Progressive Growing of GANs for Improved Quality, Stability, and Variation

Abstract

We describe a new training methodology for generative adversarial networks. The key idea is to grow both the generator and discriminator progressively: starting from a low resolution, we add new layers that model increasingly fine details as training progresses. This both speeds the training up and greatly stabilizes it, allowing us to produce images of unprecedented quality, e.g., CelebA images at 1024^2. We also propose a simple way to increase the variation in generated images, and achieve a record inception score of 8.80 in unsupervised CIFAR10. Additionally, we describe several implementation details that are important for discouraging unhealthy competition between the generator and discriminator. Finally, we suggest a new metric for evaluating GAN results, both in terms of image quality and variation. As an additional contribution, we construct a higher-quality version of the CelebA dataset.

Final ICLR 2018 version

References in corpus (21)

• Auto-Encoding Variational Bayes
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• WaveNet: A Generative Model for Raw Audio
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• Conditional Image Synthesis With Auxiliary Classifier GANs
• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
• Improved Training of Wasserstein GANs
• Improved Techniques for Training GANs
• Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks
• BEGAN: Boundary Equilibrium Generative Adversarial Networks
• Adversarially Learned Inference
• Layer Normalization
• Unrolled Generative Adversarial Networks
• High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
• L2 Regularization versus Batch and Weight Normalization
• LR-GAN: Layered Recursive Generative Adversarial Networks for Image Generation
• Least Squares Generative Adversarial Networks
• Do GANs actually learn the distribution? An empirical study
• Stacked Generative Adversarial Networks
• Megapixel Size Image Creation using Generative Adversarial Networks
• Class-Splitting Generative Adversarial Networks

Cited by in corpus (471)

• Generative Adversarial Network in Medical Imaging: A Review
• CovidGAN: Data Augmentation Using Auxiliary Classifier GAN for Improved Covid-19 Detection
• Deep Learning Methods for Reynolds-Averaged Navier-Stokes Simulations of Airfoil Flows
• Data Synthesis based on Generative Adversarial Networks
• AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control
• GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks
• A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music
• Generative Adversarial Networks in Computer Vision: A Survey and Taxonomy
• TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up
• Image Inpainting via Generative Multi-column Convolutional Neural Networks
• Syntax-Directed Variational Autoencoder for Structured Data
• An empirical study on evaluation metrics of generative adversarial networks
• A Note on the Inception Score
• Learning to Predict the Cosmological Structure Formation
• Generative Image Inpainting with Contextual Attention
• Synthesizing Tabular Data using Generative Adversarial Networks
• FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping
• Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis
• Adversarial Text-to-Image Synthesis: A Review
• A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions
• Using GANs for Sharing Networked Time Series Data: Challenges, Initial Promise, and Open Questions
• Natural Language Processing Advancements By Deep Learning: A Survey
• Optimizing the Latent Space of Generative Networks
• NetGAN: Generating Graphs via Random Walks
• Music Source Separation in the Waveform Domain
• Neural Voice Cloning with a Few Samples
• Reconstructing Faces from fMRI Patterns using Deep Generative Neural Networks
• Unsupervised Domain Adaptation through Self-Supervision
• An Introduction to Image Synthesis with Generative Adversarial Nets
• Fighting Deepfake by Exposing the Convolutional Traces on Images
• VideoGPT: Video Generation using VQ-VAE and Transformers
• Classification Accuracy Score for Conditional Generative Models
• Selective Synthetic Augmentation with HistoGAN for Improved Histopathology Image Classification
• A deep learning framework for quality assessment and restoration in video endoscopy
• Improved Techniques for Training Score-Based Generative Models
• Advances in Deep Concealed Scene Understanding
