生成对抗网络GANs（笔记一）主线

生成式对抗网络（Generative Adversarial Nets, GAN）

一、发展历程：

最开始接触GANs是因为想了解有关于在少量数据的情况下如何做数据增广。然后就了解到了DCGAN生成手写数字的案例，简直是惊为天人，然今才逐渐开始了解生成对抗网络的思想。到了后来一直想用生成对抗网络的思想做语音识别和语音合成这一方面，一直找到合适的资料。再后来，鬼使神差的想结合GANs来做毕业论文，摸摸索索的缓慢向前进发，苦于身边也没有什么人敢这一方面的东西，基本上所有事情都只能靠自己。

这里记录下关于GANs的前世今生：

http://www.lancezhange.com/2015/11/19/adversarial-samples/ 这个博文讲了生成式对抗网络的一个产生过程（姑且看作产生过程）。。。。对抗样本指的是真实样本加上一定的扰动而构成的合成样本，这样的样本看似和真实样本差别不大，但是却可以在通过分类器后产生不同的结果。举例来说，真实样本是一本书，但是对抗样本可能会得到字典的结果。再比如真实样本是一只猴子，但是分类结果可能会是长臂猿。当然，上面的举例或许有不合适的地方，而且我的观点是：实际上，分类模型的能力还涉及到许多的知识，有可能分类模型本身就有可能过拟合或者是欠拟合，谁又能说的准，深度学习的模型本来就是一个黑盒子。

Intriguing properties of neural networks, by Christian Szegedy at Google, et al，2014这篇论文的作者把这个思想对准了深度学习，认为深度学习并没有那么牛逼。其实学术界一直以来都有深度学习，人工智能等方面的争议，有人赞成自然就有人反对，本来很多东西就被吃瓜群众过分夸大了，各种泡沫。这里还想多句嘴：整天吹嘘人工智能的那群人，玩着各种思想，各种的拉投资，早就已经赚得个盆满钵满了。二实际上，真正做出来多少成果，自己心里应该都有点b数。

https://www.kdnuggets.com/2015/07/deep-learning-adversarial-examples-misconceptions.html这里一篇论文有关于对抗样本的一些讲解。主要思想是：深度学习被他们证明受对抗样本的干扰最小；线性模型才是造成分类结果不一致的主要原因，而并非是非线性因素；在数据处理的过程中，因为对抗样本在实际情况中不一定会出现，因此在训练阶段拒绝处理对抗样本要比吧对抗样本错误分类要好，但这个结果并不是让人满意的解决方案；对抗样本的产生不一定要访问模型本身才能做到，可以自己训练；对抗样本上使用正则化并不能有效。

思维上的碰撞会使得理论更加的完善，这一点都不假。人们又开始思考机器和人的视觉真正差异的地方，(Deep Learning’s Deep Flaws)’s Deep Flaws, by Zachary Chase Lipton这篇文章继续分析，对抗样本对深度学习模型的表现不只是在深度学习方面才会有，各种机器学习都不会有100%的分类正确率。这些都推动了模型抗干扰能力方面的研究，而开始引用的博文里面有提到：现在相关领域的论文，无深度，不论文，灌水的太多，随便改一改模型的架构，调一调参数就能发表，结果好了也不知道好的原因。所以对抗样本或许可以用来评价这些模型构架，使得可以用对抗样本来训练，或许可以提高模型的能力，这样，提出了对抗训练的概念（adversarial training），通过这种方式提高模型的鲁棒性。

后来，GoodFellow在Generative Adversarial Networks, by Ian Goodfellow, et al中提出了生成式对抗网络的思想用于对抗训练，对抗训练产生的结果可以产生人眼无法分辨的样本，这算得上是对抗训练的开山之作，现在这篇论文的引用好像都过万了，而且根据谷歌公司的统计，最近两年的等会论文，在GANs方面的论文，数量上都有超过深度学习的趋势。在 GANs 中，包含一个生成模型G和一个判别模型D，D要判别样本是来自G还是真实数据集，而G的目标是生成能够骗过D的对抗样本，可以将G看做假币生产者，而D就是警察，通过G和D的不断交手，彼此的技能都会逐渐提高，最终使得G生产的假币能够以假乱真。后来又有人用拉普拉斯金字塔来构建生成模型，都取得了一定的效果。

但是GANs也有很多的不足之处，论文的作者提到了原始的模型有数据坍塌的问题，会生成很多奇奇怪怪的结果。比如猫有4只眼睛这些问题。之后Conditional generative adversarial nets for convolutional face generation 条件生成对抗网络（CGANs）被提出，对于原始的GAN模式有了比较大的改善。同时期还有很多优秀的论文比如DCGAN，WGAN等这里就不一一列举了。

二、文献跟踪

另外，关于GAN的跟踪请看这里：https://github.com/hindupuravinash/the-gan-zoo列出了各种版本的GANs

• 3D-ED-GAN - Shape Inpainting using 3D Generative Adversarial Network and Recurrent Convolutional Networks
• 3D-GAN - Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling (github)
• 3D-IWGAN - Improved Adversarial Systems for 3D Object Generation and Reconstruction (github)
• 3D-PhysNet - 3D-PhysNet: Learning the Intuitive Physics of Non-Rigid Object Deformations
• 3D-RecGAN - 3D Object Reconstruction from a Single Depth View with Adversarial Learning (github)
• ABC-GAN - ABC-GAN: Adaptive Blur and Control for improved training stability of Generative Adversarial Networks(github)
• ABC-GAN - GANs for LIFE: Generative Adversarial Networks for Likelihood Free Inference
• AC-GAN - Conditional Image Synthesis With Auxiliary Classifier GANs
• acGAN - Face Aging With Conditional Generative Adversarial Networks
• ACGAN - Coverless Information Hiding Based on Generative adversarial networks
• ACtuAL - ACtuAL: Actor-Critic Under Adversarial Learning
• AdaGAN - AdaGAN: Boosting Generative Models
• Adaptive GAN - Customizing an Adversarial Example Generator with Class-Conditional GANs
• AdvEntuRe - AdvEntuRe: Adversarial Training for Textual Entailment with Knowledge-Guided Examples
• AdvGAN - Generating adversarial examples with adversarial networks
• AE-GAN - AE-GAN: adversarial eliminating with GAN
• AEGAN - Learning Inverse Mapping by Autoencoder based Generative Adversarial Nets
• AF-DCGAN - AF-DCGAN: Amplitude Feature Deep Convolutional GAN for Fingerprint Construction in Indoor Localization System
• AffGAN - Amortised MAP Inference for Image Super-resolution
• AL-CGAN - Learning to Generate Images of Outdoor Scenes from Attributes and Semantic Layouts
• ALI - Adversarially Learned Inference (github)
• AlignGAN - AlignGAN: Learning to Align Cross-Domain Images with Conditional Generative Adversarial Networks
• AlphaGAN - AlphaGAN: Generative adversarial networks for natural image matting
• AM-GAN - Activation Maximization Generative Adversarial Nets
• AmbientGAN - AmbientGAN: Generative models from lossy measurements (github)
• AMC-GAN - Video Prediction with Appearance and Motion Conditions
• AnoGAN - Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery
• APD - Adversarial Distillation of Bayesian Neural Network Posteriors
• APE-GAN - APE-GAN: Adversarial Perturbation Elimination with GAN
• ARAE - Adversarially Regularized Autoencoders for Generating Discrete Structures (github)
• ARDA - Adversarial Representation Learning for Domain Adaptation
• ARIGAN - ARIGAN: Synthetic Arabidopsis Plants using Generative Adversarial Network
• ArtGAN - ArtGAN: Artwork Synthesis with Conditional Categorial GANs
