Conditional Generative Adversarial Nets

Abstract

Generative Adversarial Nets [8] were recently introduced as a novel way to train generative models. In this work we introduce the conditional version of generative adversarial nets, which can be constructed by simply feeding the data, y, we wish to condition on to both the generator and discriminator. We show that this model can generate MNIST digits conditioned on class labels. We also illustrate how this model could be used to learn a multi-modal model, and provide preliminary examples of an application to image tagging in which we demonstrate how this approach can generate descriptive tags which are not part of training labels.

References in corpus (3)

• Improving neural networks by preventing co-adaptation of feature detectors
• Going Deeper with Convolutions
• Better Mixing via Deep Representations

Cited by in corpus (229)

• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
• Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data
• CyCADA: Cycle-Consistent Adversarial Domain Adaptation
• EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning
• Adversarial Discriminative Domain Adaptation
• Unsupervised Cross-Domain Image Generation
• Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN
• Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs
• Guided Image Generation with Conditional Invertible Neural Networks
• Disentangling factors of variation in deep representations using adversarial training
• Mode Regularized Generative Adversarial Networks
• Filmy Cloud Removal on Satellite Imagery with Multispectral Conditional Generative Adversarial Nets
• Maximum-Likelihood Augmented Discrete Generative Adversarial Networks
• MRI-only brain radiotherapy: assessing the dosimetric accuracy of synthetic CT images generated using a deep learning approach
• Towards the Automatic Anime Characters Creation with Generative Adversarial Networks
• Adversarial Feature Matching for Text Generation
• Dual Discriminator Generative Adversarial Nets
• A Bayesian Data Augmentation Approach for Learning Deep Models
• Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networks
• TAC-GAN - Text Conditioned Auxiliary Classifier Generative Adversarial Network
• Leveraging the Invariant Side of Generative Zero-Shot Learning
• Adversarial Generation of Natural Language
• Age Progression/Regression by Conditional Adversarial Autoencoder
• Continual Learning in Generative Adversarial Nets
• Transferring Multiscale Map Styles Using Generative Adversarial Networks
• Probabilistic Forecasting of Sensory Data with Generative Adversarial Networks - ForGAN
• Language Generation with Recurrent Generative Adversarial Networks without Pre-training
• Generative Adversarial Residual Pairwise Networks for One Shot Learning
• Triangle Generative Adversarial Networks
• Data Augmentation in Emotion Classification Using Generative Adversarial Networks
• Unsupervised Image-to-Image Translation with Generative Adversarial Networks
• Robust Imitation of Diverse Behaviors
• A Point Set Generation Network for 3D Object Reconstruction from a Single Image
• Semi and Weakly Supervised Semantic Segmentation Using Generative Adversarial Network
• A Novel Topology Optimization Approach using Conditional Deep Learning
• Deferred Neural Rendering: Image Synthesis using Neural Textures
• Coverless Information Hiding Based on Generative adversarial networks
• Generative adversarial network-based glottal waveform model for statistical parametric speech synthesis
• Finger-GAN: Generating Realistic Fingerprint Images Using Connectivity Imposed GAN
• DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis
• Deep De-Aliasing for Fast Compressive Sensing MRI
• Progressive Pose Attention Transfer for Person Image Generation
• Limits of Deepfake Detection: A Robust Estimation Viewpoint
• Image Companding and Inverse Halftoning using Deep Convolutional Neural Networks
• AGAN: Towards Automated Design of Generative Adversarial Networks
• Transformation-Grounded Image Generation Network for Novel 3D View Synthesis
• Adversarial Generation of Training Examples: Applications to Moving Vehicle License Plate Recognition
• Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis
• Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal
• Early Action Prediction with Generative Adversarial Networks