• SPG-Net: Segmentation Prediction and Guidance Network for Image Inpainting
• PEPSI++: Fast and Lightweight Network for Image Inpainting
• Fighting deepfakes by detecting GAN DCT anomalies
• Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal GAN
• MelNet: A Generative Model for Audio in the Frequency Domain
• Deep unsupervised learning of turbulence for inflow generation at various Reynolds numbers
• Enhanced Balancing GAN: Minority-class Image Generation
• CariGANs: Unpaired Photo-to-Caricature Translation
• Generative Models for Automatic Chemical Design
• StarGAN v2: Diverse Image Synthesis for Multiple Domains
• Reversing the Irreversible: A Survey on Inverse Biometrics
• Fashion-Gen: The Generative Fashion Dataset and Challenge
• Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations
• MaskGAN: Towards Diverse and Interactive Facial Image Manipulation
• Learning Data Augmentation for Brain Tumor Segmentation with Coarse-to-Fine Generative Adversarial Networks
• One Detector to Rule Them All: Towards a General Deepfake Attack Detection Framework
• On Identifiability in Transformers
• Painting with baryons: augmenting N-body simulations with gas using deep generative models
• Assessment of Generative Adversarial Networks Model for Synthetic Optical Coherence Tomography Images of Retinal Disorders
• CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesis
• A review of Generative Adversarial Networks for Electronic Health Records: applications, evaluation measures and data sources
• On Self Modulation for Generative Adversarial Networks
• Wavelet-Packets for Deepfake Image Analysis and Detection
• Collaborative Learning for Faster StyleGAN Embedding
• A Good Image Generator Is What You Need for High-Resolution Video Synthesis
• A Multi-Pass GAN for Fluid Flow Super-Resolution
• A Systematic Survey of Regularization and Normalization in GANs
• Demucs: Deep Extractor for Music Sources with extra unlabeled data remixed
• Detecting outliers in astronomical images with deep generative networks
• Multi-scale Convolutional Neural Networks for Inverse Problems
• On Leveraging Pretrained GANs for Generation with Limited Data
• Efficient texture-aware multi-GAN for image inpainting
• Detecting GAN generated Fake Images using Co-occurrence Matrices
• Digital rock reconstruction with user-defined properties using conditional generative adversarial networks
• DeepRhythm: Exposing DeepFakes with Attentional Visual Heartbeat Rhythms
• Photographic Text-to-Image Synthesis with a Hierarchically-nested Adversarial Network
• Image-driven discriminative and generative machine learning algorithms for establishing microstructure-processing relationships
• Facial-Sketch Synthesis: A New Challenge
• Evaluation Metrics for Conditional Image Generation
• Decision and Feature Level Fusion of Deep Features Extracted from Public COVID-19 Data-sets
• Yes, we GAN: Applying Adversarial Techniques for Autonomous Driving
• Activation Maximization Generative Adversarial Nets
• medigan: a Python library of pretrained generative models for medical image synthesis
• MeshGAN: Non-linear 3D Morphable Models of Faces
• Large image datasets: A pyrrhic win for computer vision?
• Generative Language Modeling for Automated Theorem Proving
• Convergence Problems with Generative Adversarial Networks (GANs)
• Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues
• MelanoGANs: High Resolution Skin Lesion Synthesis with GANs
• Generative adversarial interpolative autoencoding: adversarial training on latent space interpolations encourage convex latent distributions
• PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization
• One Label, One Billion Faces: Usage and Consistency of Racial Categories in Computer Vision
• Deepfake Detection Scheme Based on Vision Transformer and Distillation
• BourGAN: Generative Networks with Metric Embeddings
• Patch-based Progressive 3D Point Set Upsampling
• Generating valid Euclidean distance matrices
• SC-FEGAN: Face Editing Generative Adversarial Network with User's Sketch and Color
• Learning Continuous Image Representation with Local Implicit Image Function
• 3D Human Pose Estimation in the Wild by Adversarial Learning
• High Perceptual Quality Image Denoising with a Posterior Sampling CGAN
• Safer Classification by Synthesis
• FakeSpotter: A Simple yet Robust Baseline for Spotting AI-Synthesized Fake Faces
• Autoregressive Quantile Networks for Generative Modeling
• Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting
• Pedestrian Attribute Recognition: A Survey