• ASDL-GAN - Automatic Steganographic Distortion Learning Using a Generative Adversarial Network
• ATA-GAN - Attention-Aware Generative Adversarial Networks (ATA-GANs)
• Attention-GAN - Attention-GAN for Object Transfiguration in Wild Images
• AttGAN - Arbitrary Facial Attribute Editing: Only Change What You Want (github)
• AttnGAN - AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks (github)
• AVID - AVID: Adversarial Visual Irregularity Detection
• B-DCGAN - B-DCGAN:Evaluation of Binarized DCGAN for FPGA
• b-GAN - Generative Adversarial Nets from a Density Ratio Estimation Perspective
• BAGAN - BAGAN: Data Augmentation with Balancing GAN
• Bayesian GAN - Deep and Hierarchical Implicit Models
• Bayesian GAN - Bayesian GAN (github)
• BCGAN - Bayesian Conditional Generative Adverserial Networks
• BCGAN - Bidirectional Conditional Generative Adversarial networks
• BEAM - Boltzmann Encoded Adversarial Machines
• BEGAN - BEGAN: Boundary Equilibrium Generative Adversarial Networks
• BGAN - Binary Generative Adversarial Networks for Image Retrieval (github)
• BicycleGAN - Toward Multimodal Image-to-Image Translation (github)
• BiGAN - Adversarial Feature Learning
• BinGAN - BinGAN: Learning Compact Binary Descriptors with a Regularized GAN
• BourGAN - BourGAN: Generative Networks with Metric Embeddings
• BranchGAN - Branched Generative Adversarial Networks for Multi-Scale Image Manifold Learning
• BRE - Improving GAN Training via Binarized Representation Entropy (BRE) Regularization (github)
• BS-GAN - Boundary-Seeking Generative Adversarial Networks
• BWGAN - Banach Wasserstein GAN
• C-GAN - Face Aging with Contextual Generative Adversarial Nets
• C-RNN-GAN - C-RNN-GAN: Continuous recurrent neural networks with adversarial training (github)
• CA-GAN - Composition-aided Sketch-realistic Portrait Generation
• CaloGAN - CaloGAN: Simulating 3D High Energy Particle Showers in Multi-Layer Electromagnetic Calorimeters with Generative Adversarial Networks (github)
• CAN - CAN: Creative Adversarial Networks, Generating Art by Learning About Styles and Deviating from Style Norms
• CapsGAN - CapsGAN: Using Dynamic Routing for Generative Adversarial Networks
• CapsuleGAN - CapsuleGAN: Generative Adversarial Capsule Network
• CatGAN - Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
• CatGAN - CatGAN: Coupled Adversarial Transfer for Domain Generation
• CausalGAN - CausalGAN: Learning Causal Implicit Generative Models with Adversarial Training
• CC-GAN - Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks (github)
• cd-GAN - Conditional Image-to-Image Translation
• CDcGAN - Simultaneously Color-Depth Super-Resolution with Conditional Generative Adversarial Network
• CE-GAN - Deep Learning for Imbalance Data Classification using Class Expert Generative Adversarial Network
• CFG-GAN - Composite Functional Gradient Learning of Generative Adversarial Models
• CGAN - Conditional Generative Adversarial Nets
• CGAN - Controllable Generative Adversarial Network
• Chekhov GAN - An Online Learning Approach to Generative Adversarial Networks
• ciGAN - Conditional Infilling GANs for Data Augmentation in Mammogram Classification
• CipherGAN - Unsupervised Cipher Cracking Using Discrete GANs
• CM-GAN - CM-GANs: Cross-modal Generative Adversarial Networks for Common Representation Learning
• CoAtt-GAN - Are You Talking to Me? Reasoned Visual Dialog Generation through Adversarial Learning
• CoGAN - Coupled Generative Adversarial Networks
• ComboGAN - ComboGAN: Unrestrained Scalability for Image Domain Translation (github)
• ConceptGAN - Learning Compositional Visual Concepts with Mutual Consistency
• Conditional cycleGAN - Conditional CycleGAN for Attribute Guided Face Image Generation
• constrast-GAN - Generative Semantic Manipulation with Contrasting GAN
• Context-RNN-GAN - Contextual RNN-GANs for Abstract Reasoning Diagram Generation
• CorrGAN - Correlated discrete data generation using adversarial training
• Coulomb GAN - Coulomb GANs: Provably Optimal Nash Equilibria via Potential Fields
• Cover-GAN - Generative Steganography with Kerckhoffs' Principle based on Generative Adversarial Networks
• cowboy - Defending Against Adversarial Attacks by Leveraging an Entire GAN
• CR-GAN - CR-GAN: Learning Complete Representations for Multi-view Generation
• Cramèr GAN - The Cramer Distance as a Solution to Biased Wasserstein Gradients
• Cross-GAN - Crossing Generative Adversarial Networks for Cross-View Person Re-identification
• crVAE-GAN - Channel-Recurrent Variational Autoencoders
• CS-GAN - Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets
• CSG - Speech-Driven Expressive Talking Lips with Conditional Sequential Generative Adversarial Networks
• CT-GAN - CT-GAN: Conditional Transformation Generative Adversarial Network for Image Attribute Modification
