500种对抗生成网络

最新推荐文章于 2024-04-24 21:15:58 发布
最新推荐文章于 2024-04-24 21:15:58 发布
阅读量714 收藏 3
点赞数
分类专栏： 人工智能 智能计算 基础学习
原文链接：https://github.com/hindupuravinash/the-gan-zoo
版权

这里列出了印度一个大神整理的对抗生成网络GAN公园，里面列出了几乎所有的对抗生成网络。

 

可喜的是他还对这些网络进行的分类整理

YearMonthAbbr.TitleArxivOfficial_CodeWatchesStarsForks
 20146GANGenerative Adversarial Networkshttps://arxiv.org/abs/1406.2661https://github.com/goodfeli/adversarial1081736666
 201411CGANConditional Generative Adversarial Netshttps://arxiv.org/abs/1411.1784-   
 20156LAPGANDeep Generative Image Models using a Laplacian Pyramid of Adversarial Networkshttps://arxiv.org/abs/1506.05751https://github.com/facebook/eyescream52581138
 201511CatGANUnsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networkshttps://arxiv.org/abs/1511.06390v2-   
 201511DCGANUnsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkshttps://arxiv.org/abs/1511.06434https://github.com/Newmu/dcgan_code1682849581
 201512VAE-GANAutoencoding beyond pixels using a learned similarity metrichttps://arxiv.org/abs/1512.09300-   
 20162GRANGenerating images with recurrent adversarial networkshttps://arxiv.org/abs/1602.05110https://github.com/jiwoongim/GRAN710431
 20163S^2GANGenerative Image Modeling using Style and Structure Adversarial Networkshttps://arxiv.org/abs/1603.05631v2-   
 20164MGANPrecomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networkshttps://arxiv.org/abs/1604.04382https://github.com/chuanli11/MGANs2324143
 20165BiGANAdversarial Feature Learninghttps://arxiv.org/abs/1605.09782v7-   
 20165GAN-CLSGenerative Adversarial Text to Image Synthesishttps://arxiv.org/abs/1605.05396https://github.com/reedscot/icml201639677155
 20166ALIAdversarially Learned Inferencehttps://arxiv.org/abs/1606.00704https://github.com/IshmaelBelghazi/ALI1626272
 20166CoGANCoupled Generative Adversarial Networkshttps://arxiv.org/abs/1606.07536v2-   
 20166f-GANf-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationhttps://arxiv.org/abs/1606.00709-   
 20166Improved GANImproved Techniques for Training GANshttps://arxiv.org/abs/1606.03498https://github.com/openai/improved-gan1431462445
 20166InfoGANInfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netshttps://arxiv.org/abs/1606.03657v1https://github.com/openai/InfoGAN100666211
 20167SketchGANAdversarial Training For Sketch Retrievalhttps://arxiv.org/abs/1607.02748-   
 20169Context-RNN-GANContextual RNN-GANs for Abstract Reasoning Diagram Generationhttps://arxiv.org/abs/1609.09444-   
 20169EBGANEnergy-based Generative Adversarial Networkhttps://arxiv.org/abs/1609.03126v4-   
 20169IANNeural Photo Editing with Introspective Adversarial Networkshttps://arxiv.org/abs/1609.07093https://github.com/ajbrock/Neural-Photo-Editor741753152
 20169iGANGenerative Visual Manipulation on the Natural Image Manifoldhttps://arxiv.org/abs/1609.03552v2https://github.com/junyanz/iGAN1512984425
 20169SeqGANSeqGAN: Sequence Generative Adversarial Nets with Policy Gradienthttps://arxiv.org/abs/1609.05473v5https://github.com/LantaoYu/SeqGAN711243464
 20169SRGANPhoto-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkhttps://arxiv.org/abs/1609.04802-   
 20169VGANGenerating Videos with Scene Dynamicshttps://arxiv.org/abs/1609.02612https://github.com/cvondrick/videogan34556114
 2016103D-GANLearning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelinghttps://arxiv.org/abs/1610.07584https://github.com/zck119/3dgan-release44437122
 201610AC-GANConditional Image Synthesis With Auxiliary Classifier GANshttps://arxiv.org/abs/1610.09585-   
 201610AffGANAmortised MAP Inference for Image Super-resolutionhttps://arxiv.org/abs/1610.04490-   
 201610GAWWNLearning What and Where to Drawhttps://arxiv.org/abs/1610.02454https://github.com/reedscot/nips20162229955
 201611b-GANGenerative Adversarial Nets from a Density Ratio Estimation Perspectivehttps://arxiv.org/abs/1610.02920-   
 201611C-RNN-GANC-RNN-GAN: Continuous recurrent neural networks with adversarial traininghttps://arxiv.org/abs/1611.09904https://github.com/olofmogren/c-rnn-gan/1318867
 201611CC-GANSemi-Supervised Learning with Context-Conditional Generative Adversarial Networkshttps://arxiv.org/abs/1611.06430https://github.com/edenton/cc-gan5162
 201611DTNUnsupervised Cross-Domain Image Generationhttps://arxiv.org/abs/1611.02200-   
 201611GMANGenerative Multi-Adversarial Networkshttp://arxiv.org/abs/1611.01673-   
 201611IcGANInvertible Conditional GANs for image editinghttps://arxiv.org/abs/1611.06355https://github.com/Guim3/IcGAN6188285
 201611LSGANLeast Squares Generative Adversarial Networkshttps://arxiv.org/abs/1611.04076v3-   
 201611MV-BiGANMulti-view Generative Adversarial Networkshttps://arxiv.org/abs/1611.02019v1-   
 201611pix2pixImage-to-Image Translation with Conditional Adversarial Networkshttps://arxiv.org/abs/1611.07004https://github.com/phillipi/pix2pix2485260839
 201611RenderGANRenderGAN: Generating Realistic Labeled Datahttps://arxiv.org/abs/1611.01331-   
 201611SAD-GANSAD-GAN: Synthetic Autonomous Driving using Generative Adversarial Networkshttps://arxiv.org/abs/1611.08788v1-   
 201611SGANTexture Synthesis with Spatial Generative Adversarial Networkshttps://arxiv.org/abs/1611.08207-   
 201611SSL-GANSemi-Supervised Learning with Context-Conditional Generative Adversarial Networkshttps://arxiv.org/abs/1611.06430v1-   
 201611TGANTemporal Generative Adversarial Netshttps://arxiv.org/abs/1611.06624v1-   
 201611Unrolled GANUnrolled Generative Adversarial Networkshttps://arxiv.org/abs/1611.02163https://github.com/poolio/unrolled_gan1423440
 201611VGANGenerative Adversarial Networks as Variational Training of Energy Based Modelshttps://arxiv.org/abs/1611.01799https://github.com/Shuangfei/vgan31510
 201612AL-CGANLearning to Generate Images of Outdoor Scenes from Attributes and Semantic Layoutshttps://arxiv.org/abs/1612.00215-   
 201612MARTA-GANDeep Unsupervised Representation Learning for Remote Sensing Imageshttps://arxiv.org/abs/1612.08879-   
 201612MDGANMode Regularized Generative Adversarial Networkshttps://arxiv.org/abs/1612.02136-   
 201612MPM-GANMessage Passing Multi-Agent GANshttps://arxiv.org/abs/1612.01294-   
 201612PPGNPlug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Spacehttps://arxiv.org/abs/1612.00005-   
 201612PrGAN3D Shape Induction from 2D Views of Multiple Objectshttps://arxiv.org/abs/1612.05872-   
 201612SGANStacked Generative Adversarial Networkshttps://arxiv.org/abs/1612.04357v4https://github.com/xunhuang1995/SGAN820249
 201612SimGANLearning from Simulated and Unsupervised Images through Adversarial Traininghttps://arxiv.org/abs/1612.07828-   
 201612StackGANStackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networkshttps://arxiv.org/abs/1612.03242v1https://github.com/hanzhanggit/StackGAN591201295
 201612textGANGenerating Text via Adversarial Traininghttps://zhegan27.github.io/Papers/textGAN_nips2016_workshop.pdf-   
 20171AdaGANAdaGAN: Boosting Generative Modelshttps://arxiv.org/abs/1701.02386v1-   
 20171ID-CGANImage De-raining Using a Conditional Generative Adversarial Networkhttps://arxiv.org/abs/1701.05957v3-   
 20171LAGANLearning Particle Physics by Example: Location-Aware Generative Adversarial Networks for Physics Synthesishttps://arxiv.org/abs/1701.05927-   
 20171LS-GANLoss-Sensitive Generative Adversarial Networks on Lipschitz Densitieshttps://arxiv.org/abs/1701.06264-   
 20171SalGANSalGAN: Visual Saliency Prediction with Generative Adversarial Networkshttps://arxiv.org/abs/1701.01081https://github.com/imatge-upc/saliency-salgan-20171518080
 20171Unim2imUnsupervised Image-to-Image Translation with Generative Adversarial Networkshttps://arxiv.org/abs/1701.02676http://github.com/zsdonghao/Unsup-Im2Im74812
 20171ViGANImage Generation and Editing with Variational Info Generative Adversarial Networkshttps://arxiv.org/abs/1701.04568v1-   
 20171WGANWasserstein GANhttps://arxiv.org/abs/1701.07875v2https://github.com/martinarjovsky/WassersteinGAN991939469
 20172acGANFace Aging With Conditional Generative Adversarial Networkshttps://arxiv.org/abs/1702.01983-   
 20172ArtGANArtGAN: Artwork Synthesis with Conditional Categorial GANshttps://arxiv.org/abs/1702.03410-   
