生成对抗网络(GAN)是近段时间以来最受研究者关注的机器学习方法之一,深度学习泰斗 Yann LeCun 就曾多次谈到 这种机器学习理念的巨大价值和未来前景。而各类 GAN 的变体也层出不穷,近日机器之心也报道过生成对抗网络的最新进展与论文集,而本文更注重于从 GAN 及其变体的角度对其论文做一个完整的梳理。
项目地址:https://deephunt.in/the-gan-zoo-79597dc8c347
每一周都会有关于 GAN 的新论文出现,你很难对其一一记录,而众多 GAN 的新命名又使其难上加难。如果你想了解更多关于 GAN 的信息,可参阅 OpenAI 一篇有关生成模型的博文,或者 Goodfellow 于 NIPS 2016 所做的生成对抗网络主题演讲。
因此,下面是一个持续更新的最新列表,通过 GAN 名称+论文(并附 arXiv 论文地址)的形式汇总并编排了所有出现的 GAN:
GAN—生成对抗网络(Generative Adversarial Networks):https://arxiv.org/abs/1406.2661
3D-GAN—通过 3D 生成对抗网络建模学习概率性目标形潜在空间(Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling):https://arxiv.org/abs/1610.07584
AdaGAN—AdaGAN:增强生成模型(AdaGAN: Boosting Generative Models):http://arxiv.org/abs/1701.02386v1
AffGAN—图像超分辨率的折旧 MAP 推断(Amortised MAP Inference for Image Super-resolution):https://arxiv.org/abs/1610.04490
ALI—对抗性推断学习(Adversarially Learned Inference):https://arxiv.org/abs/1606.00704
AMGAN—带有最大化激活标注数据的生成对抗网络(Generative Adversarial Nets with Labeled Data by Activation Maximization):http://arxiv.org/abs/1703.02000v1
AnoGAN—使用生成对抗模型的无监督异常检测引导标记的发现(Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery):http://arxiv.org/abs/1703.05921v1
ArtGAN—ArtGAN: 使用条件范畴生成对抗网络合成艺术作品(ArtGAN: Artwork Synthesis with Conditional Categorial GANs):https://arxiv.org/abs/1702.03410
b-GAN—b-GAN: 生成对抗网络的统一架构(b-GAN: Unified Framework of Generative Adversarial Networks):https://openreview.net/pdf?id=S1JG13oee
Bayesian GAN—深度分层隐式模型(Deep and Hierarchical Implicit Models):https://arxiv.org/abs/1702.08896
BEGAN—BEGAN:边界均衡生成对抗网络(BEGAN:Boundary Equilibrium Generative Adversarial Networks):http://arxiv.org/abs/1703.10717v2
BiGAN—对抗性特征学习(Adversarial Feature Learning):http://arxiv.org/abs/1605.09782v7
BS-GAN—边界查找生成对抗网络(Boundary-Seeking Generative Adversarial Networks):http://arxiv.org/abs/1702.08431v1
CGAN—通过条件生成对抗网络实现多样而自然的图像描述(Towards Diverse and Natural Image Descriptions via a Conditional GAN):http://arxiv.org/abs/1703.06029v1
CCGAN—语境条件性生成对抗网络的半监督学习(Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks):https://arxiv.org/abs/1611.06430v1
CatGAN—类属生成对抗网络的无监督和半监督学习(Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks):http://arxiv.org/abs/1511.06390v2
CoGAN—共轭生成对抗网络(Coupled Generative Adversarial Networks):http://arxiv.org/abs/1606.07536v2
Context-RNN-GAN—用于抽象推导图表生成的语境性 RNN-GAN(Contextual RNN-GANs for Abstract Reasoning Diagram Generation):https://arxiv.org/abs/1609.09444
C-RNN-GAN—C-RNN-GAN:对抗训练的连续性循环神经网络(C-RNN-GAN: Continuous recurrent neural networks with adversarial training):https://arxiv.org/abs/1611.09904
CVAE-GAN—CVAE-GAN: 通过非对称训练生成细密纹路的图像(Fine-Grained Image Generation through Asymmetric Training):https://arxiv.org/abs/1703.10155
CycleGAN—使用循环一致性对抗网络进行非成对图到图翻译(Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks):https://arxiv.org/abs/1703.10593
DTN—无监督跨领域图像生成(Unsupervised Cross-Domain Image Generation):https://arxiv.org/abs/1611.02200
DCGAN—使用深度卷积生成对抗网络进行无监督表征学习(Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks):https://arxiv.org/abs/1511.06434