• CVAE-GAN - CVAE-GAN: Fine-Grained Image Generation through Asymmetric Training
• CycleGAN - Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks (github)
• D-GAN - Differential Generative Adversarial Networks: Synthesizing Non-linear Facial Variations with Limited Number of Training Data
• D-WCGAN - I-vector Transformation Using Conditional Generative Adversarial Networks for Short Utterance Speaker Verification
• D2GAN - Dual Discriminator Generative Adversarial Nets
• D2IA-GAN - Tagging like Humans: Diverse and Distinct Image Annotation
• DA-GAN - DA-GAN: Instance-level Image Translation by Deep Attention Generative Adversarial Networks (with Supplementary Materials)
• DAGAN - Data Augmentation Generative Adversarial Networks
• DAN - Distributional Adversarial Networks
• DBLRGAN - Adversarial Spatio-Temporal Learning for Video Deblurring
• DCGAN - Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks (github)
• DE-GAN - Generative Adversarial Networks with Decoder-Encoder Output Noise
• DeblurGAN - DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks (github)
• Defense-GAN - Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models (github)
• Defo-Net - Defo-Net: Learning Body Deformation using Generative Adversarial Networks
• DeliGAN - DeLiGAN : Generative Adversarial Networks for Diverse and Limited Data (github)
• DF-GAN - Learning Disentangling and Fusing Networks for Face Completion Under Structured Occlusions
• DialogWAE - DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder
• DiscoGAN - Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
• DistanceGAN - One-Sided Unsupervised Domain Mapping
• DM-GAN - Dual Motion GAN for Future-Flow Embedded Video Prediction
• DMGAN - Disconnected Manifold Learning for Generative Adversarial Networks
• DNA-GAN - DNA-GAN: Learning Disentangled Representations from Multi-Attribute Images
• dp-GAN - Differentially Private Releasing via Deep Generative Model
• DP-GAN - DP-GAN: Diversity-Promoting Generative Adversarial Network for Generating Informative and Diversified Text
• DPGAN - Differentially Private Generative Adversarial Network
• DR-GAN - Representation Learning by Rotating Your Faces
• DRAGAN - How to Train Your DRAGAN (github)
• Dropout-GAN - Dropout-GAN: Learning from a Dynamic Ensemble of Discriminators
• DRPAN - Discriminative Region Proposal Adversarial Networks for High-Quality Image-to-Image Translation
• DSH-GAN - Deep Semantic Hashing with Generative Adversarial Networks
• DSP-GAN - Depth Structure Preserving Scene Image Generation
• DTLC-GAN - Generative Adversarial Image Synthesis with Decision Tree Latent Controller
• DTN - Unsupervised Cross-Domain Image Generation
• DTR-GAN - DTR-GAN: Dilated Temporal Relational Adversarial Network for Video Summarization
• DualGAN - DualGAN: Unsupervised Dual Learning for Image-to-Image Translation
• Dualing GAN - Dualing GANs
• DVGAN - Human Motion Modeling using DVGANs
• Dynamics Transfer GAN - Dynamics Transfer GAN: Generating Video by Transferring Arbitrary Temporal Dynamics from a Source Video to a Single Target Image
• E-GAN - Evolutionary Generative Adversarial Networks
• EAR - Generative Model for Heterogeneous Inference
• EBGAN - Energy-based Generative Adversarial Network
• ecGAN - eCommerceGAN : A Generative Adversarial Network for E-commerce
• ED//GAN - Stabilizing Training of Generative Adversarial Networks through Regularization
• Editable GAN - Editable Generative Adversarial Networks: Generating and Editing Faces Simultaneously
• EGAN - Enhanced Experience Replay Generation for Efficient Reinforcement Learning
• EL-GAN - EL-GAN: Embedding Loss Driven Generative Adversarial Networks for Lane Detection
• ELEGANT - ELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face Attributes
• EnergyWGAN - Energy-relaxed Wassertein GANs (EnergyWGAN): Towards More Stable and High Resolution Image Generation
• ExGAN - Eye In-Painting with Exemplar Generative Adversarial Networks
• ExposureGAN - Exposure: A White-Box Photo Post-Processing Framework (github)
• ExprGAN - ExprGAN: Facial Expression Editing with Controllable Expression Intensity
• f-CLSWGAN - Feature Generating Networks for Zero-Shot Learning
• f-GAN - f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
• FairGAN - FairGAN: Fairness-aware Generative Adversarial Networks
• Fairness GAN - Fairness GAN
• FakeGAN - Detecting Deceptive Reviews using Generative Adversarial Networks
• FBGAN - Feedback GAN (FBGAN) for DNA: a Novel Feedback-Loop Architecture for Optimizing Protein Functions
• FBGAN - Featurized Bidirectional GAN: Adversarial Defense via Adversarially Learned Semantic Inference
• FC-GAN - Fast-converging Conditional Generative Adversarial Networks for Image Synthesis