• Style Transfer for Anime Sketches with Enhanced Residual U-net and Auxiliary Classifier GAN
• Face Synthesis from Visual Attributes via Sketch using Conditional VAEs and GANs
• Visually-Aware Fashion Recommendation and Design with Generative Image Models
• Conditional Adversarial Network for Semantic Segmentation of Brain Tumor
• Towards Optimal Structured CNN Pruning via Generative Adversarial Learning
• Unsupervised Visual Attribute Transfer with Reconfigurable Generative Adversarial Networks
• Iris-GAN: Learning to Generate Realistic Iris Images Using Convolutional GAN
• Neural Painters: A learned differentiable constraint for generating brushstroke paintings
• Model-based Adversarial Imitation Learning
• Multi-Channel Attention Selection GAN with Cascaded Semantic Guidance for Cross-View Image Translation
• Structured Generative Adversarial Networks
• Generative Adversarial Networks for Financial Trading Strategies Fine-Tuning and Combination
• Learning Loss Functions for Semi-supervised Learning via Discriminative Adversarial Networks
• Unsupervised Adversarial Attacks on Deep Feature-based Retrieval with GAN
• Comparative Study on Generative Adversarial Networks
• X2CT-GAN: Reconstructing CT from Biplanar X-Rays with Generative Adversarial Networks
• A Probe Towards Understanding GAN and VAE Models
• FCC-GAN: A Fully Connected and Convolutional Net Architecture for GANs
• High-Quality Face Image SR Using Conditional Generative Adversarial Networks
• Bandwidth Extension on Raw Audio via Generative Adversarial Networks
• Adversarial Learning for Improved Onsets and Frames Music Transcription
• GeoGAN: A Conditional GAN with Reconstruction and Style Loss to Generate Standard Layer of Maps from Satellite Images
• QGAN: Quantized Generative Adversarial Networks
• Multi-hop Federated Private Data Augmentation with Sample Compression
• Using Scene Graph Context to Improve Image Generation
• Attacking Speaker Recognition With Deep Generative Models
• Encoding Invariances in Deep Generative Models
• An Adversarial Approach to High-Quality, Sentiment-Controlled Neural Dialogue Generation
• CCMI : Classifier based Conditional Mutual Information Estimation
• DeepFlash: Turning a Flash Selfie into a Studio Portrait
• STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing
• Characterizing Bias in Classifiers using Generative Models
• Exploiting Excessive Invariance caused by Norm-Bounded Adversarial Robustness
• Compatible and Diverse Fashion Image Inpainting
• End-to-End Learning of Geometric Deformations of Feature Maps for Virtual Try-On
• Augmenting correlation structures in spatial data using deep generative models
• Towards Understanding Adversarial Examples Systematically: Exploring Data Size, Task and Model Factors
• HashGAN:Attention-aware Deep Adversarial Hashing for Cross Modal Retrieval
• Message Passing Multi-Agent GANs
• Towards Multi-pose Guided Virtual Try-on Network
• Semi-supervised learning based on generative adversarial network: a comparison between good GAN and bad GAN approach
• Energy-based Models for Video Anomaly Detection
• $c^{+}$GAN: Complementary Fashion Item Recommendation
• Photorealistic Facial Expression Synthesis by the Conditional Difference Adversarial Autoencoder
• SRGAN: Training Dataset Matters
• Kernel Change-point Detection with Auxiliary Deep Generative Models
• Interactive Generative Adversarial Networks for Facial Expression Generation in Dyadic Interactions
• Exploring Bias in GAN-based Data Augmentation for Small Samples
• Synthetic to Real Adaptation with Generative Correlation Alignment Networks
• AlignGAN: Learning to Align Cross-Domain Images with Conditional Generative Adversarial Networks
• A Utility-Preserving GAN for Face Obscuration
• Global and Local Consistent Age Generative Adversarial Networks
• Task Specific Adversarial Cost Function
• Creatism: A deep-learning photographer capable of creating professional work
• Latent Translation: Crossing Modalities by Bridging Generative Models
• Adversarial Pseudo Healthy Synthesis Needs Pathology Factorization
• An Error Detection and Correction Framework for Connectomics
• Improving Heterogeneous Face Recognition with Conditional Adversarial Networks
• Dense Intrinsic Appearance Flow for Human Pose Transfer
• FTGAN: A Fully-trained Generative Adversarial Networks for Text to Face Generation
• GlyphGAN: Style-Consistent Font Generation Based on Generative Adversarial Networks