• PConv: Simple yet Effective Convolutional Layer for Generative Adversarial Network
• Simple yet Effective Way for Improving the Performance of GAN
• On Training Sample Memorization: Lessons from Benchmarking Generative Modeling with a Large-scale Competition
• One-shot Face Reenactment
• Large-Scale Generative Data-Free Distillation
• Distinguishing Natural and Computer-Generated Images using Multi-Colorspace fused EfficientNet
• From EMBER to FIRE: predicting high resolution baryon fields from dark matter simulations with Deep Learning
• Perceptual Image Anomaly Detection
• Fundus2Angio: A Conditional GAN Architecture for Generating Fluorescein Angiography Images from Retinal Fundus Photography
• Complement Face Forensic Detection and Localization with FacialLandmarks
• Predicting Video with VQVAE
• GAN-QP: A Novel GAN Framework without Gradient Vanishing and Lipschitz Constraint
• Speech-Driven Facial Reenactment Using Conditional Generative Adversarial Networks
• Significance-aware Information Bottleneck for Domain Adaptive Semantic Segmentation
• Unsupervised Doodling and Painting with Improved SPIRAL
• Global Convergence to the Equilibrium of GANs using Variational Inequalities
• Greedy Layerwise Learning Can Scale to ImageNet
• FaceShop: Deep Sketch-based Face Image Editing
• Cross-domain Correspondence Learning for Exemplar-based Image Translation
• Foreground-aware Image Inpainting
• Mixing Real and Synthetic Data to Enhance Neural Network Training -- A Review of Current Approaches
• StyleGAN2 Distillation for Feed-forward Image Manipulation
• Semi-supervised Image Attribute Editing using Generative Adversarial Networks
• Skill Rating for Generative Models
• Image Inpainting using Block-wise Procedural Training with Annealed Adversarial Counterpart
• Physics Informed Deep Learning for Transport in Porous Media. Buckley Leverett Problem
• Generative Adversarial Networks: A Survey Towards Private and Secure Applications
• Forbidden knowledge in machine learning -- Reflections on the limits of research and publication
• Towards generative adversarial networks as a new paradigm for radiology education
• Mode Collapse and Regularity of Optimal Transportation Maps
• DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation
• Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches
• Topological Learning for Brain Networks
• Text-to-Face Generation with StyleGAN2
• QGAN: Quantized Generative Adversarial Networks
• Pro-UIGAN: Progressive Face Hallucination from Occluded Thumbnails
• A unified framework for 21cm tomography sample generation and parameter inference with Progressively Growing GANs
• GANsfer Learning: Combining labelled and unlabelled data for GAN based data augmentation
• Image Inpainting for Irregular Holes Using Partial Convolutions
• Using Scene Graph Context to Improve Image Generation
• Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning
• Unsupervised Training for 3D Morphable Model Regression
• Wasserstein-2 Generative Networks
• Unsupervised Two-Stage Anomaly Detection
• Generative Latent Flow
• Performance of GAN-based augmentation for deep learning COVID-19 image classification
• Style Generator Inversion for Image Enhancement and Animation
• Robust Single-Image Super-Resolution via CNNs and TV-TV Minimization
• Unsupervised Person Image Synthesis in Arbitrary Poses
• Unsupervised Person Image Generation with Semantic Parsing Transformation
• How Well Do WGANs Estimate the Wasserstein Metric?
• Metropolis-Hastings Generative Adversarial Networks
• A Provably Convergent Scheme for Compressive Sensing under Random Generative Priors
• InMoDeGAN: Interpretable Motion Decomposition Generative Adversarial Network for Video Generation
• A New Multi-vehicle Trajectory Generator to Simulate Vehicle-to-Vehicle Encounters
• The Riemannian Geometry of Deep Generative Models
• O-GAN: Extremely Concise Approach for Auto-Encoding Generative Adversarial Networks
• A Generative Adversarial Network for AI-Aided Chair Design
• A Convolutional LSTM based Residual Network for Deepfake Video Detection
• Synthesizing lesions using contextual GANs improves breast cancer classification on mammograms
• An error analysis of generative adversarial networks for learning distributions
• Map completion from partial observation using the global structure of multiple environmental maps
• Fair Generative Modeling via Weak Supervision
• Generative Adversarial Networks (GANs): What it can generate and What it cannot?