• FF-GAN - Towards Large-Pose Face Frontalization in the Wild
• FGGAN - Adversarial Learning for Fine-grained Image Search
• Fictitious GAN - Fictitious GAN: Training GANs with Historical Models
• FIGAN - Frame Interpolation with Multi-Scale Deep Loss Functions and Generative Adversarial Networks
• Fila-GAN - Synthesizing Filamentary Structured Images with GANs
• First Order GAN - First Order Generative Adversarial Networks (github)
• Fisher GAN - Fisher GAN
• Flow-GAN - Flow-GAN: Bridging implicit and prescribed learning in generative models
• FrankenGAN - rankenGAN: Guided Detail Synthesis for Building Mass-Models Using Style-Synchonized GANs
• FSEGAN - Exploring Speech Enhancement with Generative Adversarial Networks for Robust Speech Recognition
• FTGAN - Hierarchical Video Generation from Orthogonal Information: Optical Flow and Texture
• FusedGAN - Semi-supervised FusedGAN for Conditional Image Generation
• FusionGAN - Learning to Fuse Music Genres with Generative Adversarial Dual Learning
• FusionGAN - Generating a Fusion Image: One's Identity and Another's Shape
• G2-GAN - Geometry Guided Adversarial Facial Expression Synthesis
• GAAN - Generative Adversarial Autoencoder Networks
• GAF - Generative Adversarial Forests for Better Conditioned Adversarial Learning
• GAGAN - GAGAN: Geometry-Aware Generative Adverserial Networks
• GAIA - Generative adversarial interpolative autoencoding: adversarial training on latent space interpolations encourage convex latent distributions
• GAIN - GAIN: Missing Data Imputation using Generative Adversarial Nets
• GAMN - Generative Adversarial Mapping Networks
• GAN - Generative Adversarial Networks (github)
• GAN Q-learning - GAN Q-learning
• GAN-ATV - A Novel Approach to Artistic Textual Visualization via GAN
• GAN-CLS - Generative Adversarial Text to Image Synthesis (github)
• GAN-RS - Towards Qualitative Advancement of Underwater Machine Vision with Generative Adversarial Networks
• GAN-SD - Virtual-Taobao: Virtualizing Real-world Online Retail Environment for Reinforcement Learning
• GAN-sep - GANs for Biological Image Synthesis (github)
• GAN-VFS - Generative Adversarial Network-based Synthesis of Visible Faces from Polarimetric Thermal Faces
• GAN-Word2Vec - Adversarial Training of Word2Vec for Basket Completion
• GANAX - GANAX: A Unified MIMD-SIMD Acceleration for Generative Adversarial Networks
• GANCS - Deep Generative Adversarial Networks for Compressed Sensing Automates MRI
• GANDI - Guiding the search in continuous state-action spaces by learning an action sampling distribution from off-target samples
• GANG - GANGs: Generative Adversarial Network Games
• GANG - Beyond Local Nash Equilibria for Adversarial Networks
• GANosaic - GANosaic: Mosaic Creation with Generative Texture Manifolds
• GAP - Context-Aware Generative Adversarial Privacy
• GAP - Generative Adversarial Privacy
• GATS - Sample-Efficient Deep RL with Generative Adversarial Tree Search
• GAWWN - Learning What and Where to Draw (github)
• GC-GAN - Geometry-Contrastive Generative Adversarial Network for Facial Expression Synthesis
• GeneGAN - GeneGAN: Learning Object Transfiguration and Attribute Subspace from Unpaired Data (github)
• GeoGAN - Generating Instance Segmentation Annotation by Geometry-guided GAN
• Geometric GAN - Geometric GAN
• GLCA-GAN - Global and Local Consistent Age Generative Adversarial Networks
• GMAN - Generative Multi-Adversarial Networks
• GMM-GAN - Towards Understanding the Dynamics of Generative Adversarial Networks
• GoGAN - Gang of GANs: Generative Adversarial Networks with Maximum Margin Ranking
• GONet - GONet: A Semi-Supervised Deep Learning Approach For Traversability Estimation
• GP-GAN - GP-GAN: Towards Realistic High-Resolution Image Blending (github)
• GP-GAN - GP-GAN: Gender Preserving GAN for Synthesizing Faces from Landmarks
• GPU - A generative adversarial framework for positive-unlabeled classification
• GRAN - Generating images with recurrent adversarial networks (github)
• Graphical-GAN - Graphical Generative Adversarial Networks
• GraspGAN - Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Grasping
• GT-GAN - Deep Graph Translation
• HAN - Chinese Typeface Transformation with Hierarchical Adversarial Network
• HAN - Bidirectional Learning for Robust Neural Networks
• HiGAN - Exploiting Images for Video Recognition with Hierarchical Generative Adversarial Networks
• HP-GAN - HP-GAN: Probabilistic 3D human motion prediction via GAN
• HR-DCGAN - High-Resolution Deep Convolutional Generative Adversarial Networks
• hredGAN - Multi-turn Dialogue Response Generation in an Adversarial Learning framework
• IAN - Neural Photo Editing with Introspective Adversarial Networks (github)
• IcGAN - Invertible Conditional GANs for image editing (github)