• Ways of Conditioning Generative Adversarial Networks
• Deep Reasoning Networks: Thinking Fast and Slow
• Adversarial nets with perceptual losses for text-to-image synthesis
• Interaction-aware Multi-agent Tracking and Probabilistic Behavior Prediction via Adversarial Learning
• Deep Learning based End-to-End Wireless Communication Systems with Conditional GAN as Unknown Channel
• Connecting Touch and Vision via Cross-Modal Prediction
• Conditional Single-view Shape Generation for Multi-view Stereo Reconstruction
• GILT: Generating Images from Long Text
• PI-REC: Progressive Image Reconstruction Network With Edge and Color Domain
• Generative Adversarial Network based on Resnet for Conditional Image Restoration
• An Introduction to Person Re-identification with Generative Adversarial Networks
• Vid2Game: Controllable Characters Extracted from Real-World Videos
• Never Forget: Balancing Exploration and Exploitation via Learning Optical Flow
• Mask-Guided Portrait Editing with Conditional GANs
• Wav2Pix: Speech-conditioned Face Generation using Generative Adversarial Networks
• Recent Advances of Image Steganography with Generative Adversarial Networks
• Designing nanophotonic structures using conditional-deep convolutional generative adversarial networks
• Gated Context Model with Embedded Priors for Deep Image Compression
• Out-of-Distribution Detection for Generalized Zero-Shot Action Recognition
• TV-GAN: Generative Adversarial Network Based Thermal to Visible Face Recognition
• Unsupervised Multi-Domain Image Translation with Domain-Specific Encoders/Decoders
• RL-GAN-Net: A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape Completion
• Chinese Typeface Transformation with Hierarchical Adversarial Network
• Learning Disentangling and Fusing Networks for Face Completion Under Structured Occlusions
• Fully-Featured Attribute Transfer
• Conditional Adversarial Generative Flow for Controllable Image Synthesis
• Conditional Density Estimation with Neural Networks: Best Practices and Benchmarks
• Predicting Rapid Fire Growth (Flashover) Using Conditional Generative Adversarial Networks
• Statistical Parametric Speech Synthesis Using Generative Adversarial Networks Under A Multi-task Learning Framework
• FMRI data augmentation via synthesis
• Generative Class-conditional Autoencoders
• Generative adversarial networks for generation and classification of physical rehabilitation movement episodes
• On the Diversity of Realistic Image Synthesis
• Personalization of Saliency Estimation
• Improving Consistency and Correctness of Sequence Inpainting using Semantically Guided Generative Adversarial Network
• A Novel BiLevel Paradigm for Image-to-Image Translation
• Label-Noise Robust Multi-Domain Image-to-Image Translation
• Lung CT Imaging Sign Classification through Deep Learning on Small Data
• Image-based reconstruction for the impact problems by using DPNNs
• Coconditional Autoencoding Adversarial Networks for Chinese Font Feature Learning
• Handwritten Chinese Font Generation with Collaborative Stroke Refinement
• Structured Prediction using cGANs with Fusion Discriminator
• Generative Adversarial Classifier for Handwriting Characters Super-Resolution
• Generation High resolution 3D model from natural language by Generative Adversarial Network
• The Art of Food: Meal Image Synthesis from Ingredients
• Multi-Level Sequence GAN for Group Activity Recognition
• retina-VAE: Variationally Decoding the Spectrum of Macular Disease
• Snore-GANs: Improving Automatic Snore Sound Classification with Synthesized Data
• Trick or TReAT: Thematic Reinforcement for Artistic Typography
• Dual Generator Generative Adversarial Networks for Multi-Domain Image-to-Image Translation
• End-to-End Time-Lapse Video Synthesis from a Single Outdoor Image
• Segmentation Guided Image-to-Image Translation with Adversarial Networks
• CDVAE: Co-embedding Deep Variational Auto Encoder for Conditional Variational Generation
• Improving Bi-directional Generation between Different Modalities with Variational Autoencoders
• Adversarial Pixel-Level Generation of Semantic Images
• Ancient Painting to Natural Image: A New Solution for Painting Processing
• Better Guider Predicts Future Better: Difference Guided Generative Adversarial Networks
• Learning Disentangled Representations of Satellite Image Time Series
• Active Generative Adversarial Network for Image Classification