DiscoGAN—使用生成对抗网络学习发现跨领域关系(Learning to Discover Cross-Domain Relations with Generative Adversarial Networks):http://arxiv.org/abs/1703.05192v1
DualGAN—DualGAN: 图到图翻译的无监督对偶学习(Unsupervised Dual Learning for Image-to-Image Translation):http://arxiv.org/abs/1704.02510v1
EBGAN—基于能量的生成对抗网络(Energy-based Generative Adversarial Network):http://arxiv.org/abs/1609.03126v4
f-GAN—f-GAN:使用变分散度最小化训练生成式神经采样器(f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization):https://arxiv.org/abs/1606.00709
GoGAN—Gang of GANs: 使用最大间隔排序的生成对抗网络(Generative Adversarial Networks with Maximum Margin Ranking):https://arxiv.org/abs/1704.04865
GP-GAN—GP-GAN: 走近逼真的高分辨率图像混合(Towards Realistic High-Resolution Image Blending):http://arxiv.org/abs/1703.07195v2
IAN—使用自省的对抗性网络进行神经图像编辑(Neural Photo Editing with Introspective Adversarial Networks):https://arxiv.org/abs/1609.07093
iGAN—在自然图像流形上的生成式视觉操作(Generative Visual Manipulation on the Natural Image Manifold):https://arxiv.org/abs/1609.03552v2
IcGAN—图像编辑的可逆条件生成对抗网络(Invertible Conditional GANs for image editing):https://arxiv.org/abs/1611.06355
ID-CGAN- 使用条件生成对抗网络的图像 De-raining(Image De-raining Using a Conditional Generative Adversarial Network):http://arxiv.org/abs/1701.05957v3
Improved GAN—生成对抗网络训练的改进技术(Improved Techniques for Training GANs):https://arxiv.org/abs/1606.03498
InfoGAN—InfoGAN:信息最大化生成对抗网络的可解释性表征学习(InfoGAN:Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets):http://arxiv.org/abs/1606.03657v1
LR-GAN—LR-GAN:用于图像生成的分层递归生成对抗网络(LR-GAN: Layered Recursive Generative Adversarial Networks for Image Generation):http://arxiv.org/abs/1703.01560v1
LSGAN—最小二乘生成对抗网络(Least Squares Generative Adversarial Networks):http://arxiv.org/abs/1611.04076v3
LS-GAN—利普希茨密度上的损失敏感型生成对抗网络(Loss-Sensitive Generative Adversarial Networks on Lipschitz Densities):http://arxiv.org/abs/1701.06264v5
MGAN—使用马尔可夫过程的生成对抗网络预计算实时纹理合成(Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks):https://arxiv.org/abs/1604.04382
MAGAN—MAGAN: 生成对抗网络的边缘自适应(Margin Adaptation for Generative Adversarial Networks):http://arxiv.org/abs/1704.03817v1
MalGAN—基于生成对抗网络的黑箱攻击的对抗性恶意实例生成(Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN):http://arxiv.org/abs/1702.05983v1
MARTA-GAN—遥感图像的深度无监督表征学习(Deep Unsupervised Representation Learning for Remote Sensing Images):https://arxiv.org/abs/1612.08879
McGAN—McGan: 均值和协方差特征匹配生成对抗网络(Mean and Covariance Feature Matching GAN):http://arxiv.org/abs/1702.08398v1
MedGAN—使用生成对抗网络生成多标注的离散电子健康记录(Generating Multi-label Discrete Electronic Health Records using Generative Adversarial Networks):http://arxiv.org/abs/1703.06490v1
MIX+GAN—生成对抗网络中的泛化与均衡(Generalization and Equilibrium in Generative Adversarial Nets /GANs):https://arxiv.org/abs/1703.00573v3
MPM-GAN—生成对抗网络多智能体的信息传递(Message Passing Multi-Agent GANs):https://arxiv.org/abs/1612.01294
MV-BiGAN—多视角生成对抗网络(Multi-view Generative Adversarial Networks):http://arxiv.org/abs/1611.02019v1
pix2pix—条件对抗网络的图到图翻译(Image-to-Image Translation with Conditional Adversarial Networks):https://arxiv.org/abs/1611.07004
PPGN—即插即用生成网络:在潜在空间中生成条件迭代图像(Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space):https://arxiv.org/abs/1612.00005