• ID-CGAN - Image De-raining Using a Conditional Generative Adversarial Network
• IdCycleGAN - Face Translation between Images and Videos using Identity-aware CycleGAN
• IFcVAEGAN - Conditional Autoencoders with Adversarial Information Factorization
• iGAN - Generative Visual Manipulation on the Natural Image Manifold (github)
• Improved GAN - Improved Techniques for Training GANs (github)
• In2I - In2I : Unsupervised Multi-Image-to-Image Translation Using Generative Adversarial Networks
• InfoGAN - InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets(github)
• IntroVAE - IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis
• IR2VI - IR2VI: Enhanced Night Environmental Perception by Unsupervised Thermal Image Translation
• IRGAN - IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval models
• IRGAN - Generative Adversarial Nets for Information Retrieval: Fundamentals and Advances
• ISGAN - Invisible Steganography via Generative Adversarial Network
• Iterative-GAN - Two Birds with One Stone: Iteratively Learn Facial Attributes with GANs (github)
• IterGAN - IterGANs: Iterative GANs to Learn and Control 3D Object Transformation
• IVE-GAN - IVE-GAN: Invariant Encoding Generative Adversarial Networks
• iVGAN - Towards an Understanding of Our World by GANing Videos in the Wild (github)
• IWGAN - On Unifying Deep Generative Models
• JointGAN - JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets
• JR-GAN - JR-GAN: Jacobian Regularization for Generative Adversarial Networks
• KBGAN - KBGAN: Adversarial Learning for Knowledge Graph Embeddings
• KGAN - KGAN: How to Break The Minimax Game in GAN
• l-GAN - Representation Learning and Adversarial Generation of 3D Point Clouds
• LAC-GAN - Grounded Language Understanding for Manipulation Instructions Using GAN-Based Classification
• LAGAN - Learning Particle Physics by Example: Location-Aware Generative Adversarial Networks for Physics Synthesis
• LAPGAN - Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks (github)
• LB-GAN - Load Balanced GANs for Multi-view Face Image Synthesis
• LBT - Learning Implicit Generative Models by Teaching Explicit Ones
• LCC-GAN - Adversarial Learning with Local Coordinate Coding
• LD-GAN - Linear Discriminant Generative Adversarial Networks
• LDAN - Label Denoising Adversarial Network (LDAN) for Inverse Lighting of Face Images
• LeakGAN - Long Text Generation via Adversarial Training with Leaked Information
• LeGAN - Likelihood Estimation for Generative Adversarial Networks
• LGAN - Global versus Localized Generative Adversarial Nets
• Lipizzaner - Towards Distributed Coevolutionary GANs
• LR-GAN - LR-GAN: Layered Recursive Generative Adversarial Networks for Image Generation
• LS-GAN - Loss-Sensitive Generative Adversarial Networks on Lipschitz Densities
• LSGAN - Least Squares Generative Adversarial Networks
• M-AAE - Mask-aware Photorealistic Face Attribute Manipulation
• MAD-GAN - Multi-Agent Diverse Generative Adversarial Networks
• MAGAN - MAGAN: Margin Adaptation for Generative Adversarial Networks
• MAGAN - MAGAN: Aligning Biological Manifolds
• MalGAN - Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN
• MaliGAN - Maximum-Likelihood Augmented Discrete Generative Adversarial Networks
• manifold-WGAN - Manifold-valued Image Generation with Wasserstein Adversarial Networks
• MARTA-GAN - Deep Unsupervised Representation Learning for Remote Sensing Images
• MaskGAN - MaskGAN: Better Text Generation via Filling in the ______
• MC-GAN - Multi-Content GAN for Few-Shot Font Style Transfer (github)
• MC-GAN - MC-GAN: Multi-conditional Generative Adversarial Network for Image Synthesis
• McGAN - McGan: Mean and Covariance Feature Matching GAN
• MD-GAN - Learning to Generate Time-Lapse Videos Using Multi-Stage Dynamic Generative Adversarial Networks
• MDGAN - Mode Regularized Generative Adversarial Networks
• MedGAN - Generating Multi-label Discrete Electronic Health Records using Generative Adversarial Networks
• MedGAN - MedGAN: Medical Image Translation using GANs
• MEGAN - MEGAN: Mixture of Experts of Generative Adversarial Networks for Multimodal Image Generation
• MelanoGAN - MelanoGANs: High Resolution Skin Lesion Synthesis with GANs
• memoryGAN - Memorization Precedes Generation: Learning Unsupervised GANs with Memory Networks
• MGAN - Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks (github)
• MGGAN - Multi-Generator Generative Adversarial Nets
• MGGAN - MGGAN: Solving Mode Collapse using Manifold Guided Training
• MIL-GAN - Multimodal Storytelling via Generative Adversarial Imitation Learning
• MIX+GAN - Generalization and Equilibrium in Generative Adversarial Nets (GANs)
• MIXGAN - MIXGAN: Learning Concepts from Different Domains for Mixture Generation
• MLGAN - Metric Learning-based Generative Adversarial Network