• Pipeline Generative Adversarial Networks for Facial Images Generation with Multiple Attributes
• Depth Structure Preserving Scene Image Generation
• M3D-GAN: Multi-Modal Multi-Domain Translation with Universal Attention
• Mask Embedding in conditional GAN for Guided Synthesis of High Resolution Images
• AMAD: Adversarial Multiscale Anomaly Detection on High-Dimensional and Time-Evolving Categorical Data
• URNet : User-Resizable Residual Networks with Conditional Gating Module
• View Invariant 3D Human Pose Estimation
• UU-Nets Connecting Discriminator and Generator for Image to Image Translation
• Applying Generative Adversarial Networks to Intelligent Subsurface Imaging and Identification
• Scenario Forecasting of Residential Load Profiles
• Robust conditional GANs under missing or uncertain labels
• Stable Distribution Alignment Using the Dual of the Adversarial Distance
• Awesome Typography: Statistics-Based Text Effects Transfer
• Painting on Placement: Forecasting Routing Congestion using Conditional Generative Adversarial Nets
• Typeface Completion with Generative Adversarial Networks
• Differentially Private Generative Adversarial Networks for Time Series, Continuous, and Discrete Open Data
• Domain Adaptive Person Re-Identification via Camera Style Generation and Label Propagation
• One-Shot Image-to-Image Translation via Part-Global Learning with a Multi-adversarial Framework
• G2R Bound: A Generalization Bound for Supervised Learning from GAN-Synthetic Data
• Improved visible to IR image transformation using synthetic data augmentation with cycle-consistent adversarial networks
• Reconstructing faces from voices
• PAC-GAN: An Effective Pose Augmentation Scheme for Unsupervised Cross-View Person Re-identification
• f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning
• Synthesis of High-Quality Visible Faces from Polarimetric Thermal Faces using Generative Adversarial Networks
• DepthwiseGANs: Fast Training Generative Adversarial Networks for Realistic Image Synthesis
• Domain Partitioning Network
• Improving learnability of neural networks: adding supplementary axes to disentangle data representation
• Venn GAN: Discovering Commonalities and Particularities of Multiple Distributions
• IVE-GAN: Invariant Encoding Generative Adversarial Networks
• Visual Data Augmentation through Learning
• Kernel Mean Matching for Content Addressability of GANs
• Learning to Clean: A GAN Perspective
• Diversity Regularized Adversarial Learning
• WAYLA - Generating Images from Eye Movements
• Learning to see across Domains and Modalities
• Label-Removed Generative Adversarial Networks Incorporating with K-Means
• Realistic Ultrasonic Environment Simulation Using Conditional Generative Adversarial Networks
• Linear Discriminant Generative Adversarial Networks
• Generating Adversarial Examples With Conditional Generative Adversarial Net
• Generative Adversarial Networks for Multimodal Representation Learning in Video Hyperlinking
• Generative Adversarial Nets for Multiple Text Corpora
• Instance Map based Image Synthesis with a Denoising Generative Adversarial Network
• Grounded Language Understanding for Manipulation Instructions Using GAN-Based Classification
• A Coarse-to-Fine Framework for Learned Color Enhancement with Non-Local Attention
• Sinusoidal wave generating network based on adversarial learning and its application: synthesizing frog sounds for data augmentation
• Cyclone intensity estimate with context-aware cyclegan
• Expression Conditional GAN for Facial Expression-to-Expression Translation
• Localization in Aerial Imagery with Grid Maps using LocGAN
• Neural Embedding for Physical Manipulations
• End-to-End Learning Using Cycle Consistency for Image-to-Caption Transformations
• Generative Adversarial Imagination for Sample Efficient Deep Reinforcement Learning
• Is 'Unsupervised Learning' a Misconceived Term?
• Downhole Track Detection via Multiscale Conditional Generative Adversarial Nets
• Compact Scene Graphs for Layout Composition and Patch Retrieval
• Video-to-Video Translation for Visual Speech Synthesis
• ReshapeGAN: Object Reshaping by Providing A Single Reference Image
• Virtual Conditional Generative Adversarial Networks
• Generative Adversarial Networks for Recovering Missing Spectral Information
• Generative Adversarial Networks for Black-Box API Attacks with Limited Training Data