Generative Adversarial Network
|
|
- Steven Ryan
- 5 years ago
- Views:
Transcription
1 Generative Adversarial Network Many slides from NIPS 2014 Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio
2 Generative adversarial networks New method of training deep generative models Idea: pit a generator and a discriminator against each other Generator tries to draw samples from P(X) Discriminator tries to tell if sample came from the generator or t he real world Both discriminator and generator are deep networks (differentia ble functions) Can train with backprop: train discriminator for a while, then trai n generator, then discriminator, 2
3 Generative? Data: Discriminative model: p D x; θ D Generative model: p G x; θ G True data distribution: p data (x) Train p G x p data (x) p data (x) 3
4 Generative Adversarial Network Counterfeiters vs Police Game IT S FAKE MONEY! IT S REAL MONEY! 4
5 5
6 Generative Adversarial Network Discriminative Model D Generative Model G Sample x Random noise z p(z) 6
7 Generative Adversarial Network Discriminative Model D: tries to distinguish between samples from real data p(x) and generated ones q(x). 1 0 Try to classify the sample x D(x)=0 when x from Data D(x)=1 when x from G Differentiable function represented by a multilayer perceptron with parameters sample x from data sample x from G Generative Model G Try to generate sample x As similar as the real data random noise z p(z) 7
8 8
9 9
10 10
11 11
12 To learn the G s distribution p g over data x, we define a prior on input noise variables p z (z) Represent a mapping to data space as G(z; θ g ) whre G is a differ entiable function (MLP) A second multilayer perceptron D(x; θ d ) that outputs a single sc alar. D(x) represents the probability that x came from the data rather than p g We train D to maximize the probability of assigning the correct l abel to both training example and samples from G. We simultaneously train G to minimize log 1 D(G z ) D and G play the following 2-player minimax game with value fu nction V(G,D): 12
13 Generative Adversarial Network V D, G = E x~pdata(x) log D x min max V D, G G D + E z~pz(z) log(1 D(G(z))) Discriminative Model D 1 0 Generative Model G random noise z p(z) 13
14 Generative Adversarial Network V D, G = E x~pdata(x) log D x min max V D, G G D + E z~pz(z) log(1 D(G(z))) Discriminative Model D 1 0 Fixed G, maximize V: max D V G D = max D E x~pdata(x) log D x From sample x (i), z (i) max D m i=1 log D x i + E z~pz(z) log(1 D(G(z))) + log 1 D G z i Binary Classification (logistic loss): Sample from data: label=1 Sample from generator: label = 0 Generative Model G Stochastic Gradient random noise z p(z) 14
15 Generative Adversarial Network V D, G = E x~pdata(x) log D x min max V D, G G D + E z~pz(z) log(1 D(G(z))) Discriminative Model D 1 0 Fixed D, minimize V(G): min G V D G = min E z~pz(z) log(1 D(G(z))) Try to make D(G(z)) = 1 Generative Model G Stochastic Gradient random noise z p(z) 15
16 Generative Adversarial Network Update D Update G 16
17 GAN Results Nearest training example Generated Samples 17
18 Slide credit: Sangdoo (pil.snu.ac.kr) Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Network, ICLR Alec Radford, Luke Metz and Soumith Chintala 18
19 DCGAN Deep Convolutional Network + GAN Tricks for stable training Experimental Analysis Discriminative Model D 1 0 Generative Model G random noise z p(z) 19
20 Discriminative Model D DCGAN 1 0 Replace model s network to CNN Example of generator G (same as D) Generative Model G random noise z p(z) z: uniform dist. 20