• Twin-GAN -- Unpaired Cross-Domain Image Translation with Weight-Sharing GANs
• VQVC+: One-Shot Voice Conversion by Vector Quantization and U-Net architecture
• Learning stochastic object models from medical imaging measurements by use of advanced ambient generative adversarial networks
• Top-k Training of GANs: Improving GAN Performance by Throwing Away Bad Samples
• KaoKore: A Pre-modern Japanese Art Facial Expression Dataset
• Progressive Semantic-Aware Style Transformation for Blind Face Restoration
• Curriculum learning for language modeling
• GramGAN: Deep 3D Texture Synthesis From 2D Exemplars
• Exposing GAN-synthesized Faces Using Landmark Locations
• Effect of The Latent Structure on Clustering with GANs
• Improving Video Generation for Multi-functional Applications
• UGAN: Untraceable GAN for Multi-Domain Face Translation
• AnonymousNet: Natural Face De-Identification with Measurable Privacy
• End-to-End Chinese Landscape Painting Creation Using Generative Adversarial Networks
• ACE: Adapting to Changing Environments for Semantic Segmentation
• Generative Models as Distributions of Functions
• Multi-Domain Translation by Learning Uncoupled Autoencoders
• TraDE: Transformers for Density Estimation
• Example-Guided Style Consistent Image Synthesis from Semantic Labeling
• AdversarialNAS: Adversarial Neural Architecture Search for GANs
• Disentangling Factors of Variation by Mixing Them
• SAG-GAN: Semi-Supervised Attention-Guided GANs for Data Augmentation on Medical Images
• Semi-parametric Image Inpainting
• SGD Learns One-Layer Networks in WGANs
• An Embarrassingly Simple Approach for Knowledge Distillation
• 3D Brain and Heart Volume Generative Models: A Survey
• Image Morphing with Perceptual Constraints and STN Alignment
• Generative Convolution Layer for Image Generation
• Image Comes Dancing with Collaborative Parsing-Flow Video Synthesis
• MISO: Mutual Information Loss with Stochastic Style Representations for Multimodal Image-to-Image Translation
• Unsupervised Image to Sequence Translation with Canvas-Drawer Networks
• Two-phase Hair Image Synthesis by Self-Enhancing Generative Model
• Exploiting Human Social Cognition for the Detection of Fake and Fraudulent Faces via Memory Networks
• Studying the potential of Graphcore IPUs for applications in Particle Physics
• FaR-GAN for One-Shot Face Reenactment
• Early-Phase Performance-Driven Design using Generative Models
• Why Build an Assistant in Minecraft?
• MulGAN: Facial Attribute Editing by Exemplar
• Training Generative Adversarial Networks Via Turing Test
• Image Inpainting Using Wasserstein Generative Adversarial Imputation Network
• Towards High-Fidelity 3D Face Reconstruction from In-the-Wild Images Using Graph Convolutional Networks
• Texture Mixer: A Network for Controllable Synthesis and Interpolation of Texture
• Cascade EF-GAN: Progressive Facial Expression Editing with Local Focuses
• Improved Training with Curriculum GANs
• Iconify: Converting Photographs into Icons
• Context-Aware Mutual Learning for Blind Image Inpainting and Beyond
• Generating fMRI volumes from T1-weighted volumes using 3D CycleGAN
• COCO-GAN: Generation by Parts via Conditional Coordinating
• On the generalization of GAN image forensics
• Detection, Attribution and Localization of GAN Generated Images
• Road Damage Detection and Classification with Detectron2 and Faster R-CNN
• Learning to Detect Fake Face Images in the Wild
• FakeTagger: Robust Safeguards against DeepFake Dissemination via Provenance Tracking
• Fine-grained Synthesis of Unrestricted Adversarial Examples
• Controllable and Progressive Image Extrapolation
• A Contrastive Learning Approach for Training Variational Autoencoder Priors
• Mask-Guided Portrait Editing with Conditional GANs
• One-Shot GAN Generated Fake Face Detection
• Discriminator Contrastive Divergence: Semi-Amortized Generative Modeling by Exploring Energy of the Discriminator
• Triple Generative Adversarial Networks
• Neural Density Estimation and Likelihood-free Inference
• Diffusion Priors In Variational Autoencoders
• Dynamics of Fourier Modes in Torus Generative Adversarial Networks
• Generating Synthetic Multispectral Satellite Imagery from Sentinel-2
• Face Translation between Images and Videos using Identity-aware CycleGAN