 20172Bayesian GANDeep and Hierarchical Implicit Modelshttps://arxiv.org/abs/1702.08896-   
 20172BS-GANBoundary-Seeking Generative Adversarial Networkshttps://arxiv.org/abs/1702.08431v1-   
 20172MalGANGenerating Adversarial Malware Examples for Black-Box Attacks Based on GANhttps://arxiv.org/abs/1702.05983v1-   
 20172MaliGANMaximum-Likelihood Augmented Discrete Generative Adversarial Networkshttps://arxiv.org/abs/1702.07983-   
 20172McGANMcGan: Mean and Covariance Feature Matching GANhttps://arxiv.org/abs/1702.08398v1-   
 20172ST-GANStyle Transfer Generative Adversarial Networks: Learning to Play Chess Differentlyhttps://arxiv.org/abs/1702.06762-   
 20172WaterGANWaterGAN: Unsupervised Generative Network to Enable Real-time Color Correction of Monocular Underwater Imageshttps://arxiv.org/abs/1702.07392v1-   
 20173AEGANLearning Inverse Mapping by Autoencoder based Generative Adversarial Netshttps://arxiv.org/abs/1703.10094-   
 20173AM-GANActivation Maximization Generative Adversarial Netshttps://arxiv.org/abs/1703.02000-   
 20173AnoGANUnsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoveryhttps://arxiv.org/abs/1703.05921v1-   
 20173BEGANBEGAN: Boundary Equilibrium Generative Adversarial Networkshttps://arxiv.org/abs/1703.10717-   
 20173CS-GANImproving Neural Machine Translation with Conditional Sequence Generative Adversarial Netshttps://arxiv.org/abs/1703.04887-   
 20173CVAE-GANCVAE-GAN: Fine-Grained Image Generation through Asymmetric Traininghttps://arxiv.org/abs/1703.10155-   
 20173CycleGANUnpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkshttps://arxiv.org/abs/1703.10593https://github.com/junyanz/CycleGAN34571141099
 20173DiscoGANLearning to Discover Cross-Domain Relations with Generative Adversarial Networkshttps://arxiv.org/abs/1703.05192v1-   
 20173GP-GANGP-GAN: Towards Realistic High-Resolution Image Blendinghttps://arxiv.org/abs/1703.07195https://github.com/wuhuikai/GP-GAN612729
 20173LR-GANLR-GAN: Layered Recursive Generative Adversarial Networks for Image Generationhttps://arxiv.org/abs/1703.01560v1-   
 20173MedGANGenerating Multi-label Discrete Electronic Health Records using Generative Adversarial Networkshttps://arxiv.org/abs/1703.06490v1-   
 20173MIX+GANGeneralization and Equilibrium in Generative Adversarial Nets (GANs)https://arxiv.org/abs/1703.00573v3-   
 20173RTT-GANRecurrent Topic-Transition GAN for Visual Paragraph Generationhttps://arxiv.org/abs/1703.07022v2-   
 20173SEGANSEGAN: Speech Enhancement Generative Adversarial Networkhttps://arxiv.org/abs/1703.09452v1-   
 20173SeGANSeGAN: Segmenting and Generating the Invisiblehttps://arxiv.org/abs/1703.10239-   
 20173SGANSteganographic Generative Adversarial Networkshttps://arxiv.org/abs/1703.05502-   
 20173TAC-GANTAC-GAN - Text Conditioned Auxiliary Classifier Generative Adversarial Networkhttps://arxiv.org/abs/1703.06412v2https://github.com/dashayushman/TAC-GAN33615
 20173Triple-GANTriple Generative Adversarial Netshttps://arxiv.org/abs/1703.02291v2-   
 20173UNITUnsupervised Image-to-image Translation Networkshttps://arxiv.org/abs/1703.00848https://github.com/mingyuliutw/UNIT551094201
 20174DualGANDualGAN: Unsupervised Dual Learning for Image-to-Image Translationhttps://arxiv.org/abs/1704.02510v1-   
 20174FF-GANTowards Large-Pose Face Frontalization in the Wildhttps://arxiv.org/abs/1704.06244-   
 20174GoGANGang of GANs: Generative Adversarial Networks with Maximum Margin Rankinghttps://arxiv.org/abs/1704.04865-   
 20174MAD-GANMulti-Agent Diverse Generative Adversarial Networkshttps://arxiv.org/abs/1704.02906-   
 20174MAGANMAGAN: Margin Adaptation for Generative Adversarial Networkshttps://arxiv.org/abs/1704.03817v1-   
 20174SL-GANSemi-Latent GAN: Learning to generate and modify facial images from attributeshttps://arxiv.org/abs/1704.02166-   
 20174Softmax GANSoftmax GANhttps://arxiv.org/abs/1704.06191-   
 20174TANOutline Colorization through Tandem Adversarial Networkshttps://arxiv.org/abs/1704.08834-   
 20174TP-GANBeyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesishttps://arxiv.org/abs/1704.04086-   
 20174VariGANMulti-View Image Generation from a Single-Viewhttps://arxiv.org/abs/1704.04886-   
 20174VAW-GANVoice Conversion from Unaligned Corpora using Variational Autoencoding Wasserstein Generative Adversarial Networkshttps://arxiv.org/abs/1704.00849-   
 20174WGAN-GPImproved Training of Wasserstein GANshttps://arxiv.org/abs/1704.00028https://github.com/igul222/improved_wgan_training671277415
 20174β-GANAnnealed Generative Adversarial Networkshttps://arxiv.org/abs/1705.07505-   
 20175Bayesian GANBayesian GANhttps://arxiv.org/abs/1705.09558https://github.com/andrewgordonwilson/bayesgan/53929148
 20175CaloGANCaloGAN: Simulating 3D High Energy Particle Showers in Multi-Layer Electromagnetic Calorimeters with Generative Adversarial Networkshttps://arxiv.org/abs/1705.02355https://github.com/hep-lbdl/CaloGAN96426
 20175Conditional cycleGANConditional CycleGAN for Attribute Guided Face Image Generationhttps://arxiv.org/abs/1705.09966-   
 20175Cramèr GANThe Cramer Distance as a Solution to Biased Wasserstein Gradientshttps://arxiv.org/abs/1705.10743-   
 20175DR-GANRepresentation Learning by Rotating Your Faceshttps://arxiv.org/abs/1705.11136-   
 20175DRAGANHow to Train Your DRAGANhttps://arxiv.org/abs/1705.07215https://github.com/kodalinaveen3/DRAGAN1114317
 20175ED//GANStabilizing Training of Generative Adversarial Networks through Regularizationhttps://arxiv.org/abs/1705.09367-   
 20175EGANEnhanced Experience Replay Generation for Efficient Reinforcement Learninghttps://arxiv.org/abs/1705.08245-   
 20175Fisher GANFisher GANhttps://arxiv.org/abs/1705.09675-   
 20175Flow-GANFlow-GAN: Bridging implicit and prescribed learning in generative modelshttps://arxiv.org/abs/1705.08868-   
 20175GeneGANGeneGAN: Learning Object Transfiguration and Attribute Subspace from Unpaired Datahttps://arxiv.org/abs/1705.04932https://github.com/Prinsphield/GeneGAN910622
 20175Geometric GANGeometric GANhttps://arxiv.org/abs/1705.02894-   
 20175IRGANIRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval modelshttps://arxiv.org/abs/1705.10513v1-   
 20175MMD-GANMMD GAN: Towards Deeper Understanding of Moment Matching Networkhttps://arxiv.org/abs/1705.08584https://github.com/dougalsutherland/opt-mmd711034
 20175ORGANObjective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Modelshttps://arxiv.org/abs/1705.10843-   
 20175Pose-GANThe Pose Knows: Video Forecasting by Generating Pose Futureshttps://arxiv.org/abs/1705.00053-   
 20175PSGANLearning Texture Manifolds with the Periodic Spatial GANhttp://arxiv.org/abs/1705.06566-   
 20175RankGANAdversarial Ranking for Language Generationhttps://arxiv.org/abs/1705.11001-   
 20175RPGANStabilizing GAN Training with Multiple Random Projectionshttps://arxiv.org/abs/1705.07831https://github.com/ayanc/rpgan2154
 20175RWGANRelaxed Wasserstein with Applications to GANshttps://arxiv.org/abs/1705.07164-   
 20175SBADA-GANFrom source to target and back: symmetric bi-directional adaptive GANhttps://arxiv.org/abs/1705.08824-   
 20175SD-GANSemantically Decomposing the Latent Spaces of Generative Adversarial Networkshttps://arxiv.org/abs/1705.07904-   
 20175VEEGANVEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learninghttps://arxiv.org/abs/1705.07761https://github.com/akashgit/VEEGAN2116
 20175WS-GANWeakly Supervised Generative Adversarial Networks for 3D Reconstructionhttps://arxiv.org/abs/1705.10904-   
 20176ARAEAdversarially Regularized Autoencoders for Generating Discrete Structureshttps://arxiv.org/abs/1706.04223https://github.com/jakezhaojb/ARAE1726062
 20176BCGANBayesian Conditional Generative Adverserial Networkshttps://arxiv.org/abs/1706.05477-   
 20176CANCAN: Creative Adversarial Networks, Generating Art by Learning About Styles and Deviating from Style Normshttps://arxiv.org/abs/1706.07068-   
 20176Chekhov GANAn Online Learning Approach to Generative Adversarial Networkshttps://arxiv.org/abs/1706.03269-   
 20176crVAE-GANChannel-Recurrent Variational Autoencodershttps://arxiv.org/abs/1706.03729-   