21 Experiments LSUN bedroom dataset 3 million training examples Epoch #1 Epoch #5 21
22 Experiments Input noise z Interpolation form z i to z j z i z j 22
23 Experiments Which activations(feature map) in CNN has representation of window? At feature activations, assign neuron in the window region is 1, otherwise 0. Logistic regression to find window-representative feature map. Window feature map removal 23
24 Experiments Faces scraped human face image from web 3 million images from 10,000 people. Vector arithmetic 24
25 Experiments 25
26 Slide credit: Sangdoo (pil.snu.ac.kr) Generative Adversarial Text to Image Synthesis, ICML Scott Reed*, Zeynep Akata**, Xinchen Yan*, Lajanugen Logeswaran*, Bernt Schiele**, Honglak Lee* * University of Michigan, Ann Arbor, MI, USA (UMICH.EDU) ** Max Planck Institute for Informatics, Saarbrucken, Germany (MPI- INF.MPG.DE) 26
27 Generative Adversarial Text to Image Synthesis 27
28 Generative model What I cannot create, I do not understand Richard Feynman Generating images Image data (e.g. ImageNet): samples from the true data distribution. Generative model (e.g. deep neural network): outputs images, which means samples from the model. 28
29 Review of GAN Counterfeiters vs Police Game IT S FAKE MONEY! IT S REAL MONEY! 29
30 Review of GAN Discriminator Model D Generator Model G Sample x Random noise z p(z) 30
31 Review of GAN Discriminator Model D 1 0 Try to classify the sample x D(x)=0 when x from Data D(x)=1 when x from G (generator) Differentiable function represented by a multilayer perceptron with parameters sample x from data sample x from G Generator Model G Try to generate sample x As similar as the real data random noise z p(z) 31
32 Generative Adversarial Network V D, G = E x~pdata(x) log D x min max V D, G G D + E z~pz(z) log(1 D(G(z))) Discriminator Model D 1 0 Generator Model G random noise z p(z) 32
33 Review of DCGAN Discriminative Model D 1 0 Replace model s network to CNN Example of generator G (same as D) Generative Model G random noise z p(z) z: uniform dist. 33
34 GAN text to image synthesis ψ t : text embedding function (map to 1024 dim) -> Fully-connected layer -> 128 dim Used pre-trained text encoder (can be done end-to-end manner) z~n 0,1 : 100 dim noise vector Text-Conditional GAN 34
35 Conditional GAN 35 Mirza, Mehdi, and Simon Osindero. "Conditional generative adversarial nets."arxiv preprint arxiv: (2014).
36 Text-conditional GAN (naïve) 128 dim 4*4*16 h = ψ t Real image & matched text Fake image & arbitrary text min G max D E x~p data log D x, h + E z~pz log 1 D G z, h, h 36
37 Matching-aware discriminator 128 dim 4*4*16 h = ψ(t) min G max D Real image & matched text E x~pdata log D x, h + E x~pdata log 1 D x, h +E z~pz log 1 D G z, h, h Real image & mismatched text 37 Fake image & matched text
38 Matching-aware Discriminator h = ψ(t) min G max D Real image & matched text E x~pdata log D x, h + E x~pdata log 1 D x, h +E z~pz log 1 D G z, h, h Real image & mismatched text Fake image & matched text 38
39 Learning with Manifold Interpolation h = ψ(t) Real image & matched text Real image & mis-matched text min G max D E x~pdata log D x, h + E x~pdata log 1 D x, h +E z~pz log 1 D G z, h, h Fake image & matched text Additional term to generator to minimize: E t1,t 2 ~p textdata log 1 D G z, h), h, h = βh β h 2 h 1 = ψ t 1, h 2 = ψ t 2 39
40 Experiments
41 Experiments
42 Style Transfer 128 dim 4*4*16 L style = E t,z~n 0,1 z S G z, h S x z 2 2 Finding an inverse mapping from an image to vector 42
