Deep Learning::Redes Adversárias & Neural Style Transfer

Nesta página vamos tratar de redes neurais convolucionais dirigidas à podução de efeitos artísticos. Temos duas categorias de funções e, conseqüentemente, duas arquiteturas de rede distintas e que usam conseitos distintos:

  1. Transferência de valores de pixels a objetos semanticamente correlatos: Redes Gerativas Adverárias (GANs – Adversarial Generative Networks) e
  2. Transferência de elementos de estilo de uma imagem à outra: Redes para Transferência Neural de Estilos (NST – Neural Style Tranfer)

deep-style6a

GANs e outras Redes Gerativas

As redes gerativas implementam aprendizado não supervisionado, diferentemente dos outros modelos vistos neste site. Divide-se em três grupos:

  • Supõem modelos de probabilidade com densidade explícita e tratável: PixelRNN e PixelCNN (não possuem grande significado prático e não vamos abordar aqui)
  • Supõem modelos de probabilidade com densidade explícita, originalmente intratáveis, mas que possuem solução aproximada através de uma CNN: Autocodificadores Variacionais
  • Supõem modelos de probabilidade com densidade implícitaGANs (Redes Gerativas Adversárias)

Este tipo de rede ficou conhecido por causa de efeitos de transferência de uma imagem sobre outra, usados em aplicações como DeepFake. Adiante um vídeo que demonstra esta capacidade, que foi produzido utilizando-se um Autocodificador Variacional:

 Sobre GANs vamos falar bastate adianre. Aqui um bom resumo de VAEs (assita também a aula da disciplina de Deep Learning de Stanford):

Outra aplicação de GAN é deblurring:

 

animation3
animation4

Tutoriais de GAN

  1. Tutorial básico, em linguagem coloquial,  deixa um pouco a desejar: Towards Data Science – Demystifying Generative Adversarial Networks (Keras + TensorFlow e MNIST)
  2. GAN with Keras: Application to Image Deblurring
  3. Towards Data Science::Your Complete Beginners Guide to Generative Adversarial Networks (ultraresumido…)
  4. Towards Data Science::CycleGAN: Learning to Translate Images (Without Paired Training Data)
  5. CycleGAN & pix2pix: Image-to-Image Translation with Conditional Adversarial Nets (Implementações em TensorFlow, Keras e Chainer)
  6. Towards Data Science::GAN — Ways to improve GAN performance

horse2zebra
 

Links: GANs

  1. Artigo no Git (2018): High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs – Ting-Chun Wang Ming-Yu Liu Jun-Yan Zhu Andrew Tao Jan Kautz1 Bryan Catanzaro
    1. Artigo no arXiv: High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs – Ting-Chun Wang, Ming-Yu Liu, Jun-Yan Zhu, Andrew Tao, Jan Kautz, Bryan Catanzaro 
  2. pix2pixHD – Pytorch implementation of photorealistic image-to-image translation. It can be used for turning semantic label maps into photo-realistic images or synthesizing portraits from face label maps. 
  3. deblur-gan – Keras implementation of the paper DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks – https://github.com/RaphaelMeudec/deblur-gan
  4. DeblurGAN – Pytorch implementation of the paper DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks – https://github.com/KupynOrest/DeblurGAN
  5. Microscope Image Focus Quality Classifierhttps://github.com/google/microscopeimagequality
    1. Paper: Assessing microscope image focus quality with deep learning – https://link.springer.com/content/pdf/10.1186/s12859-018-2087-4.pdf
  6. Paper: Image Quality Assessment Guided Deep Neural Networks Training – https://arxiv.org/pdf/1708.03880.pdf
  7. Tensorflow implementation of pix2pix. Learns a mapping from input images to output images – https://github.com/affinelayer/pix2pix-tensorflow
  8. CycleGAN and pix2pix in PyTorch – https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix
  9. Deephunt::The GAN Zoo – A list of all named GANs! (Material muito completo de Avinash Hindupur com lista comentada muito completa de GANs)
  10. OpenAI::Generative Models – Four projects that share a common theme of enhancing or using generative models
  11. GAN hacks::How to Train a GAN? Tips and tricks to make GANs work
  12. Medium: DOGNET: can an AI model fool a human?
  13. Towards Data Science::Not just another GAN paper — SAGAN (Descreve Self- Attention Generative Adversarial Networks)

Para uma lista das 500+ veja GAN abaixo.

Links: GANs para Superresolução

Outra aplicação de GANs é superresolução: você tem uma imagem ruim e melhora a qualidade dele criando uma imagem artificial usando o resultado informações provenientes do aprendizado da GAN de um outro conjunto de imagens do mesmo tipo (Ground Truths).

  1. Medium::GAN — Super Resolution GAN (SRGAN)
  2. https://github.com/tensorlayer/srgan
  3. Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
  4. ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
  5. Generative adversarial network (GAN) enabled on-chip contact microscopy
  6. Super resolution with Generative Adversarial Networks – Stanford CS231n 2017

Exemplos de Aplicação

  1. Medium::Machine Learning Generated Artwork Auctions Off for $ 432,500
  2. Towards Data Science: Drawing Anime Girls With Deep Learning
  3. neurohive.io::Facial Surface and Texture Synthesis via GAN
  4. goodaudience::Vid2Vid — Conditional GANs for Video-to-Video Synthesis
    1. versão em neurohive.io: https://neurohive.io/en/state-of-the-art/vid2vid-conditional-gans-for-video-to-video-synthesis/
    2. Git::https://tcwang0509.github.io/vid2vid/ (Pytorch)

vid-2-vid

Datasets

  1. GoPro Large

 

Neural Style Transfer

NST é uma técnica onde se trabalha uma imagem de entrada, uma imagem de conteúdo,  e uma imagem de referência de estilo. A imagem de entrada costuma ser, inicialmente, uma cópia da imagem de conteúdo. O objetivo é para iterativamente aplicar o estilo da imagem de referência de estilo à imagem de entrada, gerando uma nova imagem de saída, com o conteúdo da imagem de entrada e o estilo da imagem de referência de estilo.

Os efeitos finais são similares à transferência video-a-video ou iamgem-a-imagem em GANs, mas o princípio envolvido nas CNNs usadas é diferente.

deep-style

O diagrama abaixo mostra  esquematicamente o processo:

NST-1

Nesta rede foi usada uma VGG19 pré-treinada como extrator de características. A animação adiante mostra o processo iterativo de aplicação de estilo:

DST-2

Este conteúdo foi extraído de Turning G.O.T. Characters into White Walkers.

