Conditional Image Synthesis With Auxiliary Classifier GANs

Abstract

Synthesizing high resolution photorealistic images has been a long-standing challenge in machine learning. In this paper we introduce new methods for the improved training of generative adversarial networks (GANs) for image synthesis. We construct a variant of GANs employing label conditioning that results in 128x128 resolution image samples exhibiting global coherence. We expand on previous work for image quality assessment to provide two new analyses for assessing the discriminability and diversity of samples from class-conditional image synthesis models. These analyses demonstrate that high resolution samples provide class information not present in low resolution samples. Across 1000 ImageNet classes, 128x128 samples are more than twice as discriminable as artificially resized 32x32 samples. In addition, 84.7% of the classes have samples exhibiting diversity comparable to real ImageNet data.

References in corpus (13)

• Sequence to Sequence Learning with Neural Networks
• Conditional Generative Adversarial Nets
• Conditional Image Generation with PixelCNN Decoders
• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
• Going Deeper with Convolutions
• Density estimation using Real NVP
• Semi-Supervised Learning with Generative Adversarial Networks
• Massively Multitask Networks for Drug Discovery
• Synthesizing the preferred inputs for neurons in neural networks via deep generator networks
• Learning What and Where to Draw
• Better Mixing via Deep Representations
• Improving Variational Inference with Inverse Autoregressive Flow
• Generative Adversarial Nets from a Density Ratio Estimation Perspective

Cited by in corpus (609)

• Spectral Normalization for Generative Adversarial Networks
• GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification
• Generative Adversarial Network in Medical Imaging: A Review
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• Improved Training of Wasserstein GANs
• CovidGAN: Data Augmentation Using Auxiliary Classifier GAN for Improved Covid-19 Detection
• Deep neural network models for computational histopathology: A survey
• Data Synthesis based on Generative Adversarial Networks
• Deep Learning for Chest X-ray Analysis: A Survey
• Multimodal Intelligence: Representation Learning, Information Fusion, and Applications
• cGANs with Projection Discriminator
• How Generative Adversarial Networks and Their Variants Work: An Overview
• Generating Multi-label Discrete Patient Records using Generative Adversarial Networks
• Sharpness-aware Low dose CT denoising using conditional generative adversarial network
• State Representation Learning for Control: An Overview
• Improved Precision and Recall Metric for Assessing Generative Models
• Generative Adversarial Networks in Computer Vision: A Survey and Taxonomy
• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
• Semantic Image Synthesis with Spatially-Adaptive Normalization
• BAGAN: Data Augmentation with Balancing GAN
• Variational Approaches for Auto-Encoding Generative Adversarial Networks
• Neural Photo Editing with Introspective Adversarial Networks
• GANSynth: Adversarial Neural Audio Synthesis
• Triple Generative Adversarial Nets
• Multimodal Co-learning: Challenges, Applications with Datasets, Recent Advances and Future Directions
• MD-GAN: Multi-Discriminator Generative Adversarial Networks for Distributed Datasets
• Adversarial Text-to-Image Synthesis: A Review
• Using GANs for Sharing Networked Time Series Data: Challenges, Initial Promise, and Open Questions
• The Numerics of GANs
• Representation Learning by Rotating Your Faces
• An Introduction to Image Synthesis with Generative Adversarial Nets
• Road Segmentation for Remote Sensing Images using Adversarial Spatial Pyramid Networks
• Federated Adversarial Domain Adaptation
• Differentially Private Synthetic Medical Data Generation using Convolutional GANs
• Toward Controlled Generation of Text
• Checkerboard artifact free sub-pixel convolution: A note on sub-pixel convolution, resize convolution and convolution resize
• Selective Synthetic Augmentation with HistoGAN for Improved Histopathology Image Classification
• Towards the Automatic Anime Characters Creation with Generative Adversarial Networks
• Generative Adversarial Networks (GANs) in Networking: A Comprehensive Survey & Evaluation
• Generative Adversarial Networks for Spatio-temporal Data: A Survey
• Constructing Unrestricted Adversarial Examples with Generative Models
• Video-to-Video Synthesis
• A Bayesian Data Augmentation Approach for Learning Deep Models
• TAC-GAN - Text Conditioned Auxiliary Classifier Generative Adversarial Network
• Enhanced Balancing GAN: Minority-class Image Generation
• Adaptive DropBlock Enhanced Generative Adversarial Networks for Hyperspectral Image Classification
• Review: Deep Learning in Electron Microscopy
• Regressive and generative neural networks for scalar field theory
• Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step
• Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform
• Artistic Glyph Image Synthesis via One-Stage Few-Shot Learning
• IH-GAN: A Conditional Generative Model for Implicit Surface-Based Inverse Design of Cellular Structures
• Implicit Generation and Generalization in Energy-Based Models
• ContraGAN: Contrastive Learning for Conditional Image Generation
• StarGAN v2: Diverse Image Synthesis for Multiple Domains
• High-Fidelity Image Generation With Fewer Labels
• Incremental Classifier Learning with Generative Adversarial Networks
• Controlling generative models with continuous factors of variations
• ChatPainter: Improving Text to Image Generation using Dialogue
• On Accurate Evaluation of GANs for Language Generation
• Interpreting the Latent Space of GANs for Semantic Face Editing
• On Self Modulation for Generative Adversarial Networks
• Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models
• Unsupervised Image-to-Image Translation with Generative Adversarial Networks
• SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing Objects
• Integrating the Data Augmentation Scheme with Various Classifiers for Acoustic Scene Modeling
• CTAB-GAN: Effective Table Data Synthesizing
• Stabilizing Generative Adversarial Networks: A Survey
• CM-GANs: Cross-modal Generative Adversarial Networks for Common Representation Learning