• MMC-GAN - A Multimodal Classifier Generative Adversarial Network for Carry and Place Tasks from Ambiguous Language Instructions
• MMD-GAN - MMD GAN: Towards Deeper Understanding of Moment Matching Network (github)
• MMGAN - MMGAN: Manifold Matching Generative Adversarial Network for Generating Images
• MoCoGAN - MoCoGAN: Decomposing Motion and Content for Video Generation (github)
• Modified GAN-CLS - Generate the corresponding Image from Text Description using Modified GAN-CLS Algorithm
• ModularGAN - Modular Generative Adversarial Networks
• MolGAN - MolGAN: An implicit generative model for small molecular graphs
• MPM-GAN - Message Passing Multi-Agent GANs
• MS-GAN - Temporal Coherency based Criteria for Predicting Video Frames using Deep Multi-stage Generative Adversarial Networks
• MTGAN - MTGAN: Speaker Verification through Multitasking Triplet Generative Adversarial Networks
• MuseGAN - MuseGAN: Symbolic-domain Music Generation and Accompaniment with Multi-track Sequential Generative Adversarial Networks
• MV-BiGAN - Multi-view Generative Adversarial Networks
• N2RPP - N2RPP: An Adversarial Network to Rebuild Plantar Pressure for ACLD Patients
• NAN - Understanding Humans in Crowded Scenes: Deep Nested Adversarial Learning and A New Benchmark for Multi-Human Parsing
• NCE-GAN - Dihedral angle prediction using generative adversarial networks
• ND-GAN - Novelty Detection with GAN
• NetGAN - NetGAN: Generating Graphs via Random Walks
• OCAN - One-Class Adversarial Nets for Fraud Detection
• OptionGAN - OptionGAN: Learning Joint Reward-Policy Options using Generative Adversarial Inverse Reinforcement Learning
• ORGAN - Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models
• ORGAN - 3D Reconstruction of Incomplete Archaeological Objects Using a Generative Adversary Network
• OT-GAN - Improving GANs Using Optimal Transport
• PacGAN - PacGAN: The power of two samples in generative adversarial networks
• PAN - Perceptual Adversarial Networks for Image-to-Image Transformation
• PassGAN - PassGAN: A Deep Learning Approach for Password Guessing
• PD-WGAN - Primal-Dual Wasserstein GAN
• Perceptual GAN - Perceptual Generative Adversarial Networks for Small Object Detection
• PGAN - Probabilistic Generative Adversarial Networks
• PGD-GAN - Solving Linear Inverse Problems Using GAN Priors: An Algorithm with Provable Guarantees
• PGGAN - Patch-Based Image Inpainting with Generative Adversarial Networks
• PIONEER - Pioneer Networks: Progressively Growing Generative Autoencoder
• Pip-GAN - Pipeline Generative Adversarial Networks for Facial Images Generation with Multiple Attributes
• pix2pix - Image-to-Image Translation with Conditional Adversarial Networks (github)
• pix2pixHD - High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs (github)
• PixelGAN - PixelGAN Autoencoders
• PM-GAN - PM-GANs: Discriminative Representation Learning for Action Recognition Using Partial-modalities
• PN-GAN - Pose-Normalized Image Generation for Person Re-identification
• POGAN - Perceptually Optimized Generative Adversarial Network for Single Image Dehazing
• Pose-GAN - The Pose Knows: Video Forecasting by Generating Pose Futures
• PP-GAN - Privacy-Protective-GAN for Face De-identification
• PPAN - Privacy-Preserving Adversarial Networks
• PPGN - Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space
• PrGAN - 3D Shape Induction from 2D Views of Multiple Objects
• ProGanSR - A Fully Progressive Approach to Single-Image Super-Resolution
• Progressive GAN - Progressive Growing of GANs for Improved Quality, Stability, and Variation (github)
• PS-GAN - Pedestrian-Synthesis-GAN: Generating Pedestrian Data in Real Scene and Beyond
• PSGAN - Learning Texture Manifolds with the Periodic Spatial GAN
• PSGAN - PSGAN: A Generative Adversarial Network for Remote Sensing Image Pan-Sharpening
• PS²-GAN - High-Quality Facial Photo-Sketch Synthesis Using Multi-Adversarial Networks
• RadialGAN - RadialGAN: Leveraging multiple datasets to improve target-specific predictive models using Generative Adversarial Networks
• RaGAN - The relativistic discriminator: a key element missing from standard GAN
• RAN - RAN4IQA: Restorative Adversarial Nets for No-Reference Image Quality Assessment (github)
• RankGAN - Adversarial Ranking for Language Generation
• RCGAN - Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs
• ReConNN - Reconstruction of Simulation-Based Physical Field with Limited Samples by Reconstruction Neural Network
• RefineGAN - Compressed Sensing MRI Reconstruction with Cyclic Loss in Generative Adversarial Networks
• ReGAN - ReGAN: RE[LAX|BAR|INFORCE] based Sequence Generation using GANs (github)
• RegCGAN - Unpaired Multi-Domain Image Generation via Regularized Conditional GANs
• RenderGAN - RenderGAN: Generating Realistic Labeled Data