Tutoriais e Explanações de Neural Style Transfer

  1. Neural Style Transfer: A Review (2018) – Yongcheng Jing, Yezhou Yang, Zunlei Feng, Jingwen Ye, Yizhou Yu, Mingli Song
  2. Medium::Turning G.O.T. Characters into White Walkers — Exploring Neural Style Transfer (Tutorial com PyTorch)
  3. Medium::Neural Artistic Style Transfer: A Comprehensive Look (Tutorial com PyTorch)
  4. Medium::Neural Style Transfer: Creating Art with Deep Learning using tf.keras and eager execution (Tutorial com TensorFlow puro)
  5. pyimagesearch::Neural Style Transfer with OpenCV (Tutorial com o pacote DNN do OpenCV)
  6. Towards Data Science::A brief introduction to Neural Style Transfer

Recursos para usar NST Online

  1. Deep Style – Using deep learning for artistic style transfer – A simple, scalable API for machine intelligence
  2. AI Painter – See your photo turned into artwork in seconds! – Neural Network Powered Photo to Painting
  3. deepart.io::Turn your photos into art – Repaint your picture in the style of your favorite artist

Recursos no GitHub e no arXiv

GAN

  1. 3D-ED-GAN – Shape Inpainting using 3D Generative Adversarial Network and Recurrent Convolutional Networks
  2. 3D-GAN – Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling (github)
  3. 3D-IWGAN – Improved Adversarial Systems for 3D Object Generation and Reconstruction (github)
  4. 3D-PhysNet – 3D-PhysNet: Learning the Intuitive Physics of Non-Rigid Object Deformations
  5. 3D-RecGAN – 3D Object Reconstruction from a Single Depth View with Adversarial Learning (github)
  6. ABC-GAN – ABC-GAN: Adaptive Blur and Control for improved training stability of Generative Adversarial Networks (github)
  7. ABC-GAN – GANs for LIFE: Generative Adversarial Networks for Likelihood Free Inference
  8. AC-GAN – Conditional Image Synthesis With Auxiliary Classifier GANs
  9. acGAN – Face Aging With Conditional Generative Adversarial Networks
  10. ACGAN – Coverless Information Hiding Based on Generative adversarial networks
  11. acGAN – On-line Adaptative Curriculum Learning for GANs
  12. ACtuAL – ACtuAL: Actor-Critic Under Adversarial Learning
  13. AdaGAN – AdaGAN: Boosting Generative Models
  14. Adaptive GAN – Customizing an Adversarial Example Generator with Class-Conditional GANs
  15. AdvEntuRe – AdvEntuRe: Adversarial Training for Textual Entailment with Knowledge-Guided Examples
  16. AdvGAN – Generating adversarial examples with adversarial networks
  17. AE-GAN – AE-GAN: adversarial eliminating with GAN
  18. AE-OT – Latent Space Optimal Transport for Generative Models
  19. AEGAN – Learning Inverse Mapping by Autoencoder based Generative Adversarial Nets
  20. AF-DCGAN – AF-DCGAN: Amplitude Feature Deep Convolutional GAN for Fingerprint Construction in Indoor Localization System
  21. AffGAN – Amortised MAP Inference for Image Super-resolution
  22. AIM – Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization
  23. AL-CGAN – Learning to Generate Images of Outdoor Scenes from Attributes and Semantic Layouts
  24. ALI – Adversarially Learned Inference (github)
  25. AlignGAN – AlignGAN: Learning to Align Cross-Domain Images with Conditional Generative Adversarial Networks
  26. AlphaGAN – AlphaGAN: Generative adversarial networks for natural image matting
  27. AM-GAN – Activation Maximization Generative Adversarial Nets
  28. AmbientGAN – AmbientGAN: Generative models from lossy measurements (github)
  29. AMC-GAN – Video Prediction with Appearance and Motion Conditions
  30. AnoGAN – Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery
  31. APD – Adversarial Distillation of Bayesian Neural Network Posteriors
  32. APE-GAN – APE-GAN: Adversarial Perturbation Elimination with GAN
  33. ARAE – Adversarially Regularized Autoencoders for Generating Discrete Structures (github)
  34. ARDA – Adversarial Representation Learning for Domain Adaptation
  35. ARIGAN – ARIGAN: Synthetic Arabidopsis Plants using Generative Adversarial Network
  36. ArtGAN – ArtGAN: Artwork Synthesis with Conditional Categorial GANs
  37. ASDL-GAN – Automatic Steganographic Distortion Learning Using a Generative Adversarial Network
  38. ATA-GAN – Attention-Aware Generative Adversarial Networks (ATA-GANs)
  39. Attention-GAN – Attention-GAN for Object Transfiguration in Wild Images
  40. AttGAN – Arbitrary Facial Attribute Editing: Only Change What You Want (github)
  41. AttnGAN – AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks (github)
  42. AVID – AVID: Adversarial Visual Irregularity Detection
  43. B-DCGAN – B-DCGAN:Evaluation of Binarized DCGAN for FPGA
  44. b-GAN – Generative Adversarial Nets from a Density Ratio Estimation Perspective
  45. BAGAN – BAGAN: Data Augmentation with Balancing GAN
  46. Bayesian GAN – Deep and Hierarchical Implicit Models
  47. Bayesian GAN – Bayesian GAN (github)
  48. BCGAN – Bayesian Conditional Generative Adverserial Networks
  49. BCGAN – Bidirectional Conditional Generative Adversarial networks
  50. BEAM – Boltzmann Encoded Adversarial Machines
  51. BEGAN – BEGAN: Boundary Equilibrium Generative Adversarial Networks
  52. BEGAN-CS – Escaping from Collapsing Modes in a Constrained Space
  53. Bellman GAN – Distributional Multivariate Policy Evaluation and Exploration with the Bellman GAN
  54. BGAN – Binary Generative Adversarial Networks for Image Retrieval (github)
  55. Bi-GAN – Autonomously and Simultaneously Refining Deep Neural Network Parameters by a Bi-Generative Adversarial Network Aided Genetic Algorithm
  56. BicycleGAN – Toward Multimodal Image-to-Image Translation (github)
  57. BiGAN – Adversarial Feature Learning
  58. BinGAN – BinGAN: Learning Compact Binary Descriptors with a Regularized GAN
  59. BourGAN – BourGAN: Generative Networks with Metric Embeddings
  60. BranchGAN – Branched Generative Adversarial Networks for Multi-Scale Image Manifold Learning
  61. BRE – Improving GAN Training via Binarized Representation Entropy (BRE) Regularization (github)
  62. BridgeGAN – Generative Adversarial Frontal View to Bird View Synthesis
  63. BS-GAN – Boundary-Seeking Generative Adversarial Networks
  64. BubGAN – BubGAN: Bubble Generative Adversarial Networks for Synthesizing Realistic Bubbly Flow Images
  65. BWGAN – Banach Wasserstein GAN
  66. C-GAN – Face Aging with Contextual Generative Adversarial Nets
  67. C-RNN-GAN – C-RNN-GAN: Continuous recurrent neural networks with adversarial training (github)
  68. CA-GAN – Composition-aided Sketch-realistic Portrait Generation
  69. CaloGAN – CaloGAN: Simulating 3D High Energy Particle Showers in Multi-Layer Electromagnetic Calorimeters with Generative Adversarial Networks (github)
  70. CAN – CAN: Creative Adversarial Networks, Generating Art by Learning About Styles and Deviating from Style Norms
  71. CapsGAN – CapsGAN: Using Dynamic Routing for Generative Adversarial Networks
  72. CapsuleGAN – CapsuleGAN: Generative Adversarial Capsule Network
  73. CatGAN – Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
  74. CatGAN – CatGAN: Coupled Adversarial Transfer for Domain Generation
  75. CausalGAN – CausalGAN: Learning Causal Implicit Generative Models with Adversarial Training