• Memory Replay GANs: learning to generate images from new categories without forgetting
• PasteGAN: A Semi-Parametric Method to Generate Image from Scene Graph
• CVAE-GAN: Fine-Grained Image Generation through Asymmetric Training
• Security and Privacy Issues in Deep Learning
• Small Sample Learning in Big Data Era
• Receptive Field Regularization Techniques for Audio Classification and Tagging with Deep Convolutional Neural Networks
• Generative OpenMax for Multi-Class Open Set Classification
• Efficient texture-aware multi-GAN for image inpainting
• Multi-Generator Generative Adversarial Nets
• Normalization Techniques in Training DNNs: Methodology, Analysis and Application
• Photographic Text-to-Image Synthesis with a Hierarchically-nested Adversarial Network
• Improved generator objectives for GANs
• Improving the Improved Training of Wasserstein GANs: A Consistency Term and Its Dual Effect
• Coverless Information Hiding Based on Generative adversarial networks
• Evaluation Metrics for Conditional Image Generation
• ACVAE-VC: Non-parallel many-to-many voice conversion with auxiliary classifier variational autoencoder
• Yes, we GAN: Applying Adversarial Techniques for Autonomous Driving
• Consistency Regularization for Generative Adversarial Networks
• Activation Maximization Generative Adversarial Nets
• medigan: a Python library of pretrained generative models for medical image synthesis
• Distribution Matching in Variational Inference
• DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis
• Stacked Generative Adversarial Networks
• Model Patching: Closing the Subgroup Performance Gap with Data Augmentation
• Adversarial Domain Adaptation with Prototype-Based Normalized Output Conditioner
• CalliGAN: Style and Structure-aware Chinese Calligraphy Character Generator
• Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning
• MelanoGANs: High Resolution Skin Lesion Synthesis with GANs
• Progressive Pose Attention Transfer for Person Image Generation
• Inferring Semantic Layout for Hierarchical Text-to-Image Synthesis
• Fully Automatic Electrocardiogram Classification System based on Generative Adversarial Network with Auxiliary Classifier
• Multi-View Image Generation from a Single-View
• High-Resolution Mammogram Synthesis using Progressive Generative Adversarial Networks
• GANimation: Anatomically-aware Facial Animation from a Single Image
• Semi-supervised Conditional GANs
• CR-GAN: Learning Complete Representations for Multi-view Generation
• Recent Advances of Continual Learning in Computer Vision: An Overview
• PeaceGAN: A GAN-based Multi-Task Learning Method for SAR Target Image Generation with a Pose Estimator and an Auxiliary Classifier
• Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphs
• Rethinking Monocular Depth Estimation with Adversarial Training
• SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis
• Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information Estimator
• Learning to Transfer Examples for Partial Domain Adaptation
• LoGANv2: Conditional Style-Based Logo Generation with Generative Adversarial Networks
• Semi-Latent GAN: Learning to generate and modify facial images from attributes
• Feature Alignment and Restoration for Domain Generalization and Adaptation
• Approximability of Discriminators Implies Diversity in GANs
• Wasserstein Generative Adversarial Uncertainty Quantification in Physics-Informed Neural Networks
• Generative Adversarial Networks (GANs): An Overview of Theoretical Model, Evaluation Metrics, and Recent Developments
• Style Transfer for Anime Sketches with Enhanced Residual U-net and Auxiliary Classifier GAN
• Generative Adversarial Networks for Image and Video Synthesis: Algorithms and Applications
• Face Synthesis from Visual Attributes via Sketch using Conditional VAEs and GANs
• Towards Open-Set Identity Preserving Face Synthesis
• Unsupervised End-to-End Learning of Discrete Linguistic Units for Voice Conversion
• Synthetic flow-based cryptomining attack generation through Generative Adversarial Networks
• Spatially Controllable Image Synthesis with Internal Representation Collaging
• Visually-Aware Fashion Recommendation and Design with Generative Image Models
• On the Evaluation of Conditional GANs
• Class-Splitting Generative Adversarial Networks
• MGGAN: Solving Mode Collapse using Manifold Guided Training
• Semantically Decomposing the Latent Spaces of Generative Adversarial Networks
• Domain-adaptive Message Passing Graph Neural Network
• Low-shot Learning via Covariance-Preserving Adversarial Augmentation Networks
• PConv: Simple yet Effective Convolutional Layer for Generative Adversarial Network
• Landmark Assisted CycleGAN for Cartoon Face Generation
• Generalized Capsule Networks with Trainable Routing Procedure
• FedGAN: Federated Generative Adversarial Networks for Distributed Data
• Generative Adversarial Talking Head: Bringing Portraits to Life with a Weakly Supervised Neural Network
• Simple yet Effective Way for Improving the Performance of GAN
• Improved Training of Generative Adversarial Networks Using Representative Features
• A Conditional Generative Model for Predicting Material Microstructures from Processing Methods
• A survey on Adversarial Recommender Systems: from Attack/Defense strategies to Generative Adversarial Networks
• Uncertainty Quantification in Deep Learning for Safer Neuroimage Enhancement
• Opportunities and Challenges in Deep Learning Adversarial Robustness: A Survey
• Improved Consistency Regularization for GANs
• Memorization Precedes Generation: Learning Unsupervised GANs with Memory Networks
• Training Shallow and Thin Networks for Acceleration via Knowledge Distillation with Conditional Adversarial Networks
• TextureGAN: Controlling Deep Image Synthesis with Texture Patches
• High-resolution Deep Convolutional Generative Adversarial Networks
• Synthesizing realistic neural population activity patterns using Generative Adversarial Networks
• Distilling and Transferring Knowledge via cGAN-generated Samples for Image Classification and Regression
• Decentralized Learning of Generative Adversarial Networks from Non-iid Data
• Multi-Channel Attention Selection GAN with Cascaded Semantic Guidance for Cross-View Image Translation
• McGan: Mean and Covariance Feature Matching GAN
• X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers
• Generative Adversarial Network Architectures For Image Synthesis Using Capsule Networks
• Generative Adversarial Networks: A Survey Towards Private and Secure Applications
• Regularizing Deep Networks with Semantic Data Augmentation
• FCC-GAN: A Fully Connected and Convolutional Net Architecture for GANs
• DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation
• Gang of GANs: Generative Adversarial Networks with Maximum Margin Ranking
• SemanticAdv: Generating Adversarial Examples via Attribute-conditional Image Editing
• Transferring GANs: generating images from limited data
• Towards resilient machine learning for ransomware detection
• Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networks
• Finding an Unsupervised Image Segmenter in Each of Your Deep Generative Models
• InfinityGAN: Towards Infinite-Pixel Image Synthesis
• Taming Visually Guided Sound Generation
• Learning Layout and Style Reconfigurable GANs for Controllable Image Synthesis
• Adversarial Information Factorization
• Compatible and Diverse Fashion Image Inpainting
• Labeled Graph Generative Adversarial Networks
• Chinese Typography Transfer
• COVID-19 CT Image Synthesis with a Conditional Generative Adversarial Network
• Wasserstein Dependency Measure for Representation Learning
• DASGAN -- Joint Domain Adaptation and Segmentation for the Analysis of Epithelial Regions in Histopathology PD-L1 Images
• 3DGAUnet: 3D generative adversarial networks with a 3D U-Net based generator to achieve the accurate and effective synthesis of clinical tumor image data for pancreatic cancer
• Closed-Loop Data Transcription to an LDR via Minimaxing Rate Reduction
• Learning Human Motion Models for Long-term Predictions
• Exploring DeshuffleGANs in Self-Supervised Generative Adversarial Networks
• Improving novelty detection with generative adversarial networks on hand gesture data
• Towards Understanding Adversarial Examples Systematically: Exploring Data Size, Task and Model Factors
• Unsupervised Person Image Synthesis in Arbitrary Poses
• Enhancing the Robustness of Deep Neural Networks by Boundary Conditional GAN
• StarGAN-VC2: Rethinking Conditional Methods for StarGAN-Based Voice Conversion
• Justifying Diagnosis Decisions by Deep Neural Networks
• Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Tasks
• Learning Face Age Progression: A Pyramid Architecture of GANs
• A Review of Learning with Deep Generative Models from Perspective of Graphical Modeling
• Interactive Sketch & Fill: Multiclass Sketch-to-Image Translation
• Region Based Adversarial Synthesis of Facial Action Units
• TorchGAN: A Flexible Framework for GAN Training and Evaluation
• PA-GAN: Progressive Attention Generative Adversarial Network for Facial Attribute Editing
• Fair Generative Modeling via Weak Supervision
• The Six Fronts of the Generative Adversarial Networks
• Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation
• Learning to Sketch with Shortcut Cycle Consistency
• Top-k Training of GANs: Improving GAN Performance by Throwing Away Bad Samples
• Adversarial Training for Disease Prediction from Electronic Health Records with Missing Data
• Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation
• DrumGAN: Synthesis of Drum Sounds With Timbral Feature Conditioning Using Generative Adversarial Networks
• Semi-Supervised StyleGAN for Disentanglement Learning
• CANZSL: Cycle-Consistent Adversarial Networks for Zero-Shot Learning from Natural Language
• Common Spatial Generative Adversarial Networks based EEG Data Augmentation for Cross-Subject Brain-Computer Interface
• Generative Low-bitwidth Data Free Quantization
• Wasserstein Distance Based Domain Adaptation for Object Detection
• UGAN: Untraceable GAN for Multi-Domain Face Translation
• Wide and deep volumetric residual networks for volumetric image classification
• Improving the Speed and Quality of GAN by Adversarial Training
• Generative Partial Multi-View Clustering
• Anisotropic Stroke Control for Multiple Artists Style Transfer
• To Create What You Tell: Generating Videos from Captions
• Study of Deep Generative Models for Inorganic Chemical Compositions
• GAN-based Tabular Data Generator for Constructing Synopsis in Approximate Query Processing: Challenges and Solutions
• Teacher-Student Compression with Generative Adversarial Networks
• From source to target and back: symmetric bi-directional adaptive GAN
• Active Image Synthesis for Efficient Labeling
• ACE: Adapting to Changing Environments for Semantic Segmentation
• From Inference to Generation: End-to-end Fully Self-supervised Generation of Human Face from Speech
• Learning the Redundancy-free Features for Generalized Zero-Shot Object Recognition
• Disentangling Multiple Conditional Inputs in GANs
• MichiGAN: Multi-Input-Conditioned Hair Image Generation for Portrait Editing
• Discriminative Region Proposal Adversarial Networks for High-Quality Image-to-Image Translation
• AdvSPADE: Realistic Unrestricted Attacks for Semantic Segmentation
• GlyphGAN: Style-Consistent Font Generation Based on Generative Adversarial Networks
• Improving the quality of generative models through Smirnov transformation
• Surprising Negative Results for Generative Adversarial Tree Search
• RadialGAN: Leveraging multiple datasets to improve target-specific predictive models using Generative Adversarial Networks
• Modular Generative Adversarial Networks
• cGANs with Multi-Hinge Loss
• DA-GAN: Instance-level Image Translation by Deep Attention Generative Adversarial Networks (with Supplementary Materials)
• Unbiased Auxiliary Classifier GANs with MINE
• Generation of 3D Brain MRI Using Auto-Encoding Generative Adversarial Networks
• Controllable Generative Adversarial Network
• Human Action Generation with Generative Adversarial Networks
• Attribute Guided Unpaired Image-to-Image Translation with Semi-supervised Learning
• Interactive Image Manipulation with Natural Language Instruction Commands
• Versatile Auxiliary Classifier with Generative Adversarial Network (VAC+GAN), Multi Class Scenarios
• Training Deep Energy-Based Models with f-Divergence Minimization
• Distillation Techniques for Pseudo-rehearsal Based Incremental Learning
• Human Motion Transfer from Poses in the Wild
• MulGAN: Facial Attribute Editing by Exemplar
• Adversarial Image Translation: Unrestricted Adversarial Examples in Face Recognition Systems
• Is Discriminator a Good Feature Extractor?