 20176DeliGANDeLiGAN : Generative Adversarial Networks for Diverse and Limited Datahttps://arxiv.org/abs/1706.02071https://github.com/val-iisc/deligan47425
 20176DistanceGANOne-Sided Unsupervised Domain Mappinghttps://arxiv.org/abs/1706.00826-   
 20176DSP-GANDepth Structure Preserving Scene Image Generationhttps://arxiv.org/abs/1706.00212-   
 20176Dualing GANDualing GANshttps://arxiv.org/abs/1706.06216-   
 20176Fila-GANSynthesizing Filamentary Structured Images with GANshttps://arxiv.org/abs/1706.02185-   
 20176GANCSDeep Generative Adversarial Networks for Compressed Sensing Automates MRIhttps://arxiv.org/abs/1706.00051-   
 20176GMM-GANTowards Understanding the Dynamics of Generative Adversarial Networkshttps://arxiv.org/abs/1706.09884-   
 20176IWGANOn Unifying Deep Generative Modelshttps://arxiv.org/abs/1706.00550-   
 20176PANPerceptual Adversarial Networks for Image-to-Image Transformationhttps://arxiv.org/abs/1706.09138-   
 20176Perceptual GANPerceptual Generative Adversarial Networks for Small Object Detectionhttps://arxiv.org/abs/1706.05274-   
 20176PixelGANPixelGAN Autoencodershttps://arxiv.org/abs/1706.00531-   
 20176RCGANReal-valued (Medical) Time Series Generation with Recurrent Conditional GANshttps://arxiv.org/abs/1706.02633-   
 20176RNN-WGANLanguage Generation with Recurrent Generative Adversarial Networks without Pre-traininghttps://arxiv.org/abs/1706.01399https://github.com/amirbar/rnn.wgan1920563
 20176SegANSegAN: Adversarial Network with Multi-scale L1 Loss for Medical Image Segmentationhttps://arxiv.org/abs/1706.01805-   
 20176TextureGANTextureGAN: Controlling Deep Image Synthesis with Texture Patcheshttps://arxiv.org/abs/1706.02823-   
 20176α-GANVariational Approaches for Auto-Encoding Generative Adversarial Networkshttps://arxiv.org/abs/1706.04987https://github.com/victor-shepardson/alpha-GAN25117
 201773D-IWGANImproved Adversarial Systems for 3D Object Generation and Reconstructionhttps://arxiv.org/abs/1707.09557https://github.com/EdwardSmith1884/3D-IWGAN77023
 20177AE-GANAE-GAN: adversarial eliminating with GANhttps://arxiv.org/abs/1707.05474-   
 20177AlignGANAlignGAN: Learning to Align Cross-Domain Images with Conditional Generative Adversarial Networkshttps://arxiv.org/abs/1707.01400-   
 20177APE-GANAPE-GAN: Adversarial Perturbation Elimination with GANhttps://arxiv.org/abs/1707.05474-   
 20177ARDAAdversarial Representation Learning for Domain Adaptationhttps://arxiv.org/abs/1707.01217-   
 20177DANDistributional Adversarial Networkshttps://arxiv.org/abs/1706.09549-   
 20177l-GANRepresentation Learning and Adversarial Generation of 3D Point Cloudshttps://arxiv.org/abs/1707.02392-   
 20177LD-GANLinear Discriminant Generative Adversarial Networkshttps://arxiv.org/abs/1707.07831-   
 20177LeGANLikelihood Estimation for Generative Adversarial Networkshttps://arxiv.org/abs/1707.07530-   
 20177MMGANMMGAN: Manifold Matching Generative Adversarial Network for Generating Imageshttps://arxiv.org/abs/1707.08273-   
 20177MoCoGANMoCoGAN: Decomposing Motion and Content for Video Generationhttps://arxiv.org/abs/1707.04993https://github.com/sergeytulyakov/mocogan1718047
 20177ResGANGenerative Adversarial Network based on Resnet for Conditional Image Restorationhttps://arxiv.org/abs/1707.04881-   
 20177SisGANSemantic Image Synthesis via Adversarial Learninghttps://arxiv.org/abs/1707.06873-   
 20177ss-InfoGANGuiding InfoGAN with Semi-Supervisionhttps://arxiv.org/abs/1707.04487-   
 20177SSGANSSGAN: Secure Steganography Based on Generative Adversarial Networkshttps://arxiv.org/abs/1707.01613-   
 20177SteinGANLearning Deep Energy Models: Contrastive Divergence vs. Amortized MLEhttps://arxiv.org/abs/1707.00797-   
 20177VRALVariance Regularizing Adversarial Learninghttps://arxiv.org/abs/1707.00309-   
 201783D-RecGAN3D Object Reconstruction from a Single Depth View with Adversarial Learninghttps://arxiv.org/abs/1708.07969https://github.com/Yang7879/3D-RecGAN86527
 20178ABC-GANABC-GAN: Adaptive Blur and Control for improved training stability of Generative Adversarial Networkshttps://drive.google.com/file/d/0B3wEP_lEl0laVTdGcHE2VnRiMlE/viewhttps://github.com/IgorSusmelj/ABC-GAN141
 20178ASDL-GANAutomatic Steganographic Distortion Learning Using a Generative Adversarial Networkhttps://ieeexplore.ieee.org/document/8017430/-   
 20178BGANBinary Generative Adversarial Networks for Image Retrievalhttps://arxiv.org/abs/1708.04150https://github.com/htconquer/BGAN61615
 20178CDcGANSimultaneously Color-Depth Super-Resolution with Conditional Generative Adversarial Networkhttps://arxiv.org/abs/1708.09105-   
 20178CGANControllable Generative Adversarial Networkhttps://arxiv.org/abs/1708.00598-   
 20178constrast-GANGenerative Semantic Manipulation with Contrasting GANhttps://arxiv.org/abs/1708.00315-   
 20178Coulomb GANCoulomb GANs: Provably Optimal Nash Equilibria via Potential Fieldshttps://arxiv.org/abs/1708.08819-   
 20178DM-GANDual Motion GAN for Future-Flow Embedded Video Predictionhttps://arxiv.org/abs/1708.00284-   
 20178GAN-sepGANs for Biological Image Synthesishttps://arxiv.org/abs/1708.04692https://github.com/aosokin/biogans58212
 20178GAN-VFSGenerative Adversarial Network-based Synthesis of Visible Faces from Polarimetric Thermal Faceshttps://arxiv.org/abs/1708.02681-   
 20178MGGANMulti-Generator Generative Adversarial Netshttps://arxiv.org/abs/1708.02556-   
 20178PGANProbabilistic Generative Adversarial Networkshttps://arxiv.org/abs/1708.01886-   
 20178SN-GANSpectral Normalization for Generative Adversarial Networkshttps://drive.google.com/file/d/0B8HZ50DPgR3eSVV6YlF3XzQxSjQ/viewhttps://github.com/pfnet-research/chainer-gan-lib3329762
 20178SS-GANSemi-supervised Conditional GANshttps://arxiv.org/abs/1708.05789-   
 20178VIGANVIGAN: Missing View Imputation with Generative Adversarial Networkshttps://arxiv.org/abs/1708.06724-   
 20179ARIGANARIGAN: Synthetic Arabidopsis Plants using Generative Adversarial Networkhttps://arxiv.org/abs/1709.00938-   
 20179CausalGANCausalGAN: Learning Causal Implicit Generative Models with Adversarial Traininghttps://arxiv.org/abs/1709.02023-   
 20179D2GANDual Discriminator Generative Adversarial Netshttp://arxiv.org/abs/1709.03831-   
 20179ExposureGANExposure: A White-Box Photo Post-Processing Frameworkhttps://arxiv.org/abs/1709.09602https://github.com/yuanming-hu/exposure1220543
 20179ExprGANExprGAN: Facial Expression Editing with Controllable Expression Intensityhttps://arxiv.org/abs/1709.03842-   
 20179GAMNGenerative Adversarial Mapping Networkshttps://arxiv.org/abs/1709.09820-   
 20179GraspGANUsing Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Graspinghttps://arxiv.org/abs/1709.07857-   
 20179LDANLabel Denoising Adversarial Network (LDAN) for Inverse Lighting of Face Imageshttps://arxiv.org/abs/1709.01993-   
 20179LeakGANLong Text Generation via Adversarial Training with Leaked Informationhttps://arxiv.org/abs/1709.08624-   
 20179MD-GANLearning to Generate Time-Lapse Videos Using Multi-Stage Dynamic Generative Adversarial Networkshttps://arxiv.org/abs/1709.07592-   
 20179MuseGANMuseGAN: Symbolic-domain Music Generation and Accompaniment with Multi-track Sequential Generative Adversarial Networkshttps://arxiv.org/abs/1709.06298-   
 20179OptionGANOptionGAN: Learning Joint Reward-Policy Options using Generative Adversarial Inverse Reinforcement Learninghttps://arxiv.org/abs/1709.06683-   
 20179PassGANPassGAN: A Deep Learning Approach for Password Guessinghttps://arxiv.org/abs/1709.00440-   
 20179RefineGANCompressed Sensing MRI Reconstruction with Cyclic Loss in Generative Adversarial Networkshttps://arxiv.org/abs/1709.00753-   
 20179Splitting GANClass-Splitting Generative Adversarial Networkshttps://arxiv.org/abs/1709.07359-   
 20179Δ-GANTriangle Generative Adversarial Networkshttps://arxiv.org/abs/1709.06548-   
 201710CM-GANCM-GANs: Cross-modal Generative Adversarial Networks for Common Representation Learninghttps://arxiv.org/abs/1710.05106-   
 201710GAN-ATVA Novel Approach to Artistic Textual Visualization via GANhttps://arxiv.org/abs/1710.10553-   