  76. CC-GAN – Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks (github)
  77. cd-GAN – Conditional Image-to-Image Translation
  78. CDcGAN – Simultaneously Color-Depth Super-Resolution with Conditional Generative Adversarial Network
  79. CE-GAN – Deep Learning for Imbalance Data Classification using Class Expert Generative Adversarial Network
  80. CFG-GAN – Composite Functional Gradient Learning of Generative Adversarial Models
  81. CGAN – Conditional Generative Adversarial Nets
  82. CGAN – Controllable Generative Adversarial Network
  83. Chekhov GAN – An Online Learning Approach to Generative Adversarial Networks
  84. ciGAN – Conditional Infilling GANs for Data Augmentation in Mammogram Classification
  85. CinCGAN – Unsupervised Image Super-Resolution using Cycle-in-Cycle Generative Adversarial Networks
  86. CipherGAN – Unsupervised Cipher Cracking Using Discrete GANs
  87. ClusterGAN – ClusterGAN : Latent Space Clustering in Generative Adversarial Networks
  88. CM-GAN – CM-GANs: Cross-modal Generative Adversarial Networks for Common Representation Learning
  89. CoAtt-GAN – Are You Talking to Me? Reasoned Visual Dialog Generation through Adversarial Learning
  90. CoGAN – Coupled Generative Adversarial Networks
  91. ComboGAN – ComboGAN: Unrestrained Scalability for Image Domain Translation (github)
  92. ConceptGAN – Learning Compositional Visual Concepts with Mutual Consistency
  93. Conditional cycleGAN – Conditional CycleGAN for Attribute Guided Face Image Generation
  94. constrast-GAN – Generative Semantic Manipulation with Contrasting GAN
  95. Context-RNN-GAN – Contextual RNN-GANs for Abstract Reasoning Diagram Generation
  96. CorrGAN – Correlated discrete data generation using adversarial training
  97. Coulomb GAN – Coulomb GANs: Provably Optimal Nash Equilibria via Potential Fields
  98. Cover-GAN – Generative Steganography with Kerckhoffs’ Principle based on Generative Adversarial Networks
  99. cowboy – Defending Against Adversarial Attacks by Leveraging an Entire GAN
  100. CR-GAN – CR-GAN: Learning Complete Representations for Multi-view Generation
  101. Cramèr GAN – The Cramer Distance as a Solution to Biased Wasserstein Gradients
  102. Cross-GAN – Crossing Generative Adversarial Networks for Cross-View Person Re-identification
  103. crVAE-GAN – Channel-Recurrent Variational Autoencoders
  104. CS-GAN – Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets
  105. CSG – Speech-Driven Expressive Talking Lips with Conditional Sequential Generative Adversarial Networks
  106. CT-GAN – CT-GAN: Conditional Transformation Generative Adversarial Network for Image Attribute Modification
  107. CVAE-GAN – CVAE-GAN: Fine-Grained Image Generation through Asymmetric Training
  108. CycleGAN – Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks (github)
  109. D-GAN – Differential Generative Adversarial Networks: Synthesizing Non-linear Facial Variations with Limited Number of Training Data
  110. D-WCGAN – I-vector Transformation Using Conditional Generative Adversarial Networks for Short Utterance Speaker Verification
  111. D2GAN – Dual Discriminator Generative Adversarial Nets
  112. D2IA-GAN – Tagging like Humans: Diverse and Distinct Image Annotation
  113. DA-GAN – DA-GAN: Instance-level Image Translation by Deep Attention Generative Adversarial Networks (with Supplementary Materials)
  114. DADA – DADA: Deep Adversarial Data Augmentation for Extremely Low Data Regime Classification
  115. DAGAN – Data Augmentation Generative Adversarial Networks
  116. DAN – Distributional Adversarial Networks
  117. DBLRGAN – Adversarial Spatio-Temporal Learning for Video Deblurring
  118. DCGAN – Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks (github)
  119. DE-GAN – Generative Adversarial Networks with Decoder-Encoder Output Noise
  120. DeblurGAN – DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks (github)
  121. DeepFD – Learning to Detect Fake Face Images in the Wild
  122. Defense-GAN – Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models (github)
  123. Defo-Net – Defo-Net: Learning Body Deformation using Generative Adversarial Networks
  124. DeliGAN – DeLiGAN : Generative Adversarial Networks for Diverse and Limited Data (github)
  125. DF-GAN – Learning Disentangling and Fusing Networks for Face Completion Under Structured Occlusions
  126. DialogWAE – DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder
  127. DiscoGAN – Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
  128. DistanceGAN – One-Sided Unsupervised Domain Mapping
  129. DM-GAN – Dual Motion GAN for Future-Flow Embedded Video Prediction
  130. DMGAN – Disconnected Manifold Learning for Generative Adversarial Networks
  131. DNA-GAN – DNA-GAN: Learning Disentangled Representations from Multi-Attribute Images
  132. DOPING – DOPING: Generative Data Augmentation for Unsupervised Anomaly Detection with GAN
  133. dp-GAN – Differentially Private Releasing via Deep Generative Model
  134. DP-GAN – DP-GAN: Diversity-Promoting Generative Adversarial Network for Generating Informative and Diversified Text
  135. DPGAN – Differentially Private Generative Adversarial Network
  136. DR-GAN – Representation Learning by Rotating Your Faces
  137. DRAGAN – How to Train Your DRAGAN (github)
  138. Dropout-GAN – Dropout-GAN: Learning from a Dynamic Ensemble of Discriminators
  139. DRPAN – Discriminative Region Proposal Adversarial Networks for High-Quality Image-to-Image Translation
  140. DSH-GAN – Deep Semantic Hashing with Generative Adversarial Networks
  141. DSP-GAN – Depth Structure Preserving Scene Image Generation
  142. DTLC-GAN – Generative Adversarial Image Synthesis with Decision Tree Latent Controller
  143. DTN – Unsupervised Cross-Domain Image Generation
  144. DTR-GAN – DTR-GAN: Dilated Temporal Relational Adversarial Network for Video Summarization
  145. DualGAN – DualGAN: Unsupervised Dual Learning for Image-to-Image Translation
  146. Dualing GAN – Dualing GANs
  147. DVGAN – Human Motion Modeling using DVGANs
  148. Dynamics Transfer GAN – Dynamics Transfer GAN: Generating Video by Transferring Arbitrary Temporal Dynamics from a Source Video to a Single Target Image
  149. E-GAN – Evolutionary Generative Adversarial Networks
  150. EAR – Generative Model for Heterogeneous Inference
  151. EBGAN – Energy-based Generative Adversarial Network
  152. ecGAN – eCommerceGAN : A Generative Adversarial Network for E-commerce
  153. ED//GAN – Stabilizing Training of Generative Adversarial Networks through Regularization
  154. Editable GAN – Editable Generative Adversarial Networks: Generating and Editing Faces Simultaneously
  155. EGAN – Enhanced Experience Replay Generation for Efficient Reinforcement Learning
  156. EL-GAN – EL-GAN: Embedding Loss Driven Generative Adversarial Networks for Lane Detection
  157. ELEGANT – ELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face Attributes
  158. EnergyWGAN – Energy-relaxed Wassertein GANs (EnergyWGAN): Towards More Stable and High Resolution Image Generation
  159. ESRGAN – ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