43 Style Transfer L style = E t,z~n 0,1 z S G z, h S x z 2 2 Input image: x Style: z = S(x) Generated image: G(z, h) Image Style vector Text description Style transferred image
44 Sentence Interpolation 44
45 Pixel Level Domain Transfer, ECCV
46 Domain transfer 46
47 Whole architecture Converter: deconvnet Discriminator: Real vs. Fake Discriminator : Associated or not 47
48 Dataset 48
49 Results 49
50 Results varying input conditions 50
51 Results inverse setting 51
52 Image to Image Translation 52 Image-to-Image Translation with Conditional Adversarial Networks
53 Image to Image Translation + L1 loss function Low-freq correctness + PatchGAN High-freq correctness 53
54 Image to Image Translation 54
55 Image to Image Translation 55
56 Plug & Play Generative Networks ArXiv
57 Plug & Play Generative Networks 57
58 Plug & Play Generative Networks 58
59 Noiseless joint PPGN-h Update Rule for a feature vector h Training G Training D 59
60 Noiseless joint PPGN-h Encoder network is pre-trained. G and D are trained with standard GAN learning technique. G is not directly used to generate image, but used as a guiding function combined with DAE. 60
61 PPGN results 61
62 PPGN results 62
63 Learning What and Where to Draw NIPS
64 Motivation Generative adversarial what-where nets (GAWWN) Give a bbox Give part locations Give a part location 64
65 Bounding Box Control Generator input: z, text, bbox location 65
66 Bounding Box Control Discriminator input: real/fake image, text, bbox location 66
67 Bounding Box Control Overall structure 67
68 Keypoint-Conditional Control Generator input: z, text, keypoint location (e.g., head in channel 1, left foot in channel 2, 68
69 Keypoint-Conditional Control Discriminator input: real/fake image, text, keypoint location 69
70 Keypoint-Conditional Control Overall structure 70
71 Keypoint Generation There are too much efforts to enter all keypoints (e.g., 15 parts for a bird). Given a subset of keypoints, let s find the remaining keypoints location. Among many ways, they chose to use GAN. Keypoints: k i = x i, y i, v i, i = 1,, K v i = 1 if visible else 0 k 0,1 K 3 User input: s 0,1 K s i = 1 if given else 0 Given probability: 0.1 is use Generated Keypoints: f: R Z+T+3K R 3K MLP (3-layer fully connected network is used) Kepoints Discriminator: Distinguish (k real, t real ) from synthetic (Dind t say what is used. Maybe MLP.) 71
72 Experiments Bbox control (fix text and z / varying bbox) 72
73 Experiments Keypoint control (fix text / use gt keypoints / varying z) Keypoint control (fix text and z / varying beak and tail keypoint positions and generate other keypoints conditionally) 73
74 Experiments Keypoint control (fix text and z / generate all keypoints conditioned on text) 74
75
Introduction to Generative Adversarial Networks
Introduction to Generative Adversarial Networks Luke de Oliveira Vai Technologies Lawrence Berkeley National Laboratory @lukede0 @lukedeo lukedeo@vaitech.io https://ldo.io 1 Outline Why Generative Modeling?
More informationGENERATIVE ADVERSARIAL NETWORKS FOR IMAGE STEGANOGRAPHY
GENERATIVE ADVERSARIAL NETWORKS FOR IMAGE STEGANOGRAPHY Denis Volkhonskiy 2,3, Boris Borisenko 3 and Evgeny Burnaev 1,2,3 1 Skolkovo Institute of Science and Technology 2 The Institute for Information
More informationLearning to generate with adversarial networks
Learning to generate with adversarial networks Gilles Louppe June 27, 2016 Problem statement Assume training samples D = {x x p data, x X } ; We want a generative model p model that can draw new samples