• Generative Adversarial Networks with Physical Evaluators for Spray Simulation of Pintle Injector
• One-Shot Identity-Preserving Portrait Reenactment
• Group Equivariant Generative Adversarial Networks
• Cross-modal Deep Face Normals with Deactivable Skip Connections
• Data Augmentation for Skin Lesion using Self-Attention based Progressive Generative Adversarial Network
• Optical Illusions Images Dataset
• Improved Techniques for GAN based Facial Inpainting
• Learning Spatial Pyramid Attentive Pooling in Image Synthesis and Image-to-Image Translation
• High Quality Facial Surface and Texture Synthesis via Generative Adversarial Networks
• Understanding the Effectiveness of Lipschitz-Continuity in Generative Adversarial Nets
• DeepMasterPrints: Generating MasterPrints for Dictionary Attacks via Latent Variable Evolution
• RankGAN: A Maximum Margin Ranking GAN for Generating Faces
• M2FPA: A Multi-Yaw Multi-Pitch High-Quality Database and Benchmark for Facial Pose Analysis
• Image Synthesis From Reconfigurable Layout and Style
• Accurate generation of stochastic dynamics based on multi-model Generative Adversarial Networks
• Mosaicking to Distill: Knowledge Distillation from Out-of-Domain Data
• Divide-and-Conquer Adversarial Learning for High-Resolution Image and Video Enhancement
• Recapture as You Want
• Instance-level Facial Attributes Transfer with Geometry-Aware Flow
• Faces à la Carte: Text-to-Face Generation via Attribute Disentanglement
• On Deep Speech Packet Loss Concealment: A Mini-Survey
• DUAL-GLOW: Conditional Flow-Based Generative Model for Modality Transfer
• Analysis of Manual and Automated Skin Tone Assignments for Face Recognition Applications
• Robust Attentive Deep Neural Network for Exposing GAN-generated Faces
• MineGAN: effective knowledge transfer from GANs to target domains with few images
• The Myths of Our Time: Fake News
• Markov-Chain Monte Carlo Approximation of the Ideal Observer using Generative Adversarial Networks
• GANs beyond divergence minimization
• On Relativistic $f$-Divergences
• Deep Learning of Preconditioners for Conjugate Gradient Solvers in Urban Water Related Problems
• Enjoy Your Editing: Controllable GANs for Image Editing via Latent Space Navigation
• Tensorizing Generative Adversarial Nets
• Multi-objects Generation with Amortized Structural Regularization
• Constrained Generative Adversarial Network Ensembles for Sharable Synthetic Data Generation
• Transfer feature generating networks with semantic classes structure for zero-shot learning
• SDIT: Scalable and Diverse Cross-domain Image Translation
• Decentralized Attribution of Generative Models
• Spacetime as the optimal generative network of quantum states: a roadmap to QM=GR?
• Unconstrained Facial Expression Transfer using Style-based Generator
• FakePolisher: Making DeepFakes More Detection-Evasive by Shallow Reconstruction
• Intelligent Generation of Graphical Game Assets: A Conceptual Framework and Systematic Review of the State of the Art
• FReeNet: Multi-Identity Face Reenactment
• Synthesizing facial photometries and corresponding geometries using generative adversarial networks
• Unsupervised Sketch-to-Photo Synthesis
• Reconstruction of 3D Porous Media From 2D Slices
• FReTAL: Generalizing Deepfake Detection using Knowledge Distillation and Representation Learning
• Scalable Balanced Training of Conditional Generative Adversarial Neural Networks on Image Data
• Feeding the zombies: Synthesizing brain volumes using a 3D progressive growing GAN
• An Acceleration Framework for High Resolution Image Synthesis
• CRAFT: Complementary Recommendations Using Adversarial Feature Transformer
• Biphasic Learning of GANs for High-Resolution Image-to-Image Translation
• Attentive Normalization for Conditional Image Generation
• Progressive Fashion Attribute Extraction
• Diverse Semantic Image Synthesis via Probability Distribution Modeling
• TuiGAN: Learning Versatile Image-to-Image Translation with Two Unpaired Images
• Label-Noise Robust Multi-Domain Image-to-Image Translation
• Unsupervised 3D Shape Learning from Image Collections in the Wild
• Spatial PixelCNN: Generating Images from Patches
• Deep Structured Generative Models
• Learning to Synthesize Fashion Textures
• Bi-level Feature Alignment for Versatile Image Translation and Manipulation