  160. ExGAN – Eye In-Painting with Exemplar Generative Adversarial Networks
  161. ExposureGAN – Exposure: A White-Box Photo Post-Processing Framework (github)
  162. ExprGAN – ExprGAN: Facial Expression Editing with Controllable Expression Intensity
  163. f-CLSWGAN – Feature Generating Networks for Zero-Shot Learning
  164. f-GAN – f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
  165. FairGAN – FairGAN: Fairness-aware Generative Adversarial Networks
  166. Fairness GAN – Fairness GAN
  167. FakeGAN – Detecting Deceptive Reviews using Generative Adversarial Networks
  168. FBGAN – Feedback GAN (FBGAN) for DNA: a Novel Feedback-Loop Architecture for Optimizing Protein Functions
  169. FBGAN – Featurized Bidirectional GAN: Adversarial Defense via Adversarially Learned Semantic Inference
  170. FC-GAN – Fast-converging Conditional Generative Adversarial Networks for Image Synthesis
  171. FF-GAN – Towards Large-Pose Face Frontalization in the Wild
  172. FGGAN – Adversarial Learning for Fine-grained Image Search
  173. Fictitious GAN – Fictitious GAN: Training GANs with Historical Models
  174. FIGAN – Frame Interpolation with Multi-Scale Deep Loss Functions and Generative Adversarial Networks
  175. Fila-GAN – Synthesizing Filamentary Structured Images with GANs
  176. First Order GAN – First Order Generative Adversarial Networks (github)
  177. Fisher GAN – Fisher GAN
  178. Flow-GAN – Flow-GAN: Bridging implicit and prescribed learning in generative models
  179. FrankenGAN – rankenGAN: Guided Detail Synthesis for Building Mass-Models Using Style-Synchonized GANs
  180. FSEGAN – Exploring Speech Enhancement with Generative Adversarial Networks for Robust Speech Recognition
  181. FTGAN – Hierarchical Video Generation from Orthogonal Information: Optical Flow and Texture
  182. FusedGAN – Semi-supervised FusedGAN for Conditional Image Generation
  183. FusionGAN – Learning to Fuse Music Genres with Generative Adversarial Dual Learning
  184. FusionGAN – Generating a Fusion Image: One’s Identity and Another’s Shape
  185. G2-GAN – Geometry Guided Adversarial Facial Expression Synthesis
  186. GAAN – Generative Adversarial Autoencoder Networks
  187. GAF – Generative Adversarial Forests for Better Conditioned Adversarial Learning
  188. GAGAN – GAGAN: Geometry-Aware Generative Adverserial Networks
  189. GAIA – Generative adversarial interpolative autoencoding: adversarial training on latent space interpolations encourage convex latent distributions
  190. GAIN – GAIN: Missing Data Imputation using Generative Adversarial Nets
  191. GAMN – Generative Adversarial Mapping Networks
  192. GAN – Generative Adversarial Networks (github)
  193. GAN Lab – GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentation
  194. GAN Q-learning – GAN Q-learning
  195. GAN-AD – Anomaly Detection with Generative Adversarial Networks for Multivariate Time Series
  196. GAN-ATV – A Novel Approach to Artistic Textual Visualization via GAN
  197. GAN-CLS – Generative Adversarial Text to Image Synthesis (github)
  198. GAN-RS – Towards Qualitative Advancement of Underwater Machine Vision with Generative Adversarial Networks
  199. GAN-SD – Virtual-Taobao: Virtualizing Real-world Online Retail Environment for Reinforcement Learning
  200. GAN-sep – GANs for Biological Image Synthesis (github)
  201. GAN-VFS – Generative Adversarial Network-based Synthesis of Visible Faces from Polarimetric Thermal Faces
  202. GAN-Word2Vec – Adversarial Training of Word2Vec for Basket Completion
  203. GANAX – GANAX: A Unified MIMD-SIMD Acceleration for Generative Adversarial Networks
  204. GANCS – Deep Generative Adversarial Networks for Compressed Sensing Automates MRI
  205. GANDI – Guiding the search in continuous state-action spaces by learning an action sampling distribution from off-target samples
  206. GANG – GANGs: Generative Adversarial Network Games
  207. GANG – Beyond Local Nash Equilibria for Adversarial Networks
  208. GANosaic – GANosaic: Mosaic Creation with Generative Texture Manifolds
  209. GANVO – GANVO: Unsupervised Deep Monocular Visual Odometry and Depth Estimation with Generative Adversarial Networks
  210. GAP – Context-Aware Generative Adversarial Privacy
  211. GAP – Generative Adversarial Privacy
  212. GATS – Sample-Efficient Deep RL with Generative Adversarial Tree Search
  213. GAWWN – Learning What and Where to Draw (github)
  214. GC-GAN – Geometry-Contrastive Generative Adversarial Network for Facial Expression Synthesis
  215. GcGAN – Geometry-Consistent Adversarial Networks for One-Sided Unsupervised Domain Mapping
  216. GeneGAN – GeneGAN: Learning Object Transfiguration and Attribute Subspace from Unpaired Data (github)
  217. GeoGAN – Generating Instance Segmentation Annotation by Geometry-guided GAN
  218. Geometric GAN – Geometric GAN
  219. GIN – Generative Invertible Networks (GIN): Pathophysiology-Interpretable Feature Mapping and Virtual Patient Generation
  220. GLCA-GAN – Global and Local Consistent Age Generative Adversarial Networks
  221. GM-GAN – Gaussian Mixture Generative Adversarial Networks for Diverse Datasets, and the Unsupervised Clustering of Images
  222. GMAN – Generative Multi-Adversarial Networks
  223. GMM-GAN – Towards Understanding the Dynamics of Generative Adversarial Networks
  224. GoGAN – Gang of GANs: Generative Adversarial Networks with Maximum Margin Ranking
  225. GONet – GONet: A Semi-Supervised Deep Learning Approach For Traversability Estimation
  226. GP-GAN – GP-GAN: Towards Realistic High-Resolution Image Blending (github)
  227. GP-GAN – GP-GAN: Gender Preserving GAN for Synthesizing Faces from Landmarks
  228. GPU – A generative adversarial framework for positive-unlabeled classification
  229. GRAN – Generating images with recurrent adversarial networks (github)
  230. Graphical-GAN – Graphical Generative Adversarial Networks
  231. GraphSGAN – Semi-supervised Learning on Graphs with Generative Adversarial Nets
  232. GraspGAN – Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Grasping
  233. GT-GAN – Deep Graph Translation
  234. HAN – Chinese Typeface Transformation with Hierarchical Adversarial Network
  235. HAN – Bidirectional Learning for Robust Neural Networks
  236. HiGAN – Exploiting Images for Video Recognition with Hierarchical Generative Adversarial Networks
  237. HP-GAN – HP-GAN: Probabilistic 3D human motion prediction via GAN
  238. HR-DCGAN – High-Resolution Deep Convolutional Generative Adversarial Networks
  239. hredGAN – Multi-turn Dialogue Response Generation in an Adversarial Learning framework
  240. IAN – Neural Photo Editing with Introspective Adversarial Networks (github)
  241. IcGAN – Invertible Conditional GANs for image editing (github)
  242. ID-CGAN – Image De-raining Using a Conditional Generative Adversarial Network
  243. IdCycleGAN – Face Translation between Images and Videos using Identity-aware CycleGAN
  244. IFcVAEGAN – Conditional Autoencoders with Adversarial Information Factorization
  245. iGAN – Generative Visual Manipulation on the Natural Image Manifold (github)
  246. IGMM-GAN – Coupled IGMM-GANs for deep multimodal anomaly detection in human mobility data