 201710GAPContext-Aware Generative Adversarial Privacyhttps://arxiv.org/abs/1710.09549-   
 201710GP-GANGP-GAN: Gender Preserving GAN for Synthesizing Faces from Landmarkshttps://arxiv.org/abs/1710.00962-   
 201710Progressive GANProgressive Growing of GANs for Improved Quality, Stability, and Variationhttps://arxiv.org/abs/1710.10196https://github.com/tkarras/progressive_growing_of_gans2323146529
 201710PS²-GANHigh-Quality Facial Photo-Sketch Synthesis Using Multi-Adversarial Networkshttps://arxiv.org/abs/1710.10182-   
 201710SVSGANSVSGAN: Singing Voice Separation via Generative Adversarial Networkhttps://arxiv.org/abs/1710.11428-   
 201710TGANTensorizing Generative Adversarial Netshttps://arxiv.org/abs/1710.10772-   
 2017113D-ED-GANShape Inpainting using 3D Generative Adversarial Network and Recurrent Convolutional Networkshttps://arxiv.org/abs/1711.06375-   
 201711ABC-GANGANs for LIFE: Generative Adversarial Networks for Likelihood Free Inferencehttps://arxiv.org/abs/1711.11139-   
 201711ACtuALACtuAL: Actor-Critic Under Adversarial Learninghttps://arxiv.org/abs/1711.04755-   
 201711AttGANArbitrary Facial Attribute Editing: Only Change What You Wanthttps://arxiv.org/abs/1711.10678https://github.com/LynnHo/AttGAN-Tensorflow1115819
 201711AttnGANAttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networkshttps://arxiv.org/abs/1711.10485https://github.com/taoxugit/AttnGAN2742097
 201711BCGANBidirectional Conditional Generative Adversarial networkshttps://arxiv.org/abs/1711.07461-   
 201711BicycleGANToward Multimodal Image-to-Image Translationhttps://arxiv.org/abs/1711.11586https://github.com/junyanz/BicycleGAN30696113
 201711CatGANCatGAN: Coupled Adversarial Transfer for Domain Generationhttps://arxiv.org/abs/1711.08904-   
 201711CoAtt-GANAre You Talking to Me? Reasoned Visual Dialog Generation through Adversarial Learninghttps://arxiv.org/abs/1711.07613-   
 201711ConceptGANLearning Compositional Visual Concepts with Mutual Consistencyhttps://arxiv.org/abs/1711.06148-   
 201711Cover-GANGenerative Steganography with Kerckhoffs' Principle based on Generative Adversarial Networkshttps://arxiv.org/abs/1711.04916-   
 201711D-GANDifferential Generative Adversarial Networks: Synthesizing Non-linear Facial Variations with Limited Number of Training Datahttps://arxiv.org/abs/1711.10267-   
 201711DAGANData Augmentation Generative Adversarial Networkshttps://arxiv.org/abs/1711.04340-   
 201711DeblurGANDeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networkshttps://arxiv.org/abs/1711.07064https://github.com/KupynOrest/DeblurGAN35971204
 201711DNA-GANDNA-GAN: Learning Disentangled Representations from Multi-Attribute Imageshttps://arxiv.org/abs/1711.05415-   
 201711DRPANDiscriminative Region Proposal Adversarial Networks for High-Quality Image-to-Image Translationhttps://arxiv.org/abs/1711.09554-   
 201711FIGANFrame Interpolation with Multi-Scale Deep Loss Functions and Generative Adversarial Networkshttps://arxiv.org/abs/1711.06045-   
 201711FSEGANExploring Speech Enhancement with Generative Adversarial Networks for Robust Speech Recognitionhttps://arxiv.org/abs/1711.05747-   
 201711FTGANHierarchical Video Generation from Orthogonal Information: Optical Flow and Texturehttps://arxiv.org/abs/1711.09618-   
 201711GANDIGuiding the search in continuous state-action spaces by learning an action sampling distribution from off-target sampleshttps://arxiv.org/abs/1711.01391-   
 201711GPUA generative adversarial framework for positive-unlabeled classificationhttps://arxiv.org/abs/1711.08054-   
 201711HANChinese Typeface Transformation with Hierarchical Adversarial Networkhttps://arxiv.org/abs/1711.06448-   
 201711HP-GANHP-GAN: Probabilistic 3D human motion prediction via GANhttps://arxiv.org/abs/1711.09561-   
 201711HR-DCGANHigh-Resolution Deep Convolutional Generative Adversarial Networkshttps://arxiv.org/abs/1711.06491-   
 201711IFcVAEGANConditional Autoencoders with Adversarial Information Factorizationhttps://arxiv.org/abs/1711.05175-   
 201711In2IIn2I : Unsupervised Multi-Image-to-Image Translation Using Generative Adversarial Networkshttps://arxiv.org/abs/1711.09334-   
 201711Iterative-GANTwo Birds with One Stone: Iteratively Learn Facial Attributes with GANshttps://arxiv.org/abs/1711.06078https://github.com/punkcure/Iterative-GAN184
 201711IVE-GANIVE-GAN: Invariant Encoding Generative Adversarial Networkshttps://arxiv.org/abs/1711.08646-   
 201711iVGANTowards an Understanding of Our World by GANing Videos in the Wildhttps://arxiv.org/abs/1711.11453https://github.com/bernhard2202/improved-video-gan729028
 201711KBGANKBGAN: Adversarial Learning for Knowledge Graph Embeddingshttps://arxiv.org/abs/1711.04071-   
 201711KGANKGAN: How to Break The Minimax Game in GANhttps://arxiv.org/abs/1711.01744-   
 201711LGANGlobal versus Localized Generative Adversarial Netshttps://arxiv.org/abs/1711.06020-   
 201711MLGANMetric Learning-based Generative Adversarial Networkhttps://arxiv.org/abs/1711.02792-   
 201711ORGAN3D Reconstruction of Incomplete Archaeological Objects Using a Generative Adversary Networkhttps://arxiv.org/abs/1711.06363-   
 201711Pip-GANPipeline Generative Adversarial Networks for Facial Images Generation with Multiple Attributeshttps://arxiv.org/abs/1711.10742-   
 201711pix2pixHDHigh-Resolution Image Synthesis and Semantic Manipulation with Conditional GANshttps://arxiv.org/abs/1711.11585https://github.com/NVIDIA/pix2pixHD1162426424
 201711Sobolev GANSobolev GANhttps://arxiv.org/abs/1711.04894-   
 201711StarGANStarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationhttps://arxiv.org/abs/1711.09020https://github.com/yunjey/StarGAN1093047491
 201711TGANTensor-Generative Adversarial Network with Two-dimensional Sparse Coding: Application to Real-time Indoor Localizationhttps://arxiv.org/abs/1711.02666-   
 201711tripletGANTripletGAN: Training Generative Model with Triplet Losshttps://arxiv.org/abs/1711.05084-   
 201711VA-GANVisual Feature Attribution using Wasserstein GANshttps://arxiv.org/abs/1711.08998-   
 201711XGANXGAN: Unsupervised Image-to-Image Translation for many-to-many Mappingshttps://arxiv.org/abs/1711.05139-   
 201711ZipNet-GANZipNet-GAN: Inferring Fine-grained Mobile Traffic Patterns via a Generative Adversarial Neural Networkhttps://arxiv.org/abs/1711.02413-   
 201712ACGANCoverless Information Hiding Based on Generative adversarial networkshttps://arxiv.org/abs/1712.06951-   
 201712CA-GANComposition-aided Sketch-realistic Portrait Generationhttps://arxiv.org/abs/1712.00899-   
 201712ComboGANComboGAN: Unrestrained Scalability for Image Domain Translationhttps://arxiv.org/abs/1712.06909https://github.com/AAnoosheh/ComboGAN58415
 201712DF-GANLearning Disentangling and Fusing Networks for Face Completion Under Structured Occlusionshttps://arxiv.org/abs/1712.04646-   
 201712Dynamics Transfer GANDynamics Transfer GAN: Generating Video by Transferring Arbitrary Temporal Dynamics from a Source Video to a Single Target Imagehttps://arxiv.org/abs/1712.03534-   
 201712EnergyWGANEnergy-relaxed Wassertein GANs (EnergyWGAN): Towards More Stable and High Resolution Image Generationhttps://arxiv.org/abs/1712.01026-   
 201712ExGANEye In-Painting with Exemplar Generative Adversarial Networkshttps://arxiv.org/abs/1712.03999-   
 201712f-CLSWGANFeature Generating Networks for Zero-Shot Learninghttps://arxiv.org/abs/1712.00981-   
 201712FusionGANLearning to Fuse Music Genres with Generative Adversarial Dual Learninghttps://arxiv.org/abs/1712.01456-   
 201712G2-GANGeometry Guided Adversarial Facial Expression Synthesishttps://arxiv.org/abs/1712.03474-   
 201712GAGANGAGAN: Geometry-Aware Generative Adverserial Networkshttps://arxiv.org/abs/1712.00684-   
 201712GAN-RSTowards Qualitative Advancement of Underwater Machine Vision with Generative Adversarial Networkshttps://arxiv.org/abs/1712.00736-   
 201712GANGGANGs: Generative Adversarial Network Gameshttps://arxiv.org/abs/1712.00679-   
 201712GANosaicGANosaic: Mosaic Creation with Generative Texture Manifoldshttps://arxiv.org/abs/1712.00269-   