• Improving GAN Training with Probability Ratio Clipping and Sample Reweighting
• COCO-GAN: Generation by Parts via Conditional Coordinating
• An Introduction to Person Re-identification with Generative Adversarial Networks
• Guided Variational Autoencoder for Disentanglement Learning
• Annealing Genetic GAN for Minority Oversampling
• Disentangling Style and Content in Anime Illustrations
• Fast Real-time Counterfactual Explanations
• A Survey and Taxonomy of Adversarial Neural Networks for Text-to-Image Synthesis
• Imbalanced Data Learning by Minority Class Augmentation using Capsule Adversarial Networks
• Multi-Mapping Image-to-Image Translation with Central Biasing Normalization
• The Neural Painter: Multi-Turn Image Generation
• Learning from Natural Noise to Denoise Micro-Doppler Spectrogram
• Multi-target Voice Conversion without Parallel Data by Adversarially Learning Disentangled Audio Representations
• Adaptive Generation of Unrestricted Adversarial Inputs
• Two Birds with One Stone: Transforming and Generating Facial Images with Iterative GAN
• Wav2Pix: Speech-conditioned Face Generation using Generative Adversarial Networks
• Rethinking Global Context in Crowd Counting
• An Improved Self-supervised GAN via Adversarial Training
• Robust or Private? Adversarial Training Makes Models More Vulnerable to Privacy Attacks
• Learning from a Complementary-label Source Domain: Theory and Algorithms
• Triple Generative Adversarial Networks
• Fine-grained Synthesis of Unrestricted Adversarial Examples
• DeshuffleGAN: A Self-Supervised GAN to Improve Structure Learning
• Semantic Bottleneck Scene Generation
• Continuous Conditional Generative Adversarial Networks: Novel Empirical Losses and Label Input Mechanisms
• Style Normalization and Restitution for Domain Generalization and Adaptation
• Conditional GANs with Auxiliary Discriminative Classifier
• Self-Supervised GAN to Counter Forgetting
• Hypernetworks for Continual Semi-Supervised Learning
• General-to-Detailed GAN for Infrequent Class Medical Images
• Learning Spatial Pyramid Attentive Pooling in Image Synthesis and Image-to-Image Translation
• Understanding the Effectiveness of Lipschitz-Continuity in Generative Adversarial Nets
• A Multi-attribute Controllable Generative Model for Histopathology Image Synthesis
• CounteRGAN: Generating Realistic Counterfactuals with Residual Generative Adversarial Nets
• Novel View Synthesis for Large-scale Scene using Adversarial Loss
• Disentangling and Learning Robust Representations with Natural Clustering
• Few-shot Video-to-Video Synthesis
• JGAN: A Joint Formulation of GAN for Synthesizing Images and Labels
• Versatile Auxiliary Regressor with Generative Adversarial network (VAR+GAN)
• Sequential Attention GAN for Interactive Image Editing
• Leveraging Visual Question Answering to Improve Text-to-Image Synthesis
• Deep Domain-Adversarial Image Generation for Domain Generalisation
• Image Synthesis From Reconfigurable Layout and Style
• Self-Supervised GANs via Auxiliary Rotation Loss
• Label-Noise Robust Generative Adversarial Networks
• Additional Look into GAN-based Augmentation for Deep Learning COVID-19 Image Classification
• Oversampling Adversarial Network for Class-Imbalanced Fault Diagnosis
• GANwriting: Content-Conditioned Generation of Styled Handwritten Word Images
• Adversarial Learning of General Transformations for Data Augmentation
• Deep Adversarial Transition Learning using Cross-Grafted Generative Stacks
• Variational Inference for Computational Imaging Inverse Problems
• Reconstructing ERP Signals Using Generative Adversarial Networks for Mobile Brain-Machine Interface
• A Decentralized Adaptive Momentum Method for Solving a Class of Min-Max Optimization Problems
• Learning Compositional Visual Concepts with Mutual Consistency
• Adversarial-Learned Loss for Domain Adaptation
• cGANs with Conditional Convolution Layer
• Decoupled Learning for Conditional Adversarial Networks
• Conditional Adversarial Generative Flow for Controllable Image Synthesis
• Evaluation of the Spatio-Temporal features and GAN for Micro-expression Recognition System
• Semantics Preserving Adversarial Learning
• Synthetic Augmentation and Feature-based Filtering for Improved Cervical Histopathology Image Classification
• DeepBlur: A Simple and Effective Method for Natural Image Obfuscation
• SDIT: Scalable and Diverse Cross-domain Image Translation
• CDCGen: Cross-Domain Conditional Generation via Normalizing Flows and Adversarial Training
• TwoStreamVAN: Improving Motion Modeling in Video Generation
• Hair-GANs: Recovering 3D Hair Structure from a Single Image
• Causal Adversarial Network for Learning Conditional and Interventional Distributions
• Pose-Guided High-Resolution Appearance Transfer via Progressive Training
• Generate High Resolution Images With Generative Variational Autoencoder