• Conditional Image Generation and Manipulation for User-Specified Content
• Optimization of hyperparameters for SMS reconstruction
• toon2real: Translating Cartoon Images to Realistic Images
• Blind Image Deconvolution using Pretrained Generative Priors
• FaceController: Controllable Attribute Editing for Face in the Wild
• Unsupervised multi-modal Styled Content Generation
• Selective Synthetic Augmentation with Quality Assurance
• For a semiotic AI: Bridging computer vision and visual semiotics for computational observation of large scale facial image archives
• Approximating Human Judgment of Generated Image Quality
• Fairness in generative modeling
• LPaintB: Learning to Paint from Self-Supervision
• Unpaired Multi-Domain Image Generation via Regularized Conditional GANs
• Artist Style Transfer Via Quadratic Potential
• Learning Oracle Attention for High-fidelity Face Completion
• 3D-StyleGAN: A Style-Based Generative Adversarial Network for Generative Modeling of Three-Dimensional Medical Images
• Tensorized Transformer for Dynamical Systems Modeling
• Curriculum By Smoothing
• GIQA: Generated Image Quality Assessment
• Example-Guided Image Synthesis across Arbitrary Scenes using Masked Spatial-Channel Attention and Self-Supervision
• SurfelGAN: Synthesizing Realistic Sensor Data for Autonomous Driving
• Convolutional Neural Network Interpretability with General Pattern Theory
• Taking Control of Intra-class Variation in Conditional GANs Under Weak Supervision
• Adversarial Attacks on Co-Occurrence Features for GAN Detection
• SkrGAN: Sketching-rendering Unconditional Generative Adversarial Networks for Medical Image Synthesis
• Mode matching in GANs through latent space learning and inversion
• VQ-DRAW: A Sequential Discrete VAE
• Continuous Graph Flow
• Image2GIF: Generating Cinemagraphs using Recurrent Deep Q-Networks
• ScarGAN: Chained Generative Adversarial Networks to Simulate Pathological Tissue on Cardiovascular MR Scans
• Holdout-Based Fidelity and Privacy Assessment of Mixed-Type Synthetic Data
• EPSR: Edge Profile Super resolution
• GAN-Based Facial Attractiveness Enhancement
• Adversarial Pixel-Level Generation of Semantic Images
• Classify and Generate: Using Classification Latent Space Representations for Image Generations
• Unsupervised Domain Adaptation using Generative Models and Self-ensembling
• How Old Are You? Face Age Translation with Identity Preservation Using GANs
• Sparsely Grouped Multi-task Generative Adversarial Networks for Facial Attribute Manipulation
• Reciprocal Adversarial Learning via Characteristic Functions
• GAN Memory with No Forgetting
• Assessing Dialogue Systems with Distribution Distances
• UVA: A Universal Variational Framework for Continuous Age Analysis
• An Efficient Explorative Sampling Considering the Generative Boundaries of Deep Generative Neural Networks
• Few-Shot Learning with Intra-Class Knowledge Transfer
• SPSG: Self-Supervised Photometric Scene Generation from RGB-D Scans
• Augmentation-Interpolative AutoEncoders for Unsupervised Few-Shot Image Generation
• Text Guided Person Image Synthesis
• Hidden Convexity of Wasserstein GANs: Interpretable Generative Models with Closed-Form Solutions
• FaceShapeGene: A Disentangled Shape Representation for Flexible Face Image Editing
• Auditing AI models for Verified Deployment under Semantic Specifications
• Generative adversarial network based on chaotic time series
• Towards an Understanding of Neural Networks in Natural-Image Spaces
• Covering up bias in CelebA-like datasets with Markov blankets: A post-hoc cure for attribute prior avoidance
• Example-Guided Scene Image Synthesis using Masked Spatial-Channel Attention and Patch-Based Self-Supervision
• Deep Meditations: Controlled navigation of latent space
• GANs with Variational Entropy Regularizers: Applications in Mitigating the Mode-Collapse Issue
• PriorGAN: Real Data Prior for Generative Adversarial Nets
• Constant-Expansion Suffices for Compressed Sensing with Generative Priors
• From Image to Imuge: Immunized Image Generation
• Deep Generative Modeling in Network Science with Applications to Public Policy Research
• Semi-supervised Semantic Segmentation of Prostate and Organs-at-Risk on 3D Pelvic CT Images