 201712IdCycleGANFace Translation between Images and Videos using Identity-aware CycleGANhttps://arxiv.org/abs/1712.00971-   
 201712manifold-WGANManifold-valued Image Generation with Wasserstein Adversarial Networkshttps://arxiv.org/abs/1712.01551-   
 201712MC-GANMulti-Content GAN for Few-Shot Font Style Transferhttps://arxiv.org/abs/1712.00516https://github.com/azadis/MC-GAN916754
 201712MIL-GANMultimodal Storytelling via Generative Adversarial Imitation Learninghttps://arxiv.org/abs/1712.01455-   
 201712MS-GANTemporal Coherency based Criteria for Predicting Video Frames using Deep Multi-stage Generative Adversarial Networkshttp://papers.nips.cc/paper/7014-temporal-coherency-based-criteria-for-predicting-video-frames-using-deep-multi-stage-generative-adversarial-networks-   
 201712PacGANPacGAN: The power of two samples in generative adversarial networkshttps://arxiv.org/abs/1712.04086-   
 201712PN-GANPose-Normalized Image Generation for Person Re-identificationhttps://arxiv.org/abs/1712.02225-   
 201712PPANPrivacy-Preserving Adversarial Networkshttps://arxiv.org/abs/1712.07008-   
 201712RANRAN4IQA: Restorative Adversarial Nets for No-Reference Image Quality Assessmenthttps://arxiv.org/abs/1712.05444    
 201712SGANSGAN: An Alternative Training of Generative Adversarial Networkshttps://arxiv.org/abs/1712.02330-   
 201712SRPGANSRPGAN: Perceptual Generative Adversarial Network for Single Image Super Resolutionhttps://arxiv.org/abs/1712.05927-   
 201712ST-CGANStacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removalhttps://arxiv.org/abs/1712.02478-   
 201712Super-FANSuper-FAN: Integrated facial landmark localization and super-resolution of real-world low resolution faces in arbitrary poses with GANshttps://arxiv.org/abs/1712.02765-   
 201712TV-GANTV-GAN: Generative Adversarial Network Based Thermal to Visible Face Recognitionhttps://arxiv.org/abs/1712.02514-   
 201712UGACHUnsupervised Generative Adversarial Cross-modal Hashinghttps://arxiv.org/abs/1712.00358-   
 201712UV-GANUV-GAN: Adversarial Facial UV Map Completion for Pose-invariant Face Recognitionhttps://arxiv.org/abs/1712.04695-   
 201712VGANText Generation Based on Generative Adversarial Nets with Latent Variablehttps://arxiv.org/abs/1712.00170-   
 201712weGANGenerative Adversarial Nets for Multiple Text Corporahttps://arxiv.org/abs/1712.09127-   
 20181AdvGANGenerating adversarial examples with adversarial networkshttps://arxiv.org/abs/1801.02610-   
 20181CFG-GANComposite Functional Gradient Learning of Generative Adversarial Modelshttps://arxiv.org/abs/1801.06309-   
 20181CipherGANUnsupervised Cipher Cracking Using Discrete GANshttps://arxiv.org/abs/1801.04883-   
 20181Cross-GANCrossing Generative Adversarial Networks for Cross-View Person Re-identificationhttps://arxiv.org/abs/1801.01760-   
 20181dp-GANDifferentially Private Releasing via Deep Generative Modelhttps://arxiv.org/abs/1801.01594-   
 20181ecGANeCommerceGAN : A Generative Adversarial Network for E-commercehttps://arxiv.org/abs/1801.03244-   
 20181FusedGANSemi-supervised FusedGAN for Conditional Image Generationhttps://arxiv.org/abs/1801.05551-   
 20181GeoGANGenerating Instance Segmentation Annotation by Geometry-guided GANhttps://arxiv.org/abs/1801.08839-   
 20181GLCA-GANGlobal and Local Consistent Age Generative Adversarial Networkshttps://arxiv.org/abs/1801.08390-   
 20181LAC-GANGrounded Language Understanding for Manipulation Instructions Using GAN-Based Classificationhttps://arxiv.org/abs/1801.05096-   
 20181MaskGANMaskGAN: Better Text Generation via Filling in the ______https://arxiv.org/abs/1801.07736-   
 20181SG-GANSemantic-aware Grad-GAN for Virtual-to-Real Urban Scene Adaptionhttps://arxiv.org/abs/1801.01726https://github.com/Peilun-Li/SG-GAN5368
 20181SketchyGANSketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesishttps://arxiv.org/abs/1801.02753-   
 20181tempoGANtempoGAN: A Temporally Coherent, Volumetric GAN for Super-resolution Fluid Flowhttps://arxiv.org/abs/1801.09710-   
 20181UGANEnhancing Underwater Imagery using Generative Adversarial Networkshttps://arxiv.org/abs/1801.04011-   
 20182AmbientGANAmbientGAN: Generative models from lossy measurementshttps://openreview.net/forum?id=Hy7fDog0bhttps://github.com/AshishBora/ambient-gan25717
 20182ATA-GANAttention-Aware Generative Adversarial Networks (ATA-GANs)https://arxiv.org/abs/1802.09070-   
 20182C-GANFace Aging with Contextual Generative Adversarial Netshttps://arxiv.org/abs/1802.00237-   
 20182CapsuleGANCapsuleGAN: Generative Adversarial Capsule Networkhttp://arxiv.org/abs/1802.06167-   
 20182DA-GANDA-GAN: Instance-level Image Translation by Deep Attention Generative Adversarial Networks (with Supplementary Materials)http://arxiv.org/abs/1802.06454-   
 20182DP-GANDP-GAN: Diversity-Promoting Generative Adversarial Network for Generating Informative and Diversified Texthttps://arxiv.org/abs/1802.01345-   
 20182DPGANDifferentially Private Generative Adversarial Networkhttp://arxiv.org/abs/1802.06739-   
 20182First Order GANFirst Order Generative Adversarial Networkshttps://arxiv.org/abs/1802.04591https://github.com/zalandoresearch/first_order_gan5237
 20182GC-GANGeometry-Contrastive Generative Adversarial Network for Facial Expression Synthesishttps://arxiv.org/abs/1802.01822-   
 20182LB-GANLoad Balanced GANs for Multi-view Face Image Synthesishttp://arxiv.org/abs/1802.07447-   
 20182MAGANMAGAN: Aligning Biological Manifoldshttps://arxiv.org/abs/1803.00385-   
 20182ND-GANNovelty Detection with GANhttps://arxiv.org/abs/1802.10560-   
 20182PGD-GANSolving Linear Inverse Problems Using GAN Priors: An Algorithm with Provable Guaranteeshttps://arxiv.org/abs/1802.08406-   
 20182RadialGANRadialGAN: Leveraging multiple datasets to improve target-specific predictive models using Generative Adversarial Networkshttp://arxiv.org/abs/1802.06403-   
 20182SAR-GANGenerating High Quality Visible Images from SAR Images Using CNNshttps://arxiv.org/abs/1802.10036-   
 20182SCH-GANSCH-GAN: Semi-supervised Cross-modal Hashing by Generative Adversarial Networkhttps://arxiv.org/abs/1802.02488-   
 20182StainGANStainGAN: Stain Style Transfer for Digital Histological Imageshttps://arxiv.org/abs/1804.01601-   
 20182SWGANSolving Approximate Wasserstein GANs to Stationarityhttps://arxiv.org/abs/1802.08249-   
 20182VoiceGANVoice Impersonation using Generative Adversarial Networkshttp://arxiv.org/abs/1802.06840-   
 20182WaveGANSynthesizing Audio with Generative Adversarial Networkshttps://arxiv.org/abs/1802.04208-   
 20183Attention-GANAttention-GAN for Object Transfiguration in Wild Imageshttps://arxiv.org/abs/1803.06798-   
 20183B-DCGANB-DCGAN:Evaluation of Binarized DCGAN for FPGAhttps://arxiv.org/abs/1803.10930-   
 20183BAGANBAGAN: Data Augmentation with Balancing GANhttps://arxiv.org/abs/1803.09655-   
 20183BranchGANBranched Generative Adversarial Networks for Multi-Scale Image Manifold Learninghttps://arxiv.org/abs/1803.08467-   
 20183D2IA-GANTagging like Humans: Diverse and Distinct Image Annotationhttps://arxiv.org/abs/1804.00113-   
 20183DBLRGANAdversarial Spatio-Temporal Learning for Video Deblurringhttps://arxiv.org/abs/1804.00533-   
 20183E-GANEvolutionary Generative Adversarial Networkshttps://arxiv.org/abs/1803.00657-   
 20183ELEGANTELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face Attributeshttps://arxiv.org/abs/1803.10562-   
 20183Fictitious GANFictitious GAN: Training GANs with Historical Modelshttps://arxiv.org/abs/1803.08647-   
 20183GAANGenerative Adversarial Autoencoder Networkshttps://arxiv.org/abs/1803.08887-   
 20183GONetGONet: A Semi-Supervised Deep Learning Approach For Traversability Estimationhttps://arxiv.org/abs/1803.03254-   
 20183memoryGANMemorization Precedes Generation: Learning Unsupervised GANs with Memory Networkshttps://arxiv.org/abs/1803.01500-   
 20183MTGANMTGAN: Speaker Verification through Multitasking Triplet Generative Adversarial Networkshttps://arxiv.org/abs/1803.09059-   
 20183NCE-GANDihedral angle prediction using generative adversarial networkshttps://arxiv.org/abs/1803.10996-   
