Datasets and Benchmarks
• Site-Specific Ground Motion Generative Model for Crustal Earthquakes in Japan Based on Generative Adversarial Networks
• Uncertainty-Autoencoder-Based Privacy and Utility Preserving Data Type Conscious Transformation
• RLSS: A Deep Reinforcement Learning Algorithm for Sequential Scene Generation
• The Three Hundred Project: Mapping The Matter Distribution in Galaxy Clusters Via Deep Learning from Multiview Simulated Observations
• MBAPose: Mask and Bounding-Box Aware Pose Estimation of Surgical Instruments with Photorealistic Domain Randomization
• BanglaBait: Semi-Supervised Adversarial Approach for Clickbait Detection on Bangla Clickbait Dataset
• RGB-D-Fusion: Image Conditioned Depth Diffusion of Humanoid Subjects
• Zero-shot generation of synthetic neurosurgical data with large language models
• Photon detection probability prediction using one-dimensional generative neural network
• On the average-case complexity of learning output distributions of quantum circuits
• Attention-based CT Scan Interpolation for Lesion Segmentation of Colorectal Liver Metastases
• Exploration of Convolutional Neural Network Architectures for Large Region Map Automation
• Jamdani Motif Generation using Conditional GAN
• A Simple and Robust Framework for Cross-Modality Medical Image Segmentation applied to Vision Transformers
• Parameterized Convex Universal Approximators for Decision-Making Problems
• DVGAN: Stabilize Wasserstein GAN training for time-domain Gravitational Wave physics
• Training-Free, Identity-Preserving Image Editing for Fashion Pose Alignment and Normalization
• Generative modelling for mass-mapping with fast uncertainty quantification
• Learning in Quantum Common-Interest Games and the Separability Problem
• The use of adversaries for optimal neural network training
• 3D-StyleGAN: A Style-Based Generative Adversarial Network for Generative Modeling of Three-Dimensional Medical Images
• Variational Prefix Tuning for Diverse and Accurate Code Summarization Using Pre-trained Language Models
• Parameter Efficient Diverse Paraphrase Generation Using Sequence-Level Knowledge Distillation
• DeepDiffusion: Unsupervised Learning of Retrieval-adapted Representations via Diffusion-based Ranking on Latent Feature Manifold
• Conditional Distribution Modelling for Few-Shot Image Synthesis with Diffusion Models
• GAN-Based LiDAR Intensity Simulation
• Deep Learning for Improved Polyp Detection from Synthetic Narrow-Band Imaging
• Assessing Deep Neural Networks as Probability Estimators
• Inference and De-Noising of Non-Gaussian Particle Distribution Functions: A Generative Modeling Approach
• Novel End-to-End Production-Ready Machine Learning Flow for Nanolithography Modeling and Correction
• Reconstructing the mid-infrared spectra of galaxies using ultraviolet to submillimeter photometry and Deep Generative Networks
• Learning to discover: expressive Gaussian mixture models for multi-dimensional simulation and parameter inference in the physical sciences
• A Systematic Review on the Generative AI Applications in Human Medical Genomics
• EGAIN: Extended GAn INversion
• AdvNF: Reducing Mode Collapse in Conditional Normalising Flows using Adversarial Learning
• The future of urban models in the Big Data and AI era: a bibliometric analysis (2000-2019)
• DriftGAN: Using historical data for Unsupervised Recurring Drift Detection
• Synthetic Data Augmentation for Enhancing Harmful Algal Bloom Detection with Machine Learning
• Statistically Optimal Generative Modeling with Maximum Deviation from the Empirical Distribution
• Improving Insurance Catastrophic Data with Resampling and GAN Methods
• Slice it up: Unmasking User Identities in Smartwatch Health Data
• Predicting Real-time Scientific Experiments Using Transformer models and Reinforcement Learning
• Diffeomorphic Transformations for Time Series Analysis: An Efficient Approach to Nonlinear Warping
• Enhancing Stability in Training Conditional Generative Adversarial Networks via Selective Data Matching
• Generative Plant Growth Simulation from Sequence-Informed Environmental Conditions
• Synthetic Data Generation for Classifying Electrophysiological and Morpho-Electrophysiological Neurons from Mouse Visual Cortex
• Disentangled (Un)Controllable Features
• Artificial ASMR: A Cyber-Psychological Approach
• Towards quantum machine learning for assessing the resilience of post-quantum cryptography
• TabularQGAN: A quantum generative model for tabular data synthesis
• Optimal Analysis of Method with Batching for Monotone Stochastic Finite-Sum Variational Inequalities
• Efficient Modelling Across Time of Human Actions and Interactions
• Semantically Rich Local Dataset Generation for Explainable AI in Genomics
• On Inductive Biases for Machine Learning in Data Constrained Settings
• Generative Surrogates for Fast Simulation: TPC Case
• CAMEO: Curiosity Augmented Metropolis for Exploratory Optimal Policies
• AMLNet: Adversarial Mutual Learning Neural Network for Non-AutoRegressive Multi-Horizon Time Series Forecasting
• Adversarial Jamming for Autoencoder Distribution Matching
• IGN : Implicit Generative Networks
• Ultra-Fast Generation of Air Shower Images for Imaging Air Cherenkov Telescopes using Generative Adversarial Networks