PrGAN—从多对象 2D 视角归纳 3D 模型(3D Shape Induction from 2D Views of Multiple Objects):https://arxiv.org/abs/1612.05872
RenderGAN—RenderGAN:生成逼真标注数据(RenderGAN: Generating Realistic Labeled Data):https://arxiv.org/abs/1611.01331
RTT-GAN—可视段落生成的循环主题转换 GAN(Recurrent Topic-Transition GAN for Visual Paragraph Generation):https://arxiv.org/abs/1703.07022v2
SGAN—堆栈 GAN(Stacked Generative Adversarial Networks):https://arxiv.org/abs/1612.04357v4
SGAN—空间 GAN 的纹理合成(Texture Synthesis with Spatial Generative Adversarial Networks):https://arxiv.org/abs/1611.08207
SAD-GAN—SAD-GAN:通过 GAN 合成自动驾驶(SAD-GAN: Synthetic Autonomous Driving using Generative Adversarial Networks):https://arxiv.org/abs/1611.08788v1
SalGAN—SalGAN:通过 GAN 预测视觉显著度(SalGAN: Visual Saliency Prediction with Generative Adversarial Networks):https://arxiv.org/abs/1701.01081v2
SEGAN—SEGAN:语音增强 GAN(SEGAN: Speech Enhancement Generative Adversarial Network):https://arxiv.org/abs/1703.09452v1
SeqGAN—SeqGAN:具有策略梯度的序列 GAN ( SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient):https://arxiv.org/abs/1609.05473v5
SketchGAN—用于草图检索的对抗训练(Adversarial Training For Sketch Retrieval):https://arxiv.org/abs/1607.02748
SL-GAN—半隐 GAN:学习根据属性生成和修改面部图像(Semi-Latent GAN: Learning to generate and modify facial images from attributes):https://arxiv.org/abs/1704.02166
SRGAN—使用一个 GAN 实现图片逼真的单一图像超分辨率(Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network):https://arxiv.org/abs/1609.04802v3
S²GAN—使用风格与结构对抗网络建模生成图像(Generative Image Modeling using Style and Structure Adversarial Networks):https://arxiv.org/abs/1603.05631v2
SSL-GAN—通过语境条件下的 GAN 实现半监督学习(Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks):https://arxiv.org/abs/1611.06430v1
StackGAN—StackGAN:通过堆栈 GAN 合成文本到图片的逼真图像(StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks):https://arxiv.org/abs/1612.03242v1
TGAN—时间 GAN(Temporal Generative Adversarial Nets):https://arxiv.org/abs/1611.06624v1
TAC-GAN—TAC-GAN—文本条件下的辅助生成器 GAN(TAC-GAN—Text Conditioned Auxiliary Classifier Generative Adversarial Network):https://arxiv.org/abs/1703.06412v2
TP-GAN—超越人脸旋转:通过保有正面视图合成打造用于逼真和身份的整体与局部感知 GAN(Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis):https://arxiv.org/abs/1704.04086
Triple-GAN—三重 GAN(Triple Generative Adversarial Nets):https://arxiv.org/abs/1703.02291v2
VGAN—作为能量模型变分训练的 GAN(Generative Adversarial Networks as Variational Training of Energy Based Models):https://arxiv.org/abs/1611.01799
VAE-GAN—使用学习的相似性度量进行超像素自编码(Autoencoding beyond pixels using a learned similarity metric):https://arxiv.org/abs/1512.09300
ViGAN—通过变分信息 GAN 生成和编辑图像(Image Generation and Editing with Variational Info Generative AdversarialNetworks):https://arxiv.org/abs/1701.04568v1
WGAN—Wasserstein GAN:https://arxiv.org/abs/1701.07875v2
WGAN-GP—Wasserstein GAN 的改进训练(Improved Training of Wasserstein GANs):https://arxiv.org/abs/1704.00028
WaterGAN—WaterGAN:实时校正单目水下图像色彩的无监督生成网络(WaterGAN: Unsupervised Generative Network to Enable Real-time Color Correction of Monocular Underwater Images):https://arxiv.org/abs/1702.07392v1
机器之心报道 GAN 相关文章