  247. Improved GAN – Improved Techniques for Training GANs (github)
  248. In2I – In2I : Unsupervised Multi-Image-to-Image Translation Using Generative Adversarial Networks
  249. InfoGAN – InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets (github)
  250. IntroVAE – IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis
  251. IR2VI – IR2VI: Enhanced Night Environmental Perception by Unsupervised Thermal Image Translation
  252. IRGAN – IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval models
  253. IRGAN – Generative Adversarial Nets for Information Retrieval: Fundamentals and Advances
  254. ISGAN – Invisible Steganography via Generative Adversarial Network
  255. ISP-GPM – Inner Space Preserving Generative Pose Machine
  256. Iterative-GAN – Two Birds with One Stone: Iteratively Learn Facial Attributes with GANs (github)
  257. IterGAN – IterGANs: Iterative GANs to Learn and Control 3D Object Transformation
  258. IVE-GAN – IVE-GAN: Invariant Encoding Generative Adversarial Networks
  259. iVGAN – Towards an Understanding of Our World by GANing Videos in the Wild (github)
  260. IWGAN – On Unifying Deep Generative Models
  261. JointGAN – JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets
  262. JR-GAN – JR-GAN: Jacobian Regularization for Generative Adversarial Networks
  263. KBGAN – KBGAN: Adversarial Learning for Knowledge Graph Embeddings
  264. KGAN – KGAN: How to Break The Minimax Game in GAN
  265. l-GAN – Representation Learning and Adversarial Generation of 3D Point Clouds
  266. LAC-GAN – Grounded Language Understanding for Manipulation Instructions Using GAN-Based Classification
  267. LAGAN – Learning Particle Physics by Example: Location-Aware Generative Adversarial Networks for Physics Synthesis
  268. LAPGAN – Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks (github)
  269. LB-GAN – Load Balanced GANs for Multi-view Face Image Synthesis
  270. LBT – Learning Implicit Generative Models by Teaching Explicit Ones
  271. LCC-GAN – Adversarial Learning with Local Coordinate Coding
  272. LD-GAN – Linear Discriminant Generative Adversarial Networks
  273. LDAN – Label Denoising Adversarial Network (LDAN) for Inverse Lighting of Face Images
  274. LeakGAN – Long Text Generation via Adversarial Training with Leaked Information
  275. LeGAN – Likelihood Estimation for Generative Adversarial Networks
  276. LGAN – Global versus Localized Generative Adversarial Nets
  277. Lipizzaner – Towards Distributed Coevolutionary GANs
  278. LR-GAN – LR-GAN: Layered Recursive Generative Adversarial Networks for Image Generation
  279. LS-GAN – Loss-Sensitive Generative Adversarial Networks on Lipschitz Densities
  280. LSGAN – Least Squares Generative Adversarial Networks
  281. M-AAE – Mask-aware Photorealistic Face Attribute Manipulation
  282. MAD-GAN – Multi-Agent Diverse Generative Adversarial Networks
  283. MAGAN – MAGAN: Margin Adaptation for Generative Adversarial Networks
  284. MAGAN – MAGAN: Aligning Biological Manifolds
  285. MalGAN – Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN
  286. MaliGAN – Maximum-Likelihood Augmented Discrete Generative Adversarial Networks
  287. manifold-WGAN – Manifold-valued Image Generation with Wasserstein Adversarial Networks
  288. MARTA-GAN – Deep Unsupervised Representation Learning for Remote Sensing Images
  289. MaskGAN – MaskGAN: Better Text Generation via Filling in the ______
  290. MC-GAN – Multi-Content GAN for Few-Shot Font Style Transfer (github)
  291. MC-GAN – MC-GAN: Multi-conditional Generative Adversarial Network for Image Synthesis
  292. McGAN – McGan: Mean and Covariance Feature Matching GAN
  293. MD-GAN – Learning to Generate Time-Lapse Videos Using Multi-Stage Dynamic Generative Adversarial Networks
  294. MDGAN – Mode Regularized Generative Adversarial Networks
  295. MedGAN – Generating Multi-label Discrete Electronic Health Records using Generative Adversarial Networks
  296. MedGAN – MedGAN: Medical Image Translation using GANs
  297. MEGAN – MEGAN: Mixture of Experts of Generative Adversarial Networks for Multimodal Image Generation
  298. MelanoGAN – MelanoGANs: High Resolution Skin Lesion Synthesis with GANs
  299. memoryGAN – Memorization Precedes Generation: Learning Unsupervised GANs with Memory Networks
  300. MeRGAN – Memory Replay GANs: learning to generate images from new categories without forgetting
  301. MGAN – Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks (github)
  302. MGGAN – Multi-Generator Generative Adversarial Nets
  303. MGGAN – MGGAN: Solving Mode Collapse using Manifold Guided Training
  304. MIL-GAN – Multimodal Storytelling via Generative Adversarial Imitation Learning
  305. MinLGAN – Anomaly Detection via Minimum Likelihood Generative Adversarial Networks
  306. MIX+GAN – Generalization and Equilibrium in Generative Adversarial Nets (GANs)
  307. MIXGAN – MIXGAN: Learning Concepts from Different Domains for Mixture Generation
  308. MLGAN – Metric Learning-based Generative Adversarial Network
  309. MMC-GAN – A Multimodal Classifier Generative Adversarial Network for Carry and Place Tasks from Ambiguous Language Instructions
  310. MMD-GAN – MMD GAN: Towards Deeper Understanding of Moment Matching Network (github)
  311. MMGAN – MMGAN: Manifold Matching Generative Adversarial Network for Generating Images
  312. MoCoGAN – MoCoGAN: Decomposing Motion and Content for Video Generation (github)
  313. Modified GAN-CLS – Generate the corresponding Image from Text Description using Modified GAN-CLS Algorithm
  314. ModularGAN – Modular Generative Adversarial Networks
  315. MolGAN – MolGAN: An implicit generative model for small molecular graphs
  316. MPM-GAN – Message Passing Multi-Agent GANs
  317. MS-GAN – Temporal Coherency based Criteria for Predicting Video Frames using Deep Multi-stage Generative Adversarial Networks
  318. MTGAN – MTGAN: Speaker Verification through Multitasking Triplet Generative Adversarial Networks
  319. MuseGAN – MuseGAN: Symbolic-domain Music Generation and Accompaniment with Multi-track Sequential Generative Adversarial Networks
  320. MV-BiGAN – Multi-view Generative Adversarial Networks
  321. N2RPP – N2RPP: An Adversarial Network to Rebuild Plantar Pressure for ACLD Patients
  322. NAN – Understanding Humans in Crowded Scenes: Deep Nested Adversarial Learning and A New Benchmark for Multi-Human Parsing
  323. NCE-GAN – Dihedral angle prediction using generative adversarial networks
  324. ND-GAN – Novelty Detection with GAN
  325. NetGAN – NetGAN: Generating Graphs via Random Walks
  326. OCAN – One-Class Adversarial Nets for Fraud Detection
  327. OptionGAN – OptionGAN: Learning Joint Reward-Policy Options using Generative Adversarial Inverse Reinforcement Learning
  328. ORGAN – Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models
  329. ORGAN – 3D Reconstruction of Incomplete Archaeological Objects Using a Generative Adversary Network
  330. OT-GAN – Improving GANs Using Optimal Transport
  331. PacGAN – PacGAN: The power of two samples in generative adversarial networks
  332. PAN – Perceptual Adversarial Networks for Image-to-Image Transformation