• Resembled GAN - Resembled Generative Adversarial Networks: Two Domains with Similar Attributes
• ResGAN - Generative Adversarial Network based on Resnet for Conditional Image Restoration
• RNN-WGAN - Language Generation with Recurrent Generative Adversarial Networks without Pre-training (github)
• RoCGAN - Robust Conditional Generative Adversarial Networks
• RPGAN - Stabilizing GAN Training with Multiple Random Projections (github)
• RTT-GAN - Recurrent Topic-Transition GAN for Visual Paragraph Generation
• RWGAN - Relaxed Wasserstein with Applications to GANs
• SAD-GAN - SAD-GAN: Synthetic Autonomous Driving using Generative Adversarial Networks
• SAGA - Generative Adversarial Learning for Spectrum Sensing
• SAGAN - Self-Attention Generative Adversarial Networks
• SalGAN - SalGAN: Visual Saliency Prediction with Generative Adversarial Networks (github)
• sAOG - Deep Structured Generative Models
• SAR-GAN - Generating High Quality Visible Images from SAR Images Using CNNs
• SBADA-GAN - From source to target and back: symmetric bi-directional adaptive GAN
• SCH-GAN - SCH-GAN: Semi-supervised Cross-modal Hashing by Generative Adversarial Network
• SD-GAN - Semantically Decomposing the Latent Spaces of Generative Adversarial Networks
• Sdf-GAN - Sdf-GAN: Semi-supervised Depth Fusion with Multi-scale Adversarial Networks
• SEGAN - SEGAN: Speech Enhancement Generative Adversarial Network
• SeGAN - SeGAN: Segmenting and Generating the Invisible
• SegAN - SegAN: Adversarial Network with Multi-scale L1 Loss for Medical Image Segmentation
• Sem-GAN - Sem-GAN: Semantically-Consistent Image-to-Image Translation
• SeqGAN - SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient (github)
• SeUDA - Semantic-Aware Generative Adversarial Nets for Unsupervised Domain Adaptation in Chest X-ray Segmentation
• SG-GAN - Semantic-aware Grad-GAN for Virtual-to-Real Urban Scene Adaption (github)
• SG-GAN - Sparsely Grouped Multi-task Generative Adversarial Networks for Facial Attribute Manipulation
• SGAN - Texture Synthesis with Spatial Generative Adversarial Networks
• SGAN - Stacked Generative Adversarial Networks (github)
• SGAN - Steganographic Generative Adversarial Networks
• SGAN - SGAN: An Alternative Training of Generative Adversarial Networks
• SGAN - CT Image Enhancement Using Stacked Generative Adversarial Networks and Transfer Learning for Lesion Segmentation Improvement
• sGAN - Generative Adversarial Training for MRA Image Synthesis Using Multi-Contrast MRI
• SiGAN - SiGAN: Siamese Generative Adversarial Network for Identity-Preserving Face Hallucination
• SimGAN - Learning from Simulated and Unsupervised Images through Adversarial Training
• SisGAN - Semantic Image Synthesis via Adversarial Learning
• Sketcher-Refiner GAN - Learning Myelin Content in Multiple Sclerosis from Multimodal MRI through Adversarial Training
• SketchGAN - Adversarial Training For Sketch Retrieval
• SketchyGAN - SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis
• SL-GAN - Semi-Latent GAN: Learning to generate and modify facial images from attributes
• SN-DCGAN - Generative Adversarial Networks for Unsupervised Object Co-localization
• SN-GAN - Spectral Normalization for Generative Adversarial Networks (github)
• SN-PatchGAN - Free-Form Image Inpainting with Gated Convolution
• Sobolev GAN - Sobolev GAN
• Social GAN - Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks
• Softmax GAN - Softmax GAN
• SoPhie - SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraints
• speech-driven animation GAN - End-to-End Speech-Driven Facial Animation with Temporal GANs
• Spike-GAN - Synthesizing realistic neural population activity patterns using Generative Adversarial Networks
• Splitting GAN - Class-Splitting Generative Adversarial Networks
• SR-CNN-VAE-GAN - Semi-Recurrent CNN-based VAE-GAN for Sequential Data Generation (github)
• SRGAN - Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
• SRPGAN - SRPGAN: Perceptual Generative Adversarial Network for Single Image Super Resolution
• SS-GAN - Semi-supervised Conditional GANs
• ss-InfoGAN - Guiding InfoGAN with Semi-Supervision
• SSGAN - SSGAN: Secure Steganography Based on Generative Adversarial Networks
• SSL-GAN - Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks
• ST-CGAN - Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal
• ST-GAN - Style Transfer Generative Adversarial Networks: Learning to Play Chess Differently
• ST-GAN - ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing
• StackGAN - StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks (github)
• StainGAN - StainGAN: Stain Style Transfer for Digital Histological Images
• StarGAN - StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation (github)
• StarGAN-VC - StarGAN-VC: Non-parallel many-to-many voice conversion with star generative adversarial networks