• CPGAN: Full-Spectrum Content-Parsing Generative Adversarial Networks for Text-to-Image Synthesis
• Improving Global Adversarial Robustness Generalization With Adversarially Trained GAN
• Generative Adversarial Zero-Shot Relational Learning for Knowledge Graphs
• Diverse Sample Generation: Pushing the Limit of Generative Data-free Quantization
• Fonts-2-Handwriting: A Seed-Augment-Train framework for universal digit classification
• Quality Evaluation of GANs Using Cross Local Intrinsic Dimensionality
• A Plug-in Method for Representation Factorization in Connectionist Models
• MatchGAN: A Self-Supervised Semi-Supervised Conditional Generative Adversarial Network
• FontGAN: A Unified Generative Framework for Chinese Character Stylization and De-stylization
• MixNMatch: Multifactor Disentanglement and Encoding for Conditional Image Generation
• Structured Prediction using cGANs with Fusion Discriminator
• EdgeNet: A novel approach for Arabic numeral classification
• Cooperative Training of Fast Thinking Initializer and Slow Thinking Solver for Conditional Learning
• On the Diversity of Realistic Image Synthesis
• Unsupervised CT Metal Artifact Learning using Attention-guided beta-CycleGAN
• IMAGINE: Image Synthesis by Image-Guided Model Inversion
• Image Quality Assessment Techniques Show Improved Training and Evaluation of Autoencoder Generative Adversarial Networks
• Progressive and Aligned Pose Attention Transfer for Person Image Generation
• Asymmetric GANs for Image-to-Image Translation
• GANs Can Play Lottery Tickets Too
• MRI to PET Cross-Modality Translation using Globally and Locally Aware GAN (GLA-GAN) for Multi-Modal Diagnosis of Alzheimer's Disease
• Biphasic Learning of GANs for High-Resolution Image-to-Image Translation
• Spatial PixelCNN: Generating Images from Patches
• ACGAN-based Data Augmentation Integrated with Long-term Scalogram for Acoustic Scene Classification
• An Acceleration Framework for High Resolution Image Synthesis
• Improved Techniques For Weakly-Supervised Object Localization
• Improving Consistency and Correctness of Sequence Inpainting using Semantically Guided Generative Adversarial Network
• Scalable Balanced Training of Conditional Generative Adversarial Neural Networks on Image Data
• Attentive Normalization for Conditional Image Generation
• Supervised Adversarial Networks for Image Saliency Detection
• Adversarial Graph Disentanglement
• Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples
• Unsupervised multi-modal Styled Content Generation
• The Art of Food: Meal Image Synthesis from Ingredients
• Dual Generator Generative Adversarial Networks for Multi-Domain Image-to-Image Translation
• Learning Continuous Face Age Progression: A Pyramid of GANs
• Effective Data Augmentation with Multi-Domain Learning GANs
• Selective Synthetic Augmentation with Quality Assurance
• Garment Design with Generative Adversarial Networks
• PowerGAN: Synthesizing Appliance Power Signatures Using Generative Adversarial Networks
• XRayGAN: Consistency-preserving Generation of X-ray Images from Radiology Reports
• Score-Guided Generative Adversarial Networks
• DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial Network
• Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning
• In&Out : Diverse Image Outpainting via GAN Inversion
• HumanGAN: A Generative Model of Humans Images
• Multi-Knowledge Fusion for New Feature Generation in Generalized Zero-Shot Learning
• Learning Invariant Representation for Continual Learning
• Model Extraction and Defenses on Generative Adversarial Networks
• 3D-StyleGAN: A Style-Based Generative Adversarial Network for Generative Modeling of Three-Dimensional Medical Images
• Ebola Optimization Search Algorithm (EOSA): A new metaheuristic algorithm based on the propagation model of Ebola virus disease
• Informative Class Activation Maps
• A Deep Learning Approach to Private Data Sharing of Medical Images Using Conditional GANs
• DeltaGAN: Towards Diverse Few-shot Image Generation with Sample-Specific Delta
• Disentangling representations of retinal images with generative models
• Manifold Topology Divergence: a Framework for Comparing Data Manifolds
• A multi-stage GAN for multi-organ chest X-ray image generation and segmentation
• DISSECT: Disentangled Simultaneous Explanations via Concept Traversals
• MatchingGAN: Matching-based Few-shot Image Generation
• Separating Content from Style Using Adversarial Learning for Recognizing Text in the Wild
• Variational Conditional GAN for Fine-grained Controllable Image Generation
• SkrGAN: Sketching-rendering Unconditional Generative Adversarial Networks for Medical Image Synthesis
• AutoGAN: Robust Classifier Against Adversarial Attacks
• Taking Control of Intra-class Variation in Conditional GANs Under Weak Supervision