  333. PassGAN – PassGAN: A Deep Learning Approach for Password Guessing
  334. PD-WGAN – Primal-Dual Wasserstein GAN
  335. Perceptual GAN – Perceptual Generative Adversarial Networks for Small Object Detection
  336. PGAN – Probabilistic Generative Adversarial Networks
  337. PGD-GAN – Solving Linear Inverse Problems Using GAN Priors: An Algorithm with Provable Guarantees
  338. PGGAN – Patch-Based Image Inpainting with Generative Adversarial Networks
  339. PIONEER – Pioneer Networks: Progressively Growing Generative Autoencoder
  340. Pip-GAN – Pipeline Generative Adversarial Networks for Facial Images Generation with Multiple Attributes
  341. pix2pix – Image-to-Image Translation with Conditional Adversarial Networks (github)
  342. pix2pixHD – High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs (github)
  343. PixelGAN – PixelGAN Autoencoders
  344. PM-GAN – PM-GANs: Discriminative Representation Learning for Action Recognition Using Partial-modalities
  345. PN-GAN – Pose-Normalized Image Generation for Person Re-identification
  346. POGAN – Perceptually Optimized Generative Adversarial Network for Single Image Dehazing
  347. Pose-GAN – The Pose Knows: Video Forecasting by Generating Pose Futures
  348. PP-GAN – Privacy-Protective-GAN for Face De-identification
  349. PPAN – Privacy-Preserving Adversarial Networks
  350. PPGN – Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space
  351. PrGAN – 3D Shape Induction from 2D Views of Multiple Objects
  352. ProGanSR – A Fully Progressive Approach to Single-Image Super-Resolution
  353. Progressive GAN – Progressive Growing of GANs for Improved Quality, Stability, and Variation (github)
  354. PS-GAN – Pedestrian-Synthesis-GAN: Generating Pedestrian Data in Real Scene and Beyond
  355. PSGAN – Learning Texture Manifolds with the Periodic Spatial GAN
  356. PSGAN – PSGAN: A Generative Adversarial Network for Remote Sensing Image Pan-Sharpening
  357. PS²-GAN – High-Quality Facial Photo-Sketch Synthesis Using Multi-Adversarial Networks
  358. RadialGAN – RadialGAN: Leveraging multiple datasets to improve target-specific predictive models using Generative Adversarial Networks
  359. RaGAN – The relativistic discriminator: a key element missing from standard GAN
  360. RAN – RAN4IQA: Restorative Adversarial Nets for No-Reference Image Quality Assessment (github)
  361. RankGAN – Adversarial Ranking for Language Generation
  362. RCGAN – Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs
  363. ReConNN – Reconstruction of Simulation-Based Physical Field with Limited Samples by Reconstruction Neural Network
  364. Recycle-GAN – Recycle-GAN: Unsupervised Video Retargeting
  365. RefineGAN – Compressed Sensing MRI Reconstruction with Cyclic Loss in Generative Adversarial Networks
  366. ReGAN – ReGAN: RE[LAX|BAR|INFORCE] based Sequence Generation using GANs (github)
  367. RegCGAN – Unpaired Multi-Domain Image Generation via Regularized Conditional GANs
  368. RenderGAN – RenderGAN: Generating Realistic Labeled Data
  369. Resembled GAN – Resembled Generative Adversarial Networks: Two Domains with Similar Attributes
  370. ResGAN – Generative Adversarial Network based on Resnet for Conditional Image Restoration
  371. RNN-WGAN – Language Generation with Recurrent Generative Adversarial Networks without Pre-training (github)
  372. RoCGAN – Robust Conditional Generative Adversarial Networks
  373. RPGAN – Stabilizing GAN Training with Multiple Random Projections (github)
  374. RTT-GAN – Recurrent Topic-Transition GAN for Visual Paragraph Generation
  375. RWGAN – Relaxed Wasserstein with Applications to GANs
  376. SAD-GAN – SAD-GAN: Synthetic Autonomous Driving using Generative Adversarial Networks
  377. SAGA – Generative Adversarial Learning for Spectrum Sensing
  378. SAGAN – Self-Attention Generative Adversarial Networks
  379. SalGAN – SalGAN: Visual Saliency Prediction with Generative Adversarial Networks (github)
  380. SAM – Sample-Efficient Imitation Learning via Generative Adversarial Nets
  381. sAOG – Deep Structured Generative Models
  382. SAR-GAN – Generating High Quality Visible Images from SAR Images Using CNNs
  383. SBADA-GAN – From source to target and back: symmetric bi-directional adaptive GAN
  384. ScarGAN – ScarGAN: Chained Generative Adversarial Networks to Simulate Pathological Tissue on Cardiovascular MR Scans
  385. SCH-GAN – SCH-GAN: Semi-supervised Cross-modal Hashing by Generative Adversarial Network
  386. SD-GAN – Semantically Decomposing the Latent Spaces of Generative Adversarial Networks
  387. Sdf-GAN – Sdf-GAN: Semi-supervised Depth Fusion with Multi-scale Adversarial Networks
  388. SEGAN – SEGAN: Speech Enhancement Generative Adversarial Network
  389. SeGAN – SeGAN: Segmenting and Generating the Invisible
  390. SegAN – SegAN: Adversarial Network with Multi-scale L1 Loss for Medical Image Segmentation
  391. Sem-GAN – Sem-GAN: Semantically-Consistent Image-to-Image Translation
  392. SeqGAN – SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient (github)
  393. SeUDA – Semantic-Aware Generative Adversarial Nets for Unsupervised Domain Adaptation in Chest X-ray Segmentation
  394. SG-GAN – Semantic-aware Grad-GAN for Virtual-to-Real Urban Scene Adaption (github)
  395. SG-GAN – Sparsely Grouped Multi-task Generative Adversarial Networks for Facial Attribute Manipulation
  396. SGAN – Texture Synthesis with Spatial Generative Adversarial Networks
  397. SGAN – Stacked Generative Adversarial Networks (github)
  398. SGAN – Steganographic Generative Adversarial Networks
  399. SGAN – SGAN: An Alternative Training of Generative Adversarial Networks
  400. SGAN – CT Image Enhancement Using Stacked Generative Adversarial Networks and Transfer Learning for Lesion Segmentation Improvement
  401. sGAN – Generative Adversarial Training for MRA Image Synthesis Using Multi-Contrast MRI
  402. SiftingGAN – SiftingGAN: Generating and Sifting Labeled Samples to Improve the Remote Sensing Image Scene Classification Baseline in vitro
  403. SiGAN – SiGAN: Siamese Generative Adversarial Network for Identity-Preserving Face Hallucination
  404. SimGAN – Learning from Simulated and Unsupervised Images through Adversarial Training
  405. SisGAN – Semantic Image Synthesis via Adversarial Learning
  406. Sketcher-Refiner GAN – Learning Myelin Content in Multiple Sclerosis from Multimodal MRI through Adversarial Training
  407. SketchGAN – Adversarial Training For Sketch Retrieval
  408. SketchyGAN – SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis
  409. Skip-Thought GAN – Generating Text through Adversarial Training using Skip-Thought Vectors
  410. SL-GAN – Semi-Latent GAN: Learning to generate and modify facial images from attributes
  411. SLSR – Sparse Label Smoothing for Semi-supervised Person Re-Identification
  412. SN-DCGAN – Generative Adversarial Networks for Unsupervised Object Co-localization
  413. SN-GAN – Spectral Normalization for Generative Adversarial Networks (github)
  414. SN-PatchGAN – Free-Form Image Inpainting with Gated Convolution
  415. Sobolev GAN – Sobolev GAN
  416. Social GAN – Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks
  417. Softmax GAN – Softmax GAN
  418. SoPhie – SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraints
  419. speech-driven animation GAN – End-to-End Speech-Driven Facial Animation with Temporal GANs
  420. Spike-GAN – Synthesizing realistic neural population activity patterns using Generative Adversarial Networks
  421. Splitting GAN – Class-Splitting Generative Adversarial Networks
  422. SR-CNN-VAE-GAN – Semi-Recurrent CNN-based VAE-GAN for Sequential Data Generation (github)
  423. SRGAN – Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
  424. SRPGAN – SRPGAN: Perceptual Generative Adversarial Network for Single Image Super Resolution
  425. SS-GAN – Semi-supervised Conditional GANs
  426. ss-InfoGAN – Guiding InfoGAN with Semi-Supervision
  427. SSGAN – SSGAN: Secure Steganography Based on Generative Adversarial Networks
  428. SSL-GAN – Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks
  429. ST-CGAN – Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal
  430. ST-GAN – Style Transfer Generative Adversarial Networks: Learning to Play Chess Differently
  431. ST-GAN – ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing
  432. StackGAN – StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks (github)
  433. StainGAN – StainGAN: Stain Style Transfer for Digital Histological Images
  434. StarGAN – StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation (github)
  435. StarGAN-VC – StarGAN-VC: Non-parallel many-to-many voice conversion with star generative adversarial networks
  436. SteinGAN – Learning Deep Energy Models: Contrastive Divergence vs. Amortized MLE
  437. StepGAN – Improving Conditional Sequence Generative Adversarial Networks by Stepwise Evaluation
  438. Super-FAN – Super-FAN: Integrated facial landmark localization and super-resolution of real-world low resolution faces in arbitrary poses with GANs
  439. SVSGAN – SVSGAN: Singing Voice Separation via Generative Adversarial Network
  440. SWGAN – Solving Approximate Wasserstein GANs to Stationarity
  441. SyncGAN – SyncGAN: Synchronize the Latent Space of Cross-modal Generative Adversarial Networks
  442. S^2GAN – Generative Image Modeling using Style and Structure Adversarial Networks
  443. T2Net – T2Net: Synthetic-to-Realistic Translation for Solving Single-Image Depth Estimation Tasks
  444. table-GAN – Data Synthesis based on Generative Adversarial Networks
  445. TAC-GAN – TAC-GAN – Text Conditioned Auxiliary Classifier Generative Adversarial Network (github)
  446. TAN – Outline Colorization through Tandem Adversarial Networks
  447. tcGAN – Cross-modal Hallucination for Few-shot Fine-grained Recognition
  448. TD-GAN – Task Driven Generative Modeling for Unsupervised Domain Adaptation: Application to X-ray Image Segmentation
  449. tempCycleGAN – Improving Surgical Training Phantoms by Hyperrealism: Deep Unpaired Image-to-Image Translation from Real Surgeries
  450. tempoGAN – tempoGAN: A Temporally Coherent, Volumetric GAN for Super-resolution Fluid Flow
  451. TequilaGAN – TequilaGAN: How to easily identify GAN samples
  452. Text2Shape – Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings
  453. textGAN – Generating Text via Adversarial Training
  454. TextureGAN – TextureGAN: Controlling Deep Image Synthesis with Texture Patches
  455. TGAN – Temporal Generative Adversarial Nets
  456. TGAN – Tensorizing Generative Adversarial Nets
  457. TGAN – Tensor-Generative Adversarial Network with Two-dimensional Sparse Coding: Application to Real-time Indoor Localization
  458. TGANs-C – To Create What You Tell: Generating Videos from Captions
  459. tiny-GAN – Analysis of Nonautonomous Adversarial Systems
  460. TP-GAN – Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis
  461. TreeGAN – TreeGAN: Syntax-Aware Sequence Generation with Generative Adversarial Networks
  462. Triple-GAN – Triple Generative Adversarial Nets
  463. tripletGAN – TripletGAN: Training Generative Model with Triplet Loss
  464. TV-GAN – TV-GAN: Generative Adversarial Network Based Thermal to Visible Face Recognition
  465. Twin-GAN – Twin-GAN — Unpaired Cross-Domain Image Translation with Weight-Sharing GANs
  466. UGACH – Unsupervised Generative Adversarial Cross-modal Hashing
  467. UGAN – Enhancing Underwater Imagery using Generative Adversarial Networks
  468. Unim2im – Unsupervised Image-to-Image Translation with Generative Adversarial Networks (github)
  469. UNIT – Unsupervised Image-to-image Translation Networks (github)
  470. Unrolled GAN – Unrolled Generative Adversarial Networks (github)
  471. UT-SCA-GAN – Spatial Image Steganography Based on Generative Adversarial Network
  472. UV-GAN – UV-GAN: Adversarial Facial UV Map Completion for Pose-invariant Face Recognition
  473. VA-GAN – Visual Feature Attribution using Wasserstein GANs
  474. VAC+GAN – Versatile Auxiliary Classifier with Generative Adversarial Network (VAC+GAN), Multi Class Scenarios
  475. VAE-GAN – Autoencoding beyond pixels using a learned similarity metric
  476. VariGAN – Multi-View Image Generation from a Single-View
  477. VAW-GAN – Voice Conversion from Unaligned Corpora using Variational Autoencoding Wasserstein Generative Adversarial Networks
  478. VEEGAN – VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning (github)
  479. VGAN – Generating Videos with Scene Dynamics (github)
  480. VGAN – Generative Adversarial Networks as Variational Training of Energy Based Models (github)
  481. VGAN – Text Generation Based on Generative Adversarial Nets with Latent Variable
  482. ViGAN – Image Generation and Editing with Variational Info Generative Adversarial Networks
  483. VIGAN – VIGAN: Missing View Imputation with Generative Adversarial Networks
  484. VoiceGAN – Voice Impersonation using Generative Adversarial Networks
  485. VOS-GAN – VOS-GAN: Adversarial Learning of Visual-Temporal Dynamics for Unsupervised Dense Prediction in Videos
  486. VRAL – Variance Regularizing Adversarial Learning
  487. WaterGAN – WaterGAN: Unsupervised Generative Network to Enable Real-time Color Correction of Monocular Underwater Images
  488. WaveGAN – Synthesizing Audio with Generative Adversarial Networks
  489. WaveletGLCA-GAN – Global and Local Consistent Wavelet-domain Age Synthesis
  490. weGAN – Generative Adversarial Nets for Multiple Text Corpora
  491. WGAN – Wasserstein GAN (github)
  492. WGAN-CLS – Text to Image Synthesis Using Generative Adversarial Networks
  493. WGAN-GP – Improved Training of Wasserstein GANs (github)
  494. WGAN-L1 – Subsampled Turbulence Removal Network
  495. WS-GAN – Weakly Supervised Generative Adversarial Networks for 3D Reconstruction
  496. X-GANs – X-GANs: Image Reconstruction Made Easy for Extreme Cases
  497. XGAN – XGAN: Unsupervised Image-to-Image Translation for many-to-many Mappings
  498. ZipNet-GAN – ZipNet-GAN: Inferring Fine-grained Mobile Traffic Patterns via a Generative Adversarial Neural Network
  499. α-GAN – Variational Approaches for Auto-Encoding Generative Adversarial Networks (github)
  500. β-GAN – Annealed Generative Adversarial Networks
  501. Δ-GAN – Triangle Generative Adversarial Networks