 20183NetGANNetGAN: Generating Graphs via Random Walkshttps://arxiv.org/abs/1803.00816-   
 20183OCANOne-Class Adversarial Nets for Fraud Detectionhttps://arxiv.org/abs/1803.01798-   
 20183OT-GANImproving GANs Using Optimal Transporthttps://arxiv.org/abs/1803.05573-   
 20183PGGANPatch-Based Image Inpainting with Generative Adversarial Networkshttps://arxiv.org/abs/1803.07422-   
 20183Sdf-GANSdf-GAN: Semi-supervised Depth Fusion with Multi-scale Adversarial Networkshttps://arxiv.org/abs/1803.06657-   
 20183Social GANSocial GAN: Socially Acceptable Trajectories with Generative Adversarial Networkshttps://arxiv.org/abs/1803.10892-   
 20183Spike-GANSynthesizing realistic neural population activity patterns using Generative Adversarial Networkshttps://arxiv.org/abs/1803.00338-   
 20183ST-GANST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositinghttps://arxiv.org/abs/1803.01837-   
 20183Text2ShapeText2Shape: Generating Shapes from Natural Language by Learning Joint Embeddingshttps://arxiv.org/abs/1803.08495-   
 20183tiny-GANAnalysis of Nonautonomous Adversarial Systemshttps://arxiv.org/abs/1803.05045-   
 20183VOS-GANVOS-GAN: Adversarial Learning of Visual-Temporal Dynamics for Unsupervised Dense Prediction in Videoshttps://arxiv.org/abs/1803.09092-   
 201843D-PhysNet3D-PhysNet: Learning the Intuitive Physics of Non-Rigid Object Deformationshttps://arxiv.org/abs/1805.00328-   
 20184AF-DCGANAF-DCGAN: Amplitude Feature Deep Convolutional GAN for Fingerprint Construction in Indoor Localization Systemhttps://arxiv.org/abs/1804.05347-   
 20184BEAMBoltzmann Encoded Adversarial Machineshttps://arxiv.org/abs/1804.08682-   
 20184CorrGANCorrelated discrete data generation using adversarial traininghttps://arxiv.org/abs/1804.00925-   
 20184D-WCGANI-vector Transformation Using Conditional Generative Adversarial Networks for Short Utterance Speaker Verificationhttps://arxiv.org/abs/1804.00290-   
 20184Defo-NetDefo-Net: Learning Body Deformation using Generative Adversarial Networkshttps://arxiv.org/abs/1804.05928-   
 20184DSH-GANDeep Semantic Hashing with Generative Adversarial Networkshttps://arxiv.org/abs/1804.08275-   
 20184DTR-GANDTR-GAN: Dilated Temporal Relational Adversarial Network for Video Summarizationhttps://arxiv.org/abs/1804.11228-   
 20184DVGANHuman Motion Modeling using DVGANshttps://arxiv.org/abs/1804.10652-   
 20184EARGenerative Model for Heterogeneous Inferencehttps://arxiv.org/abs/1804.09858-   
 20184FBGANFeedback GAN (FBGAN) for DNA: a Novel Feedback-Loop Architecture for Optimizing Protein Functionshttps://arxiv.org/abs/1804.01694-   
 20184FusionGANGenerating a Fusion Image: One's Identity and Another's Shapehttps://arxiv.org/abs/1804.07455-   
 20184Graphical-GANGraphical Generative Adversarial Networkshttps://arxiv.org/abs/1804.03429-   
 20184IterGANIterGANs: Iterative GANs to Learn and Control 3D Object Transformationhttps://arxiv.org/abs/1804.05651-   
 20184M-AAEMask-aware Photorealistic Face Attribute Manipulationhttps://arxiv.org/abs/1804.08882-   
 20184MelanoGANMelanoGANs: High Resolution Skin Lesion Synthesis with GANshttps://arxiv.org/abs/1804.04338-   
 20184MGGANMGGAN: Solving Mode Collapse using Manifold Guided Traininghttps://arxiv.org/abs/1804.04391-   
 20184ModularGANModular Generative Adversarial Networkshttps://arxiv.org/abs/1804.03343-   
 20184NANUnderstanding Humans in Crowded Scenes: Deep Nested Adversarial Learning and A New Benchmark for Multi-Human Parsinghttps://arxiv.org/abs/1804.03287-   
 20184PM-GANPM-GANs: Discriminative Representation Learning for Action Recognition Using Partial-modalitieshttps://arxiv.org/abs/1804.06248-   
 20184ProGanSRA Fully Progressive Approach to Single-Image Super-Resolutionhttps://arxiv.org/abs/1804.02900-   
 20184PS-GANPedestrian-Synthesis-GAN: Generating Pedestrian Data in Real Scene and Beyondhttps://arxiv.org/abs/1804.02047-   
 20184ReConNNReconstruction of Simulation-Based Physical Field with Limited Samples by Reconstruction Neural Networkhttps://arxiv.org/abs/1805.00528-   
 20184SAGAGenerative Adversarial Learning for Spectrum Sensinghttps://arxiv.org/abs/1804.00709-   
 20184sGANGenerative Adversarial Training for MRA Image Synthesis Using Multi-Contrast MRIhttps://arxiv.org/abs/1804.04366-   
 20184Sketcher-Refiner GANLearning Myelin Content in Multiple Sclerosis from Multimodal MRI through Adversarial Traininghttps://arxiv.org/abs/1804.08039-   
 20184SyncGANSyncGAN: Synchronize the Latent Space of Cross-modal Generative Adversarial Networkshttps://arxiv.org/abs/1804.00410-   
 20184TGANs-CTo Create What You Tell: Generating Videos from Captionshttps://arxiv.org/abs/1804.08264-   
 20184UT-SCA-GANSpatial Image Steganography Based on Generative Adversarial Networkhttps://arxiv.org/abs/1804.07939-   
 20185AdvEntuReAdvEntuRe: Adversarial Training for Textual Entailment with Knowledge-Guided Exampleshttps://arxiv.org/abs/1805.04680-   
 20185AVIDAVID: Adversarial Visual Irregularity Detectionhttps://arxiv.org/abs/1805.09521-   
 20185BourGANBourGAN: Generative Networks with Metric Embeddingshttps://arxiv.org/abs/1805.07674-   
 20185BREImproving GAN Training via Binarized Representation Entropy (BRE) Regularizationhttps://arxiv.org/abs/1805.03644https://github.com/BorealisAI/bre-gan372
 20185cd-GANConditional Image-to-Image Translationhttps://arxiv.org/abs/1805.00251-   
 20185cowboyDefending Against Adversarial Attacks by Leveraging an Entire GANhttps://arxiv.org/abs/1805.10652-   
 20185CSGSpeech-Driven Expressive Talking Lips with Conditional Sequential Generative Adversarial Networkshttps://arxiv.org/abs/1806.00154-   
 20185Defense-GANDefense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelshttps://arxiv.org/abs/1805.06605https://github.com/kabkabm/defensegan2358
 20185DialogWAEDialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoderhttps://arxiv.org/abs/1805.12352-   
 20185DTLC-GANGenerative Adversarial Image Synthesis with Decision Tree Latent Controllerhttps://arxiv.org/abs/1805.10603-   
 20185FairGANFairGAN: Fairness-aware Generative Adversarial Networkshttps://arxiv.org/abs/1805.11202-   
 20185Fairness GANFairness GANhttps://arxiv.org/abs/1805.09910-   
 20185FakeGANDetecting Deceptive Reviews using Generative Adversarial Networkshttps://arxiv.org/abs/1805.10364-   
 20185FBGANFeaturized Bidirectional GAN: Adversarial Defense via Adversarially Learned Semantic Inferencehttps://arxiv.org/abs/1805.07862-   
 20185FC-GANFast-converging Conditional Generative Adversarial Networks for Image Synthesishttps://arxiv.org/abs/1805.01972-   
 20185GAFGenerative Adversarial Forests for Better Conditioned Adversarial Learninghttps://arxiv.org/abs/1805.05185-   
 20185GAN Q-learningGAN Q-learninghttps://arxiv.org/abs/1805.04874-   
 20185GAN-SDVirtual-Taobao: Virtualizing Real-world Online Retail Environment for Reinforcement Learninghttps://arxiv.org/abs/1805.10000-   
 20185GAN-Word2VecAdversarial Training of Word2Vec for Basket Completionhttps://arxiv.org/abs/1805.08720-   
 20185GANAXGANAX: A Unified MIMD-SIMD Acceleration for Generative Adversarial Networkshttps://arxiv.org/abs/1806.01107-   
 20185GT-GANDeep Graph Translationhttps://arxiv.org/abs/1805.09980-   
 20185HANBidirectional Learning for Robust Neural Networkshttps://arxiv.org/abs/1805.08006-   
 20185HiGANExploiting Images for Video Recognition with Hierarchical Generative Adversarial Networkshttps://arxiv.org/abs/1805.04384-   
 20185hredGANMulti-turn Dialogue Response Generation in an Adversarial Learning frameworkhttps://arxiv.org/abs/1805.11752-   
 20185MC-GANMC-GAN: Multi-conditional Generative Adversarial Network for Image Synthesishttps://arxiv.org/abs/1805.01123-   
 20185MEGANMEGAN: Mixture of Experts of Generative Adversarial Networks for Multimodal Image Generationhttps://arxiv.org/abs/1805.02481-   
 20185MolGANMolGAN: An implicit generative model for small molecular graphshttps://arxiv.org/abs/1805.11973-   
 20185N2RPPN2RPP: An Adversarial Network to Rebuild Plantar Pressure for ACLD Patientshttps://arxiv.org/abs/1805.02825-   
 20185PD-WGANPrimal-Dual Wasserstein GANhttps://arxiv.org/abs/1805.09575-   