• Customizing an Adversarial Example Generator with Class-Conditional GANs
• SCH-GAN: Semi-supervised Cross-modal Hashing by Generative Adversarial Network
• Segmentation Guided Image-to-Image Translation with Adversarial Networks
• Removing Class Imbalance using Polarity-GAN: An Uncertainty Sampling Approach
• MIXGAN: Learning Concepts from Different Domains for Mixture Generation
• Mode matching in GANs through latent space learning and inversion
• New Ideas and Trends in Deep Multimodal Content Understanding: A Review
• Versatile Auxiliary Classifier with Generative Adversarial Network (VAC+GAN)
• MPG: A Multi-ingredient Pizza Image Generator with Conditional StyleGANs
• Understanding the Intrinsic Robustness of Image Distributions using Conditional Generative Models
• Improving Model Robustness with Latent Distribution Locally and Globally
• Class-Distinct and Class-Mutual Image Generation with GANs
• A Unified Conditional Disentanglement Framework for Multimodal Brain MR Image Translation
• Synchronized Detection and Recovery of Steganographic Messages with Adversarial Learning
• Semi-supervised Conditional GAN for Simultaneous Generation and Detection of Phishing URLs: A Game theoretic Perspective
• Resembled Generative Adversarial Networks: Two Domains with Similar Attributes
• Minimax Defense against Gradient-based Adversarial Attacks
• Joint Learning of Generative Translator and Classifier for Visually Similar Classes
• GAC-GAN: A General Method for Appearance-Controllable Human Video Motion Transfer
• Continual Learning: Tackling Catastrophic Forgetting in Deep Neural Networks with Replay Processes
• Emotion Generation and Recognition: A StarGAN Approach
• Multilevel Context Representation for Improving Object Recognition
• Perturbations are not Enough: Generating Adversarial Examples with Spatial Distortions
• Generative adversarial network based on chaotic time series
• Sketch-to-Art: Synthesizing Stylized Art Images From Sketches
• Self-supervised Audio Spatialization with Correspondence Classifier
• Pipeline Generative Adversarial Networks for Facial Images Generation with Multiple Attributes
• Text Guided Person Image Synthesis
• Lip Movements Generation at a Glance
• Red-GAN: Attacking class imbalance via conditioned generation. Yet another perspective on medical image synthesis for skin lesion dermoscopy and brain tumor MRI
• Semi-supervised Learning for Few-shot Image-to-Image Translation
• Active Generative Adversarial Network for Image Classification
• M3D-GAN: Multi-Modal Multi-Domain Translation with Universal Attention
• Attribute-guided image generation from layout
• World-Consistent Video-to-Video Synthesis
• Distribution Aligned Multimodal and Multi-Domain Image Stylization
• Effective and Privacy preserving Tabular Data Synthesizing
• Deep Attentive Generative Adversarial Network for Photo-Realistic Image De-Quantization
• Generative Adversarial Mapping Networks
• CapsGAN: Using Dynamic Routing for Generative Adversarial Networks
• Conditional Video Generation Using Action-Appearance Captions
• Rare Event Detection using Disentangled Representation Learning
• Semi-Supervised Learning by Disentangling and Self-Ensembling Over Stochastic Latent Space
• F2GAN: Fusing-and-Filling GAN for Few-shot Image Generation
• Automatic Detection of Vague Words and Sentences in Privacy Policies
• Mapping Images to Psychological Similarity Spaces Using Neural Networks
• Focusing on Persons: Colorizing Old Images Learning from Modern Historical Movies
• Line Artist: A Multiple Style Sketch to Painting Synthesis Scheme
• DarkGAN: Exploiting Knowledge Distillation for Comprehensible Audio Synthesis with GANs
• Adversarial Learning of Semantic Relevance in Text to Image Synthesis
• Generative Design of Hardware-aware DNNs
• Semantic Image Manipulation Using Scene Graphs
• Deep learning framework DNN with conditional WGAN for protein solubility prediction
• A cost-effective method for improving and re-purposing large, pre-trained GANs by fine-tuning their class-embeddings
• Scenario Forecasting of Residential Load Profiles
• Improving image generative models with human interactions
• Deep Consensus Learning
• Show, Attend and Translate: Unpaired Multi-Domain Image-to-Image Translation with Visual Attention
• Latent Adversarial Defence with Boundary-guided Generation
• Taxonomy Completion via Triplet Matching Network
• InfoScrub: Towards Attribute Privacy by Targeted Obfuscation
• PC-GAIN: Pseudo-label Conditional Generative Adversarial Imputation Networks for Incomplete Data
• Omni-GAN: On the Secrets of cGANs and Beyond
• crank: An Open-Source Software for Nonparallel Voice Conversion Based on Vector-Quantized Variational Autoencoder
• Adversarial Attack Type I: Cheat Classifiers by Significant Changes
• Generating Unobserved Alternatives
• How good is my GAN?