• SAFRON: Stitching Across the Frontier for Generating Colorectal Cancer Histology Images
• Using Generative Models for Pediatric wbMRI
• Synthesis and Edition of Ultrasound Images via Sketch Guided Progressive Growing GANs
• Multi-Texture GAN: Exploring the Multi-Scale Texture Translation for Brain MR Images
• A Novel Framework for Selection of GANs for an Application
• Woodbury Transformations for Deep Generative Flows
• Pareto GAN: Extending the Representational Power of GANs to Heavy-Tailed Distributions
• Interpreting the Latent Space of GANs via Correlation Analysis for Controllable Concept Manipulation
• Attribute-Driven Spontaneous Motion in Unpaired Image Translation
• Scalable Fine-grained Generated Image Classification Based on Deep Metric Learning
• Orthogonal Wasserstein GANs
• Collaborative Sampling in Generative Adversarial Networks
• Learning Discriminators as Energy Networks in Adversarial Learning
• Efficient Super Resolution For Large-Scale Images Using Attentional GAN
• Reborn Mechanism: Rethinking the Negative Phase Information Flow in Convolutional Neural Network
• Parametric Synthesis of Text on Stylized Backgrounds using PGGANs
• Channel-Recurrent Autoencoding for Image Modeling
• Language Model Evaluation in Open-ended Text Generation
• High-dimensional Assisted Generative Model for Color Image Restoration
• A Neuro-AI Interface for Evaluating Generative Adversarial Networks
• Deep-learning PDEs with unlabeled data and hardwiring physics laws
• Deep Consensus Learning
• Restore from Restored: Single-image Inpainting
• Fine-grained Image-to-Image Transformation towards Visual Recognition
• Hierarchical Video Generation for Complex Data
• Cross-View Image Synthesis with Deformable Convolution and Attention Mechanism
• Progressively-Growing AmbientGANs For Learning Stochastic Object Models From Imaging Measurements
• Advancing the AmbientGAN for learning stochastic object models
• Adaptive Divergence for Rapid Adversarial Optimization
• G3AN: Disentangling Appearance and Motion for Video Generation
• D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
• Amora: Black-box Adversarial Morphing Attack
• Conditional Adversarial Camera Model Anonymization
• Deep Image Synthesis from Intuitive User Input: A Review and Perspectives
• Anysize GAN: A solution to the image-warping problem
• Online Kernel based Generative Adversarial Networks
• The Unreasonable Effectiveness of Texture Transfer for Single Image Super-resolution
• One-Shot Domain Adaptation For Face Generation
• PortraitGAN for Flexible Portrait Manipulation
• Venn GAN: Discovering Commonalities and Particularities of Multiple Distributions
• Free-Form Image Inpainting via Contrastive Attention Network
• 3D Guided Fine-Grained Face Manipulation
• A Spectral Enabled GAN for Time Series Data Generation
• HRVGAN: High Resolution Video Generation using Spatio-Temporal GAN
• Taming Adversarial Domain Transfer with Structural Constraints for Image Enhancement
• Disentangled Representation Learning with Information Maximizing Autoencoder
• Discriminative Cross-Modal Data Augmentation for Medical Imaging Applications
• PBGen: Partial Binarization of Deconvolution-Based Generators for Edge Intelligence
• Random Network Distillation as a Diversity Metric for Both Image and Text Generation
• Reconstructing faces from voices
• HUMBO: Bridging Response Generation and Facial Expression Synthesis
• Wasserstein Introspective Neural Networks
• Data-driven Accelerogram Synthesis using Deep Generative Models
• TunaGAN: Interpretable GAN for Smart Editing
• Inverse mapping of face GANs
• Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization
• Multi-Modal Super Resolution for Dense Microscopic Particle Size Estimation
• Image Manipulation with Natural Language using Two-sidedAttentive Conditional Generative Adversarial Network
• Image Captions are Natural Prompts for Text-to-Image Models
• Image Manipulation with Perceptual Discriminators
• Improved Image Generation via Sparse Modeling
• Face-to-Music Translation Using a Distance-Preserving Generative Adversarial Network with an Auxiliary Discriminator
• A Survey on Adversarial Image Synthesis
• Perception Matters: Exploring Imperceptible and Transferable Anti-forensics for GAN-generated Fake Face Imagery Detection