More informationGenerative Adversarial Text to Image Synthesis
Generative Adversarial Text to Image Synthesis Scott Reed, Zeynep Akata, Xinchen Yan, Lajanugen Logeswaran, Bernt Schiele, Honglak Lee Presented by: Jingyao Zhan Contents Introduction Related Work Method
More informationarxiv: v1 [cs.mm] 16 Mar 2017
Steganographic Generative Adversarial Networks arxiv:1703.05502v1 [cs.mm] 16 Mar 2017 Denis Volkhonskiy 1,2,3, Ivan Nazarov 1,2, Boris Borisenko 3 and Evgeny Burnaev 1,2,3 1 Skolkovo Institute of Science
More informationDeep generative models of natural images
Spring 2016 1 Motivation 2 3 Variational autoencoders Generative adversarial networks Generative moment matching networks Evaluating generative models 4 Outline 1 Motivation 2 3 Variational autoencoders
More informationGENERATIVE ADVERSARIAL NETWORKS (GAN) Presented by Omer Stein and Moran Rubin
GENERATIVE ADVERSARIAL NETWORKS (GAN) Presented by Omer Stein and Moran Rubin GENERATIVE MODEL Given a training dataset, x, try to estimate the distribution, Pdata(x) Explicitly or Implicitly (GAN) Explicitly
More informationDeep Fakes using Generative Adversarial Networks (GAN)
Deep Fakes using Generative Adversarial Networks (GAN) Tianxiang Shen UCSD La Jolla, USA tis038@eng.ucsd.edu Ruixian Liu UCSD La Jolla, USA rul188@eng.ucsd.edu Ju Bai UCSD La Jolla, USA jub010@eng.ucsd.edu
More informationAn Empirical Study of Generative Adversarial Networks for Computer Vision Tasks
An Empirical Study of Generative Adversarial Networks for Computer Vision Tasks Report for Undergraduate Project - CS396A Vinayak Tantia (Roll No: 14805) Guide: Prof Gaurav Sharma CSE, IIT Kanpur, India
More informationIntroduction to Generative Adversarial Networks
Introduction to Generative Adversarial Networks Ian Goodfellow, OpenAI Research Scientist NIPS 2016 Workshop on Adversarial Training Barcelona, 2016-12-9 Adversarial Training A phrase whose usage is in
More informationarxiv: v1 [eess.sp] 23 Oct 2018
Reproducing AmbientGAN: Generative models from lossy measurements arxiv:1810.10108v1 [eess.sp] 23 Oct 2018 Mehdi Ahmadi Polytechnique Montreal mehdi.ahmadi@polymtl.ca Mostafa Abdelnaim University de Montreal
More informationGenerative Networks. James Hays Computer Vision
Generative Networks James Hays Computer Vision Interesting Illusion: Ames Window https://www.youtube.com/watch?v=ahjqe8eukhc https://en.wikipedia.org/wiki/ames_trapezoid Recap Unsupervised Learning Style
More informationarxiv: v1 [cs.cv] 5 Jul 2017
AlignGAN: Learning to Align Cross- Images with Conditional Generative Adversarial Networks Xudong Mao Department of Computer Science City University of Hong Kong xudonmao@gmail.com Qing Li Department of
More informationProgressive Generative Hashing for Image Retrieval
Progressive Generative Hashing for Image Retrieval Yuqing Ma, Yue He, Fan Ding, Sheng Hu, Jun Li, Xianglong Liu 2018.7.16 01 BACKGROUND the NNS problem in big data 02 RELATED WORK Generative adversarial
More informationSYNTHESIS OF IMAGES BY TWO-STAGE GENERATIVE ADVERSARIAL NETWORKS. Qiang Huang, Philip J.B. Jackson, Mark D. Plumbley, Wenwu Wang
SYNTHESIS OF IMAGES BY TWO-STAGE GENERATIVE ADVERSARIAL NETWORKS Qiang Huang, Philip J.B. Jackson, Mark D. Plumbley, Wenwu Wang Centre for Vision, Speech and Signal Processing University of Surrey, Guildford,
More informationarxiv: v1 [cs.ne] 11 Jun 2018
Generative Adversarial Network Architectures For Image Synthesis Using Capsule Networks arxiv:1806.03796v1 [cs.ne] 11 Jun 2018 Yash Upadhyay University of Minnesota, Twin Cities Minneapolis, MN, 55414