• Robust conditional GANs under missing or uncertain labels
• How to make a pizza: Learning a compositional layer-based GAN model
• An Auxiliary Classifier Generative Adversarial Framework for Relation Extraction
• Channel-Recurrent Autoencoding for Image Modeling
• UU-Nets Connecting Discriminator and Generator for Image to Image Translation
• Imaginative Walks: Generative Random Walk Deviation Loss for Improved Unseen Learning Representation
• Capsule GAN Using Capsule Network for Generator Architecture
• Auto-Embedding Generative Adversarial Networks for High Resolution Image Synthesis
• A Novel Framework for Selection of GANs for an Application
• An Empirical Study of Batch Normalization and Group Normalization in Conditional Computation
• Continuous Face Aging via Self-estimated Residual Age Embedding
• RNN-based Generative Model for Fine-Grained Sketching
• Double cycle-consistent generative adversarial network for unsupervised conditional generation
• Deconstructing Generative Adversarial Networks
• Typeface Completion with Generative Adversarial Networks
• Differential-Critic GAN: Generating What You Want by a Cue of Preferences
• Intelligent Home 3D: Automatic 3D-House Design from Linguistic Descriptions Only
• Disentangled Face Attribute Editing via Instance-Aware Latent Space Search
• Mixture of Spectral Generative Adversarial Networks for Imbalanced Hyperspectral Image Classification
• Learning Generative Models of Tissue Organization with Supervised GANs
• Lessons Learned from the Training of GANs on Artificial Datasets
• Generative-Discriminative Complementary Learning
• MU-GAN: Facial Attribute Editing based on Multi-attention Mechanism
• A Decoupled 3D Facial Shape Model by Adversarial Training
• Attribute-Guided Sketch Generation
• Attribute-conditioned Layout GAN for Automatic Graphic Design
• Weakly Supervised Context Encoder using DICOM metadata in Ultrasound Imaging
• Fine-grained Image-to-Image Transformation towards Visual Recognition
• ICE-GAN: Identity-aware and Capsule-Enhanced GAN with Graph-based Reasoning for Micro-Expression Recognition and Synthesis
• Data Augmentation via Mixed Class Interpolation using Cycle-Consistent Generative Adversarial Networks Applied to Cross-Domain Imagery
• Towards a Neural Graphics Pipeline for Controllable Image Generation
• Intrinsic Autoencoders for Joint Neural Rendering and Intrinsic Image Decomposition
• SSN: Soft Shadow Network for Image Compositing
• DLGAN: Disentangling Label-Specific Fine-Grained Features for Image Manipulation
• Multiple Exemplars-based Hallucinationfor Face Super-resolution and Editing
• TreeGAN: Incorporating Class Hierarchy into Image Generation
• Discriminative Cross-Modal Data Augmentation for Medical Imaging Applications
• Conditioning Trick for Training Stable GANs
• Random Network Distillation as a Diversity Metric for Both Image and Text Generation
• CoPE: Conditional image generation using Polynomial Expansions
• MR-Contrast-Aware Image-to-Image Translations with Generative Adversarial Networks
• Robust Training Using Natural Transformation
• Generating Unrestricted 3D Adversarial Point Clouds
• Weakly-supervised Generative Adversarial Networks for medical image classification
• Multiple Organ Failure Prediction with Classifier-Guided Generative Adversarial Imputation Networks
• Deep Image Synthesis from Intuitive User Input: A Review and Perspectives
• On The Distribution of Penultimate Activations of Classification Networks
• Synthesizing Multi-Tracer PET Images for Alzheimer's Disease Patients using a 3D Unified Anatomy-aware Cyclic Adversarial Network
• Generative Models for Security: Attacks, Defenses, and Opportunities
• Realistic Image Synthesis with Configurable 3D Scene Layouts
• Guiding the One-to-one Mapping in CycleGAN via Optimal Transport
• Student's t-Generative Adversarial Networks
• Protecting Anonymous Speech: A Generative Adversarial Network Methodology for Removing Stylistic Indicators in Text
• Visual Explanations for Convolutional Neural Networks via Latent Traversal of Generative Adversarial Networks
• Teaching a GAN What Not to Learn
• Geometry-Aware Universal Mirror-Prox
• End-to-end Generative Zero-shot Learning via Few-shot Learning
• CIZSL++: Creativity Inspired Generative Zero-Shot Learning
• A Spectral Enabled GAN for Time Series Data Generation
• A Multimodal Classifier Generative Adversarial Network for Carry and Place Tasks from Ambiguous Language Instructions
• Unsupervised Disentanglement of Linear-Encoded Facial Semantics
• Supervised Anomaly Detection via Conditional Generative Adversarial Network and Ensemble Active Learning
• YuruGAN: Yuru-Chara Mascot Generator Using Generative Adversarial Networks With Clustering Small Dataset
• Generative Creativity: Adversarial Learning for Bionic Design
• Stabilizing Training of Generative Adversarial Nets via Langevin Stein Variational Gradient Descent
• Generative Feature Replay with Orthogonal Weight Modification for Continual Learning
• Words as Art Materials: Generating Paintings with Sequential GANs
• Learning End-to-End Action Interaction by Paired-Embedding Data Augmentation
• Unsupervised Representation Adversarial Learning Network: from Reconstruction to Generation
• Benefiting Deep Latent Variable Models via Learning the Prior and Removing Latent Regularization
• Domain2Vec: Domain Embedding for Unsupervised Domain Adaptation
• Generative networks as inverse problems with fractional wavelet scattering networks
• Neural Crossbreed: Neural Based Image Metamorphosis
• PBGen: Partial Binarization of Deconvolution-Based Generators for Edge Intelligence
• Online Detection of Action Start in Untrimmed, Streaming Videos
• Robust Conditional GAN from Uncertainty-Aware Pairwise Comparisons
• Face Attribute Invertion
• CookGAN: Meal Image Synthesis from Ingredients
• Low-Shot Learning from Imaginary 3D Model
• A Layer-Based Sequential Framework for Scene Generation with GANs
• Domain Adaptive Person Re-Identification via Camera Style Generation and Label Propagation
• G2R Bound: A Generalization Bound for Supervised Learning from GAN-Synthetic Data
• Understanding Natural Language Instructions for Fetching Daily Objects Using GAN-Based Multimodal Target-Source Classification