• Escaping from Collapsing Modes in a Constrained Space
• Image Semantic Transformation: Faster, Lighter and Stronger
• Rig-space Neural Rendering
• Learning to navigate image manifolds induced by generative adversarial networks for unsupervised video generation
• Directional GAN: A Novel Conditioning Strategy for Generative Networks
• Generating the support with extreme value losses
• Unsupervised Image-to-Image Translation with Stacked Cycle-Consistent Adversarial Networks
• BSD-GAN: Branched Generative Adversarial Network for Scale-Disentangled Representation Learning and Image Synthesis
• Accelerating GAN training using highly parallel hardware on public cloud
• On the Frequency Bias of Generative Models
• Assessing Automated Machine Learning service to detect COVID-19 from X-Ray and CT images: A Real-time Smartphone Application case study
• An Independent Discriminant Network Towards Identification of Counterfeit Images and Videos
• Generative Model with Dynamic Linear Flow
• Continuous learning of face attribute synthesis
• Multi-Attributed and Structured Text-to-Face Synthesis
• High Diversity Attribute Guided Face Generation with GANs
• Securing Voice-driven Interfaces against Fake (Cloned) Audio Attacks
• Procedural 3D Terrain Generation using Generative Adversarial Networks
• Wavelets to the Rescue: Improving Sample Quality of Latent Variable Deep Generative Models
• Nested Scale Editing for Conditional Image Synthesis
• NeurInt : Learning to Interpolate through Neural ODEs
• Adaptive Densely Connected Super-Resolution Reconstruction
• Improving Stability of LS-GANs for Audio and Speech Signals
• GL-GAN: Adaptive Global and Local Bilevel Optimization model of Image Generation
• Dual Encoder-Decoder based Generative Adversarial Networks for Disentangled Facial Representation Learning
• Barcode Method for Generative Model Evaluation driven by Topological Data Analysis
• Deep Generative Models: Deterministic Prediction with an Application in Inverse Rendering
• Deeply Matting-based Dual Generative Adversarial Network for Image and Document Label Supervision
• Reconstructing discrete measures from projections. Consequences on the empirical Sliced Wasserstein Distance
• Unsupervised Cross-Domain Speech-to-Speech Conversion with Time-Frequency Consistency
• GIID-Net: Generalizable Image Inpainting Detection via Neural Architecture Search and Attention
• Fast Face Image Synthesis with Minimal Training
• Enlisting 3D Crop Models and GANs for More Data Efficient and Generalizable Fruit Detection
• Dual Projection Generative Adversarial Networks for Conditional Image Generation
• Adversarial Code Learning for Image Generation
• Sym-parameterized Dynamic Inference for Mixed-Domain Image Translation
• Sequentially Aggregated Convolutional Networks
• Separation of target anatomical structure and occlusions in chest radiographs
• PCGAN-CHAR: Progressively Trained Classifier Generative Adversarial Networks for Classification of Noisy Handwritten Bangla Characters
• Pixel-wise Dense Detector for Image Inpainting
• One-shot domain adaptation for semantic face editing of real world images using StyleALAE
• Learning to Inpaint by Progressively Growing the Mask Regions
• Style-Restricted GAN: Multi-Modal Translation with Style Restriction Using Generative Adversarial Networks
• Difference-in-Differences: Bridging Normalization and Disentanglement in PG-GAN
• Shape related constraints aware generation of Mechanical Designs through Deep Convolutional GAN
• Reducing the Representation Error of GAN Image Priors Using the Deep Decoder
• TUCaN: Progressively Teaching Colourisation to Capsules
• Inverting Generative Adversarial Renderer for Face Reconstruction
• Self-supervised Correlation Mining Network for Person Image Generation
• TiVGAN: Text to Image to Video Generation with Step-by-Step Evolutionary Generator
• Face Images as Jigsaw Puzzles: Compositional Perception of Human Faces for Machines Using Generative Adversarial Networks
• Generating Diverse Realistic Laughter for Interactive Art
• Exploring Adversarial Fake Images on Face Manifold
• Towards Disentangling Latent Space for Unsupervised Semantic Face Editing
• Conditional Invertible Neural Networks for Diverse Image-to-Image Translation
• Capsule GAN for Prostate MRI Super-Resolution