More information(University Improving of Montreal) Generative Adversarial Networks with Denoising Feature Matching / 17
Improving Generative Adversarial Networks with Denoising Feature Matching David Warde-Farley 1 Yoshua Bengio 1 1 University of Montreal, ICLR,2017 Presenter: Bargav Jayaraman Outline 1 Introduction 2 Background
More informationarxiv: v1 [cs.cv] 16 Jul 2017
enerative adversarial network based on resnet for conditional image restoration Paper: jc*-**-**-****: enerative Adversarial Network based on Resnet for Conditional Image Restoration Meng Wang, Huafeng
More informationarxiv: v1 [cs.cv] 20 Mar 2017
I2T2I: LEARNING TEXT TO IMAGE SYNTHESIS WITH TEXTUAL DATA AUGMENTATION Hao Dong, Jingqing Zhang, Douglas McIlwraith, Yike Guo arxiv:1703.06676v1 [cs.cv] 20 Mar 2017 Data Science Institute, Imperial College
More informationAlternatives to Direct Supervision
CreativeAI: Deep Learning for Graphics Alternatives to Direct Supervision Niloy Mitra Iasonas Kokkinos Paul Guerrero Nils Thuerey Tobias Ritschel UCL UCL UCL TUM UCL Timetable Theory and Basics State of
More informationProgress on Generative Adversarial Networks
Progress on Generative Adversarial Networks Wangmeng Zuo Vision Perception and Cognition Centre Harbin Institute of Technology Content Image generation: problem formulation Three issues about GAN Discriminate
More informationSequential Line Search for Generative Adversarial Networks
Seuential Line Search for Generative Adversarial Networks Masahiro Kazama Recruit Technologies Co.,Ltd. Tokyo, Japan masahiro_kazama@r.recruit.co.jp Viviane Takahashi Recruit Technologies Co.,Ltd. Tokyo,
More informationGenerative Adversarial Networks (GANs)
Generative Adversarial Networks (GANs) Hossein Azizpour Most of the slides are courtesy of Dr. Ian Goodfellow (Research Scientist at OpenAI) and from his presentation at NIPS 2016 tutorial Note. I am generally
More informationarxiv: v1 [cs.cv] 7 Mar 2018
Accepted as a conference paper at the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN) 2018 Inferencing Based on Unsupervised Learning of Disentangled
More informationAdversarially Learned Inference
Institut des algorithmes d apprentissage de Montréal Adversarially Learned Inference Aaron Courville CIFAR Fellow Université de Montréal Joint work with: Vincent Dumoulin, Ishmael Belghazi, Olivier Mastropietro,
More informationarxiv: v2 [cs.lg] 17 Dec 2018
Lu Mi 1 * Macheng Shen 2 * Jingzhao Zhang 2 * 1 MIT CSAIL, 2 MIT LIDS {lumi, macshen, jzhzhang}@mit.edu The authors equally contributed to this work. This report was a part of the class project for 6.867
More informationGENERATIVE ADVERSARIAL NETWORK-BASED VIR-
GENERATIVE ADVERSARIAL NETWORK-BASED VIR- TUAL TRY-ON WITH CLOTHING REGION Shizuma Kubo, Yusuke Iwasawa, and Yutaka Matsuo The University of Tokyo Bunkyo-ku, Japan {kubo, iwasawa, matsuo}@weblab.t.u-tokyo.ac.jp
More informationClass-Splitting Generative Adversarial Networks
Class-Splitting Generative Adversarial Networks Guillermo L. Grinblat 1, Lucas C. Uzal 1, and Pablo M. Granitto 1 arxiv:1709.07359v2 [stat.ml] 17 May 2018 1 CIFASIS, French Argentine International Center
More informationarxiv: v1 [stat.ml] 19 Aug 2017
Semi-supervised Conditional GANs Kumar Sricharan 1, Raja Bala 1, Matthew Shreve 1, Hui Ding 1, Kumar Saketh 2, and Jin Sun 1 1 Interactive and Analytics Lab, Palo Alto Research Center, Palo Alto, CA 2
More informationUnsupervised Learning