• Making Method of Moments Great Again? -- How can GANs learn distributions
• Conditional Adversarial Camera Model Anonymization
• Learn to synthesize and synthesize to learn
• Resisting Large Data Variations via Introspective Transformation Network
• FusedProp: Towards Efficient Training of Generative Adversarial Networks
• Enhanced Magnetic Resonance Image Synthesis with Contrast-Aware Generative Adversarial Networks
• Deploying Scientific AI Networks at Petaflop Scale on Secure Large Scale HPC Production Systems with Containers
• Disentangling Latent Space for VAE by Label Relevant/Irrelevant Dimensions
• Deep Semantic Hashing with Generative Adversarial Networks
• Conditional Neural Architecture Search
• Impressions2Font: Generating Fonts by Specifying Impressions
• 3D-MOV: Audio-Visual LSTM Autoencoder for 3D Reconstruction of Multiple Objects from Video
• ReshapeGAN: Object Reshaping by Providing A Single Reference Image
• Generative Adversarial Network based Speaker Adaptation for High Fidelity WaveNet Vocoder
• Physical Context and Timing Aware Sequence Generating GANs
• HAD-GAN: A Human-perception Auxiliary Defense GAN to Defend Adversarial Examples
• Disentanglement based Active Learning
• Generating Long-term Continuous Multi-type Generation Profiles
• AIP: Adversarial Iterative Pruning Based on Knowledge Transfer for Convolutional Neural Networks
• Learning Task-oriented Disentangled Representations for Unsupervised Domain Adaptation
• Learning to Reconstruct and Segment 3D Objects
• Multi-Attributed and Structured Text-to-Face Synthesis
• Training face verification models from generated face identity data
• Evaluating the distribution learning capabilities of GANs
• Force-in-domain GAN inversion
• Parallel Medical Imaging for Intelligent Medical Image Analysis: Concepts, Methods, and Applications
• Class Balancing GAN with a Classifier in the Loop
• Synthetic Convolutional Features for Improved Semantic Segmentation
• Conditional Image Generation with One-Vs-All Classifier
• Cascading Modular Network (CAM-Net) for Multimodal Image Synthesis
• On the Performance of Generative Adversarial Network (GAN) Variants: A Clinical Data Study
• Stochastic Deconvolutional Neural Network Ensemble Training on Generative Pseudo-Adversarial Networks
• Grounded Language Understanding for Manipulation Instructions Using GAN-Based Classification
• Conditional Transferring Features: Scaling GANs to Thousands of Classes with 30% Less High-quality Data for Training
• FoCL: Feature-Oriented Continual Learning for Generative Models
• Labeled Data Generation with Inexact Supervision
• Improving Differentiable Architecture Search with a Generative Model
• ClsGAN: Selective Attribute Editing Model Based On Classification Adversarial Network
• Gated SwitchGAN for multi-domain facial image translation
• TiVGAN: Text to Image to Video Generation with Step-by-Step Evolutionary Generator
• Neural Wireframe Renderer: Learning Wireframe to Image Translations
• Capturing Evolution Genes for Time Series Data
• Dual Projection Generative Adversarial Networks for Conditional Image Generation
• Subspace Capsule Network
• Generating Videos of Zero-Shot Compositions of Actions and Objects
• Hierarchical Reinforcement Learning with Optimal Level Synchronization Based on Flow-Based Deep Generative Model
• Improving Generalization via Attribute Selection on Out-of-the-box Data
• Generative Steganography with Kerckhoffs' Principle
• Stein Latent Optimization for Generative Adversarial Networks
• Label Geometry Aware Discriminator for Conditional Generative Networks
• Towards Fair Cross-Domain Adaptation via Generative Learning
• Sinusoidal wave generating network based on adversarial learning and its application: synthesizing frog sounds for data augmentation
• Style-Restricted GAN: Multi-Modal Translation with Style Restriction Using Generative Adversarial Networks
• Synthetic Image Augmentation for Improved Classification using Generative Adversarial Networks
• Inner Space Preserving Generative Pose Machine
• A Generative Approach for Detection-driven Underwater Image Enhancement
• More than just an auxiliary loss: Anti-spoofing Backbone Training via Adversarial Pseudo-depth Generation
• ArrowGAN : Learning to Generate Videos by Learning Arrow of Time
• Virtual Conditional Generative Adversarial Networks
• Deep Factorised Inverse-Sketching
• Editable Generative Adversarial Networks: Generating and Editing Faces Simultaneously
• HumanACGAN: conditional generative adversarial network with human-based auxiliary classifier and its evaluation in phoneme perception
• Generative Adversarial Networks for Unsupervised Object Co-localization
• FakeSafe: Human Level Data Protection by Disinformation Mapping using Cycle-consistent Adversarial Network
• Inducing Optimal Attribute Representations for Conditional GANs
• DINO: A Conditional Energy-Based GAN for Domain Translation
• Dual-MTGAN: Stochastic and Deterministic Motion Transfer for Image-to-Video Synthesis
• Learning to see across Domains and Modalities
• A study of traits that affect learnability in GANs
• CooGAN: A Memory-Efficient Framework for High-Resolution Facial Attribute Editing
• Improving Model Compatibility of Generative Adversarial Networks by Boundary Calibration
• Multi-attribute Pizza Generator: Cross-domain Attribute Control with Conditional StyleGAN
• Sym-parameterized Dynamic Inference for Mixed-Domain Image Translation
• ID-Unet: Iterative Soft and Hard Deformation for View Synthesis
• Generating Adversarial Examples With Conditional Generative Adversarial Net
• Harnessing the Conditioning Sensorium for Improved Image Translation
• Linear Discriminant Generative Adversarial Networks
• Linear Semantics in Generative Adversarial Networks
• Finite Difference Nets: A Deep Recurrent Framework for Solving Evolution PDEs
• PCGAN-CHAR: Progressively Trained Classifier Generative Adversarial Networks for Classification of Noisy Handwritten Bangla Characters
• Bridging the Gap between Label- and Reference-based Synthesis in Multi-attribute Image-to-Image Translation
• Shape-conditioned Image Generation by Learning Latent Appearance Representation from Unpaired Data
• Approximating Probability Distributions by using Wasserstein Generative Adversarial Networks