• SteinGAN - Learning Deep Energy Models: Contrastive Divergence vs. Amortized MLE
• Super-FAN - Super-FAN: Integrated facial landmark localization and super-resolution of real-world low resolution faces in arbitrary poses with GANs
• SVSGAN - SVSGAN: Singing Voice Separation via Generative Adversarial Network
• SWGAN - Solving Approximate Wasserstein GANs to Stationarity
• SyncGAN - SyncGAN: Synchronize the Latent Space of Cross-modal Generative Adversarial Networks
• S^2GAN - Generative Image Modeling using Style and Structure Adversarial Networks
• table-GAN - Data Synthesis based on Generative Adversarial Networks
• TAC-GAN - TAC-GAN - Text Conditioned Auxiliary Classifier Generative Adversarial Network (github)
• TAN - Outline Colorization through Tandem Adversarial Networks
• tcGAN - Cross-modal Hallucination for Few-shot Fine-grained Recognition
• TD-GAN - Task Driven Generative Modeling for Unsupervised Domain Adaptation: Application to X-ray Image Segmentation
• tempCycleGAN - Improving Surgical Training Phantoms by Hyperrealism: Deep Unpaired Image-to-Image Translation from Real Surgeries
• tempoGAN - tempoGAN: A Temporally Coherent, Volumetric GAN for Super-resolution Fluid Flow
• TequilaGAN - TequilaGAN: How to easily identify GAN samples
• Text2Shape - Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings
• textGAN - Generating Text via Adversarial Training
• TextureGAN - TextureGAN: Controlling Deep Image Synthesis with Texture Patches
• TGAN - Temporal Generative Adversarial Nets
• TGAN - Tensorizing Generative Adversarial Nets
• TGAN - Tensor-Generative Adversarial Network with Two-dimensional Sparse Coding: Application to Real-time Indoor Localization
• TGANs-C - To Create What You Tell: Generating Videos from Captions
• tiny-GAN - Analysis of Nonautonomous Adversarial Systems
• TP-GAN - Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis
• Triple-GAN - Triple Generative Adversarial Nets
• tripletGAN - TripletGAN: Training Generative Model with Triplet Loss
• TV-GAN - TV-GAN: Generative Adversarial Network Based Thermal to Visible Face Recognition
• UGACH - Unsupervised Generative Adversarial Cross-modal Hashing
• UGAN - Enhancing Underwater Imagery using Generative Adversarial Networks
• Unim2im - Unsupervised Image-to-Image Translation with Generative Adversarial Networks (github)
• UNIT - Unsupervised Image-to-image Translation Networks (github)
• Unrolled GAN - Unrolled Generative Adversarial Networks (github)
• UT-SCA-GAN - Spatial Image Steganography Based on Generative Adversarial Network
• UV-GAN - UV-GAN: Adversarial Facial UV Map Completion for Pose-invariant Face Recognition
• VA-GAN - Visual Feature Attribution using Wasserstein GANs
• VAC+GAN - Versatile Auxiliary Classifier with Generative Adversarial Network (VAC+GAN), Multi Class Scenarios
• VAE-GAN - Autoencoding beyond pixels using a learned similarity metric
• VariGAN - Multi-View Image Generation from a Single-View
• VAW-GAN - Voice Conversion from Unaligned Corpora using Variational Autoencoding Wasserstein Generative Adversarial Networks
• VEEGAN - VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning (github)
• VGAN - Generating Videos with Scene Dynamics (github)
• VGAN - Generative Adversarial Networks as Variational Training of Energy Based Models (github)
• VGAN - Text Generation Based on Generative Adversarial Nets with Latent Variable
• ViGAN - Image Generation and Editing with Variational Info Generative Adversarial Networks
• VIGAN - VIGAN: Missing View Imputation with Generative Adversarial Networks
• VoiceGAN - Voice Impersonation using Generative Adversarial Networks
• VOS-GAN - VOS-GAN: Adversarial Learning of Visual-Temporal Dynamics for Unsupervised Dense Prediction in Videos
• VRAL - Variance Regularizing Adversarial Learning
• WaterGAN - WaterGAN: Unsupervised Generative Network to Enable Real-time Color Correction of Monocular Underwater Images
• WaveGAN - Synthesizing Audio with Generative Adversarial Networks
• weGAN - Generative Adversarial Nets for Multiple Text Corpora
• WGAN - Wasserstein GAN (github)
• WGAN-CLS - Text to Image Synthesis Using Generative Adversarial Networks
• WGAN-GP - Improved Training of Wasserstein GANs (github)
• WGAN-L1 - Subsampled Turbulence Removal Network
• WS-GAN - Weakly Supervised Generative Adversarial Networks for 3D Reconstruction
• XGAN - XGAN: Unsupervised Image-to-Image Translation for many-to-many Mappings
• ZipNet-GAN - ZipNet-GAN: Inferring Fine-grained Mobile Traffic Patterns via a Generative Adversarial Neural Network
• α-GAN - Variational Approaches for Auto-Encoding Generative Adversarial Networks (github)
• β-GAN - Annealed Generative Adversarial Networks
• Δ-GAN - Triangle Generative Adversarial Networks