Copyright © 2018 Aldo von Wangenheim/INCoD/Universidade Federal de Santa Catarina

188
Unique
Visitors
Powered By Google Analytics

Sobre o Autor

possui graduação em Ciências da Computação pela Universidade Federal de Santa Catarina (1989) e Doutorado Acadêmico (Dr. rer.nat.) em Ciências da Computação pela Universidade de Kaiserslautern (1996). Atualmente é professor Associado da Universidade Federal de Santa Catarina, onde é professor do Programa de Pós-graduação em Ciência da Computação e dos cursos de graduação em Ciências da Computação e Sistemas de Informação. É também professor e orientador de doutorado do Programa de Pós-Graduação em Ciências da Computação da Universidade Federal do Paraná - UFPR. Tem experiência nas áreas de Produção de Conteúdo para TV Digital Interativa, Informática em Saúde, Processamento e Análise de Imagens e Engenharia Biomédica, com ênfase em Telemedicina, Telerradiologia, Sistemas de Auxílio ao Diagnóstico por Imagem e Processamento de Imagens Médicas, com foco nos seguintes temas: analise inteligente de imagens, DICOM, CBIR, informática médica, visão computacional e PACS. Coordena o Instituto Nacional de Ciência e Tecnologia para Convergência Digital - INCoD. É também Coordenador Técnico do Sistema Integrado Catarinense de Telemedicina e Telessaúde (STT/SC), coordenador do Grupo de Trabalho Normalização em Telessaúde do Comitê Permanente de Telessaúde/Ministério da Saúde e membro fundador e ex-coordenador da Comissão Informática em Saúde da ABNT - ABNT/CEET 00:001.78. Atualmente também é membro da comissão ISO/TC 215 - Health Informatics. Foi coordenador da RFP6 - Conteúdo - do SBTVD - Sistema Brasileiro de TV Digital/Ministério das Comunicações. Foi o criador e primeiro Coordenador do Núcleo de Telessaúde de Santa Catarina no âmbito do Programa Telessaúde Brasil do Ministério da Saúde e da OPAS - Organização Pan-Americana de Saúde e criador do Núcleo Santa Catarina da RUTE - Rede Universitária de Telemedicina.