 20185POGANPerceptually Optimized Generative Adversarial Network for Single Image Dehazinghttps://arxiv.org/abs/1805.01084-   
 20185PSGANPSGAN: A Generative Adversarial Network for Remote Sensing Image Pan-Sharpeninghttps://arxiv.org/abs/1805.03371-   
 20185ReGANReGAN: RE[LAX|BAR|INFORCE] based Sequence Generation using GANshttps://arxiv.org/abs/1805.02788https://github.com/TalkToTheGAN/REGAN2242
 20185RegCGANUnpaired Multi-Domain Image Generation via Regularized Conditional GANshttps://arxiv.org/abs/1805.02456-   
 20185RoCGANRobust Conditional Generative Adversarial Networkshttps://arxiv.org/abs/1805.08657-   
 20185SAGANSelf-Attention Generative Adversarial Networkshttps://arxiv.org/abs/1805.08318-   
 20185SG-GANSparsely Grouped Multi-task Generative Adversarial Networks for Facial Attribute Manipulationhttps://arxiv.org/abs/1805.07509-   
 20185speech-driven animation GANEnd-to-End Speech-Driven Facial Animation with Temporal GANshttps://arxiv.org/abs/1805.09313-   
 20185WGAN-CLSText to Image Synthesis Using Generative Adversarial Networkshttps://arxiv.org/abs/1805.00676-   
 20186Adaptive GANCustomizing an Adversarial Example Generator with Class-Conditional GANshttps://arxiv.org/abs/1806.10496-   
 20186APDAdversarial Distillation of Bayesian Neural Network Posteriorshttps://arxiv.org/abs/1806.10317-   
 20186BinGANBinGAN: Learning Compact Binary Descriptors with a Regularized GANhttps://arxiv.org/abs/1806.06778-   
 20186BWGANBanach Wasserstein GANhttps://arxiv.org/abs/1806.06621-   
 20186CapsGANCapsGAN: Using Dynamic Routing for Generative Adversarial Networkshttps://arxiv.org/abs/1806.03968-   
 20186CR-GANCR-GAN: Learning Complete Representations for Multi-view Generationhttps://arxiv.org/abs/1806.11191-   
 20186DMGANDisconnected Manifold Learning for Generative Adversarial Networkshttps://arxiv.org/abs/1806.00880-   
 20186EL-GANEL-GAN: Embedding Loss Driven Generative Adversarial Networks for Lane Detectionhttps://arxiv.org/abs/1806.05525-   
 20186FrankenGANrankenGAN: Guided Detail Synthesis for Building Mass-Models Using Style-Synchonized GANshttps://arxiv.org/abs/1806.07179-   
 20186GAINGAIN: Missing Data Imputation using Generative Adversarial Netshttps://arxiv.org/abs/1806.02920-   
 20186GANGBeyond Local Nash Equilibria for Adversarial Networkshttps://arxiv.org/abs/1806.07268-   
 20186GATSSample-Efficient Deep RL with Generative Adversarial Tree Searchhttps://arxiv.org/abs/1806.05780-   
 20186IR2VIIR2VI: Enhanced Night Environmental Perception by Unsupervised Thermal Image Translationhttps://arxiv.org/abs/1806.09565-   
 20186IRGANGenerative Adversarial Nets for Information Retrieval: Fundamentals and Advanceshttps://arxiv.org/abs/1806.03577-   
 20186JointGANJointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Netshttps://arxiv.org/abs/1806.02978-   
 20186JR-GANJR-GAN: Jacobian Regularization for Generative Adversarial Networkshttps://arxiv.org/abs/1806.09235-   
 20186LCC-GANAdversarial Learning with Local Coordinate Codinghttps://arxiv.org/abs/1806.04895-   
 20186MedGANMedGAN: Medical Image Translation using GANshttps://arxiv.org/abs/1806.06397-   
 20186MMC-GANA Multimodal Classifier Generative Adversarial Network for Carry and Place Tasks from Ambiguous Language Instructionshttps://arxiv.org/abs/1806.03847-   
 20186Modified GAN-CLSGenerate the corresponding Image from Text Description using Modified GAN-CLS Algorithmhttps://arxiv.org/abs/1806.11302-   
 20186PP-GANPrivacy-Protective-GAN for Face De-identificationhttps://arxiv.org/abs/1806.08906-   
 20186SeUDASemantic-Aware Generative Adversarial Nets for Unsupervised Domain Adaptation in Chest X-ray Segmentationhttps://arxiv.org/abs/1806.00600-   
 20186SN-DCGANGenerative Adversarial Networks for Unsupervised Object Co-localizationhttps://arxiv.org/abs/1806.00236-   
 20186SN-PatchGANFree-Form Image Inpainting with Gated Convolutionhttps://arxiv.org/abs/1806.03589-   
 20186SoPhieSoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraintshttps://arxiv.org/abs/1806.01482-   
 20186SR-CNN-VAE-GANSemi-Recurrent CNN-based VAE-GAN for Sequential Data Generationhttps://arxiv.org/abs/1806.00509https://github.com/makbari7/SR-CNN-VAE-GAN283
 20186StarGAN-VCStarGAN-VC: Non-parallel many-to-many voice conversion with star generative adversarial networkshttps://arxiv.org/abs/1806.02169-   
 20186table-GANData Synthesis based on Generative Adversarial Networkshttps://arxiv.org/abs/1806.03384-   
 20186tcGANCross-modal Hallucination for Few-shot Fine-grained Recognitionhttps://arxiv.org/abs/1806.05147-   
 20186TD-GANTask Driven Generative Modeling for Unsupervised Domain Adaptation: Application to X-ray Image Segmentationhttps://arxiv.org/abs/1806.07201-   
 20186tempCycleGANImproving Surgical Training Phantoms by Hyperrealism: Deep Unpaired Image-to-Image Translation from Real Surgerieshttps://arxiv.org/abs/1806.03627-   
 20186VAC+GANVersatile Auxiliary Classifier with Generative Adversarial Network (VAC+GAN), Multi Class Scenarioshttps://arxiv.org/abs/1806.07751-   
 20187acGANOn-line Adaptative Curriculum Learning for GANshttps://arxiv.org/abs/1808.00020-   
 20187AlphaGANAlphaGAN: Generative adversarial networks for natural image mattinghttps://arxiv.org/abs/1807.10088-   
 20187AMC-GANVideo Prediction with Appearance and Motion Conditionshttps://arxiv.org/abs/1807.02635-   
 20187CE-GANDeep Learning for Imbalance Data Classification using Class Expert Generative Adversarial Networkhttps://arxiv.org/abs/1807.04585-   
 20187ciGANConditional Infilling GANs for Data Augmentation in Mammogram Classificationhttps://arxiv.org/abs/1807.08093-   
 20187CT-GANCT-GAN: Conditional Transformation Generative Adversarial Network for Image Attribute Modificationhttps://arxiv.org/abs/1807.04812-   
 20187DE-GANGenerative Adversarial Networks with Decoder-Encoder Output Noisehttps://arxiv.org/abs/1807.03923-   
 20187Dropout-GANDropout-GAN: Learning from a Dynamic Ensemble of Discriminatorshttps://arxiv.org/abs/1807.11346-   
 20187Editable GANEditable Generative Adversarial Networks: Generating and Editing Faces Simultaneouslyhttps://arxiv.org/abs/1807.07700-   
 20187FGGANAdversarial Learning for Fine-grained Image Searchhttps://arxiv.org/abs/1807.02247-   
 20187GAIAGenerative adversarial interpolative autoencoding: adversarial training on latent space interpolations encourage convex latent distributionshttps://arxiv.org/abs/1807.06650-   
 20187GAPGenerative Adversarial Privacyhttps://arxiv.org/abs/1807.05306-   
 20187IntroVAEIntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesishttps://arxiv.org/abs/1807.06358-   
 20187ISGANInvisible Steganography via Generative Adversarial Networkhttps://arxiv.org/abs/1807.08571-   
 20187LBTLearning Implicit Generative Models by Teaching Explicit Oneshttps://arxiv.org/abs/1807.03870-   
 20187LipizzanerTowards Distributed Coevolutionary GANshttps://arxiv.org/abs/1807.08194-   
 20187MIXGANMIXGAN: Learning Concepts from Different Domains for Mixture Generationhttps://arxiv.org/abs/1807.01659-   
 20187PIONEERPioneer Networks: Progressively Growing Generative Autoencoderhttps://arxiv.org/abs/1807.03026-   
 20187RaGANThe relativistic discriminator: a key element missing from standard GANhttps://arxiv.org/abs/1807.00734-   
 20187Resembled GANResembled Generative Adversarial Networks: Two Domains with Similar Attributeshttps://arxiv.org/abs/1807.00947-   
 20187sAOGDeep Structured Generative Modelshttps://arxiv.org/abs/1807.03877-   
 20187Sem-GANSem-GAN: Semantically-Consistent Image-to-Image Translationhttps://arxiv.org/abs/1807.04409-   
 20187SGANCT Image Enhancement Using Stacked Generative Adversarial Networks and Transfer Learning for Lesion Segmentation Improvementhttps://arxiv.org/abs/1807.07144-   
 20187SiGANSiGAN: Siamese Generative Adversarial Network for Identity-Preserving Face Hallucinationhttps://arxiv.org/abs/1807.08370-   
 20187TequilaGANTequilaGAN: How to easily identify GAN sampleshttps://arxiv.org/abs/1807.04919-   
 20187WGAN-L1Subsampled Turbulence Removal Networkhttps://arxiv.org/abs/1807.04418-   
 20188BEGAN-CSEscaping from Collapsing Modes in a Constrained Spacehttps://arxiv.org/abs/1808.07258-   
 20188Bellman GANDistributional Multivariate Policy Evaluation and Exploration with the Bellman GANhttps://arxiv.org/abs/1808.01960-   
 20188BridgeGANGenerative Adversarial Frontal View to Bird View Synthesishttps://arxiv.org/abs/1808.00327-   
 20188DOPINGDOPING: Generative Data Augmentation for Unsupervised Anomaly Detection with GANhttps://arxiv.org/abs/1808.07632-   
 20188GINGenerative Invertible Networks (GIN): Pathophysiology-Interpretable Feature Mapping and Virtual Patient Generationhttps://arxiv.org/abs/1808.04495-   
 20188GM-GANGaussian Mixture Generative Adversarial Networks for Diverse Datasets, and the Unsupervised Clustering of Imageshttps://arxiv.org/abs/1808.10356-   
 20188ISP-GPMInner Space Preserving Generative Pose Machinehttps://arxiv.org/abs/1808.02104-   
 20188MinLGANAnomaly Detection via Minimum Likelihood Generative Adversarial Networkshttps://arxiv.org/abs/1808.00200-   
 20188Recycle-GANRecycle-GAN: Unsupervised Video Retargetinghttps://arxiv.org/abs/1808.05174-   
 20188ScarGANScarGAN: Chained Generative Adversarial Networks to Simulate Pathological Tissue on Cardiovascular MR Scanshttps://arxiv.org/abs/1808.04500-   
 20188Skip-Thought GANGenerating Text through Adversarial Training using Skip-Thought Vectorshttps://arxiv.org/abs/1808.08703-   
 20188StepGANImproving Conditional Sequence Generative Adversarial Networks by Stepwise Evaluationhttps://arxiv.org/abs/1808.05599-   
 20188T2NetT2Net: Synthetic-to-Realistic Translation for Solving Single-Image Depth Estimation Taskshttps://arxiv.org/abs/1808.01454-   
 20188TreeGANTreeGAN: Syntax-Aware Sequence Generation with Generative Adversarial Networkshttps://arxiv.org/abs/1808.07582-   
 20188X-GANsX-GANs: Image Reconstruction Made Easy for Extreme Caseshttps://arxiv.org/abs/1808.04432-   
 20189AE-OTLatent Space Optimal Transport for Generative Modelshttps://arxiv.org/abs/1809.05964-   
 20189AIMGenerating Informative and Diverse Conversational Responses via Adversarial Information Maximizationhttps://arxiv.org/abs/1809.05972-   
 20189Bi-GANAutonomously and Simultaneously Refining Deep Neural Network Parameters by a Bi-Generative Adversarial Network Aided Genetic Algorithmhttps://arxiv.org/abs/1809.10244-   
 20189BubGANBubGAN: Bubble Generative Adversarial Networks for Synthesizing Realistic Bubbly Flow Imageshttps://arxiv.org/abs/1809.02266-   
 20189CinCGANUnsupervised Image Super-Resolution using Cycle-in-Cycle Generative Adversarial Networkshttps://arxiv.org/abs/1809.00437-   
 20189ClusterGANClusterGAN : Latent Space Clustering in Generative Adversarial Networkshttps://arxiv.org/abs/1809.03627-   
 20189DADADADA: Deep Adversarial Data Augmentation for Extremely Low Data Regime Classificationhttps://arxiv.org/abs/1809.00981-   
 20189DeepFDLearning to Detect Fake Face Images in the Wildhttps://arxiv.org/abs/1809.08754-   
 20189ESRGANESRGAN: Enhanced Super-Resolution Generative Adversarial Networkshttps://arxiv.org/abs/1809.00219-   
 20189GAN LabGAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentationhttps://arxiv.org/abs/1809.01587-   
 20189GAN-ADAnomaly Detection with Generative Adversarial Networks for Multivariate Time Serieshttps://arxiv.org/abs/1809.04758-   
 20189GANVOGANVO: Unsupervised Deep Monocular Visual Odometry and Depth Estimation with Generative Adversarial Networkshttps://arxiv.org/abs/1809.05786-   
 20189GcGANGeometry-Consistent Adversarial Networks for One-Sided Unsupervised Domain Mappinghttps://arxiv.org/abs/1809.05852-   
 20189GraphSGANSemi-supervised Learning on Graphs with Generative Adversarial Netshttps://arxiv.org/abs/1809.00130-   
 20189IGMM-GANCoupled IGMM-GANs for deep multimodal anomaly detection in human mobility datahttps://arxiv.org/abs/1809.02728-   
 20189MeRGANMemory Replay GANs: learning to generate images from new categories without forgettinghttps://arxiv.org/abs/1809.02058-   
 20189SAMSample-Efficient Imitation Learning via Generative Adversarial Netshttps://arxiv.org/abs/1809.02064-   
 20189SiftingGANSiftingGAN: Generating and Sifting Labeled Samples to Improve the Remote Sensing Image Scene Classification Baseline in vitrohttps://arxiv.org/abs/1809.04985-   
 20189SLSRSparse Label Smoothing for Semi-supervised Person Re-Identificationhttps://arxiv.org/abs/1809.04976-   
 20189Twin-GANTwin-GAN -- Unpaired Cross-Domain Image Translation with Weight-Sharing GANshttps://arxiv.org/abs/1809.00946-   
 20189WaveletGLCA-GANGlobal and Local Consistent Wavelet-domain Age Synthesishttps://arxiv.org/abs/1809.07764

网址

https://github.com/hindupuravinash/the-gan-zoo

https://github.com/hindupuravinash/the-gan-zoo/blob/master/gans.tsv 

oceanstonetree
关注
  • 0
    点赞
  • 踩
  • 3
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
专栏目录
PyTorch生成对抗网络编程
07-14
PyTorch生成对抗网络编程（畅销书《Python神经网络编程》作者最新力作！用PyTorch构建自己的生成对抗网络） by 塔里克·拉希德
GAN（生成对抗网络）
04-11
GAN（生成对抗网络）+pdf+网络结构+损失函数+公式推导 GAN的基础学习
生成对抗网络（GAN）
sinat_31608641的博客
04-24 1084
生成对抗网络（Generative Adversarial Network，GAN）是一种机器学习模型，由生成器和判别器两部分组成，用于生成逼真的图像、文本或音频等内容。GAN的作用主要包括以下几个方面：图像生成：GAN可以生成高质量的逼真图像，可以应用在图像合成、风格转换、视频生成等领域。数据增强：通过生成对抗网络，可以合成更多的数据样本来增加原始数据集的多样性，提高机器学习模型的泛化能力。
深度学习 - 生成对抗网络
qq_40671063的博客
05-14 4442
GAN、CGAN、InfoGAN、 DCGAN、GAN应用
GAN生成对抗性网络
m0_46928770的博客
02-13 1381
用于判别数据是真实数据还是生成数据(伪数据)的判别模型(判别图像真伪的网络)：输入一张图像，输出代表其为真实图像的概率值，100%即判断该图像是真的。对于G：G希望自己生成的图片越接近真实越好，即G希望D(G(z))尽可能大，V(D, G)会变小，所以对于G是min_G。对于D：D的能力越强，D(x)越大，D(G(x))越小，V(D,G)会变大，所以对于D是求最大max_D。D(x)：D网络判断真实图片是否真实的概率，因为x本来就是真实的，所以该值越接近1越好。2.反向传播阶段—优化目标。
理解生成对抗网络
m0_47199826的博客
04-20 1760
这样，G和D构成了一个动态对抗(或博弈过程)，随着训练(对抗)的进行，G生成的数据越来越接近真实数据，D鉴别数据的水平越来越高。训练完成后，我们得到了一个生成模型G，它可以用来生成以假乱真的数据。它的输入参数是x，x代表数据，输出D(x)代表x为真实数据的概率，如果为1，就代表100%是真实的数据，而输出为0，就代表不可能是真实的数据。这个结果就是我们想要生成的图片，也就是通过学习来的F， 生成器能将一个随机向量的空间映射到训练数据的分布上， 通过一个随机向量能通过映射F生成一个符合训练数据分布的数据。
生成对抗网络GAN
null的专栏
05-06 5983
1. 概述 生成对抗网络GAN（Generative adversarial nets）[1]是由Goodfellow等人于2014年提出的基于深度学习模型的生成框架，可用于多种生成任务。从名称也不难看出，在GAN中包括了两个部分，分别为”生成”和“对抗”，整两个部分也分别对应了两个网络，即生成网络（Generator）GGG和判别网络（Discriminator）DDD，为描述简单，以图像生成为例： 生成网络（Generator）GGG用于生成图片，其输入是一个随机的噪声z\boldsymbol{z}z
生成对抗网络详细介绍
记录 IT 领域经验与见解的博客
05-16 2468
它是由两个不同的神经网络组成的，一个生成器和一个判别器，两个网络通过竞争式学习的方式进行协同训练，以提高生成模型的性能。尽管GANs可能对新手来说有一定的学习曲线，但通过逐步学习和实践，新手也可以掌握生成对抗网络的核心概念和应用。它提供了GAN的全面介绍和基础概念，并深入讨论了GAN的应用和扩展。它对GAN的基本原理进行了详细说明，并展示了如何使用GAN生成高质量的围棋棋局和变强的AI对手。它介绍了医学图像生成、分割和分类等任务中使用GAN的方法，并提供了直观的案例研究和实例。
GAN（生成对抗网络）的系统全面介绍（醍醐灌顶）
热门推荐
m0_61878383的博客
01-18 13万+
本文是关于GAN学习的较为系统全面的介绍，主要针对初学者，希望能够对大家带来帮助。
生成对抗网络---GAN
qq_74722169的博客
01-03 3233
生成式对抗网络（）是一种深度学习模型，014年lan Goodfellow的开篇之作，是近年来复杂分布上无监督学习最具前景的方法之一。模型通过框架中（至少）两个模块：生成模型（Generative Model）和判别模型（Discriminative Model）的互相博弈学习产生相当好的输出。原始 GAN 理论中，并不要求 G 和 D 都是神经网络，只需要是能拟合相应生成和判别的函数即可。但实用中一般均使用深度神经网络作为 G 和 D。GAN在各种领域都有广泛的应用，包括等。
一文读懂对抗生成网络的3种模型
喜欢打酱油的老鸟
01-07 3802
https://www.toutiao.com/i6635851641293636109/   2018-12-17 14:53:28     基于对抗生成网络技术的在线工具edges2cats， 可以为简笔画涂色 前言 在GAN系列课程中分别讲解了对抗生成网络的三种模型，从Goodfellow最初提出的原始的对抗生成网络，到改进型的DC GAN，再到解决了原始GAN存在问题，...
pytorch GAN生成对抗网络实例
09-18
在本文中，我们将深入探讨如何使用PyTorch实现生成对抗网络（GAN）的实例。GAN是一种深度学习模型，由两部分组成：生成器（Generator）和判别器（Discriminator）。生成器尝试创建与训练数据相似的新样本，而判别器...
生成对抗网络（GAN）实例 代码+数据集
04-18
生成对抗网络（GAN）是一种深度学习模型，由Ian Goodfellow在2014年提出，主要用于生成逼真的新样本。GANs的核心是通过两个神经网络——生成器（Generator）和判别器（Discriminator）之间的博弈来学习数据分布。在...
生成对抗网络GAN训练及应用
05-30
生成对抗网络（Generative Adversarial Network，简称GAN），是一种基于深度学习的无监督学习方法，由Ian Goodfellow等人于2014年提出。GAN的核心思想是通过构建两个神经网络——生成器（Generator）和判别器...
chromeforxp.zipchromeforxp.zipchromeforxp.zip
08-04
chromeforxp.zipchromeforxp.zipchromeforxp.zip
shapely-2.0.5-cp311-cp311-win32.whl
最新发布
08-04
shapely-2.0.5-cp311-cp311-win32.whl
[毕业设计]vb+access抽奖系统(系统+论文+开题报告+外文翻译+封面+中英摘要+任务书+中期检查表).zip
08-04
[毕业设计]vb+access抽奖系统(系统+论文+开题报告+外文翻译+封面+中英摘要+任务书+中期检查表)
shapely-2.0.5-cp39-cp39-macosx_10_9_x86_64.whl
08-04
shapely-2.0.5-cp39-cp39-macosx_10_9_x86_64.whl
生成对抗网络(GAN)原理与应用解析
该论文介绍了生成对抗网络（GANs）的概念，这是一种用于估计生成模型的新方法，它通过两个模型之间的对抗性训练来实现：生成模型G和判别模型D。 生成模型G的目标是学习数据的真实分布，以便能够生成看起来像来自...
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值