Deep Learning for Graphics Unsupervised Learning Niloy Mitra Iasonas Kokkinos Paul Guerrero Vladimir Kim Kostas Rematas Tobias Ritschel UCL UCL/Facebook UCL Adobe Research U Washington UCL Timetable Niloy
More informationarxiv: v1 [cs.cv] 8 Jan 2019
GILT: Generating Images from Long Text Ori Bar El, Ori Licht, Netanel Yosephian Tel-Aviv University {oribarel, oril, yosephian}@mail.tau.ac.il arxiv:1901.02404v1 [cs.cv] 8 Jan 2019 Abstract Creating an
More informationStructured GANs. Irad Peleg 1 and Lior Wolf 1,2. Abstract. 1. Introduction. 2. Symmetric GANs Related Work
Structured GANs Irad Peleg 1 and Lior Wolf 1,2 1 Tel Aviv University 2 Facebook AI Research Abstract We present Generative Adversarial Networks (GANs), in which the symmetric property of the generated
More informationInverting The Generator Of A Generative Adversarial Network
1 Inverting The Generator Of A Generative Adversarial Network Antonia Creswell and Anil A Bharath, Imperial College London arxiv:1802.05701v1 [cs.cv] 15 Feb 2018 Abstract Generative adversarial networks
More informationVisual Recommender System with Adversarial Generator-Encoder Networks
Visual Recommender System with Adversarial Generator-Encoder Networks Bowen Yao Stanford University 450 Serra Mall, Stanford, CA 94305 boweny@stanford.edu Yilin Chen Stanford University 450 Serra Mall
More informationConditional DCGAN For Anime Avatar Generation
Conditional DCGAN For Anime Avatar Generation Wang Hang School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai 200240, China Email: wang hang@sjtu.edu.cn Abstract
More informationLecture 19: Generative Adversarial Networks
Lecture 19: Generative Adversarial Networks Roger Grosse 1 Introduction Generative modeling is a type of machine learning where the aim is to model the distribution that a given set of data (e.g. images,
More informationWays of Conditioning Generative Adversarial Networks
Ways of Conditioning Generative Adversarial Networks Hanock Kwak and Byoung-Tak Zhang School of Computer Science and Engineering Seoul National University Seoul 151-744, Korea {hnkwak, btzhang}@bi.snu.ac.kr
More informationGenerative Adversarial Text to Image Synthesis
Scott Reed, Zeynep Akata, Xinchen Yan, Lajanugen Logeswaran REEDSCOT 1, AKATA 2, XCYAN 1, LLAJAN 1 Bernt Schiele, Honglak Lee SCHIELE 2,HONGLAK 1 1 University of Michigan, Ann Arbor, MI, USA (UMICH.EDU)
More informationA GENERATIVE ADVERSARIAL NETWORK BASED FRAMEWORK FOR UNSUPERVISED VISUAL SURFACE INSPECTION. Wei Zhai Jiang Zhu Yang Cao Zengfu Wang
A GENERATIVE ADVERSARIAL NETWORK BASED FRAMEWORK FOR UNSUPERVISED VISUAL SURFACE INSPECTION Wei Zhai Jiang Zhu Yang Cao Zengfu Wang Department of Automation, University of Science and Technology of China
More informationarxiv: v1 [cs.cv] 17 Nov 2016
Inverting The Generator Of A Generative Adversarial Network arxiv:1611.05644v1 [cs.cv] 17 Nov 2016 Antonia Creswell BICV Group Bioengineering Imperial College London ac2211@ic.ac.uk Abstract Anil Anthony
More informationGenerative Adversarial Networks (GANs) Ian Goodfellow, Research Scientist MLSLP Keynote, San Francisco
Generative Adversarial Networks (GANs) Ian Goodfellow, Research Scientist MLSLP Keynote, San Francisco 2016-09-13 Generative Modeling Density estimation Sample generation Training examples Model samples
More informationarxiv: v1 [cs.cv] 6 Sep 2018
arxiv:1809.01890v1 [cs.cv] 6 Sep 2018 Full-body High-resolution Anime Generation with Progressive Structure-conditional Generative Adversarial Networks Koichi Hamada, Kentaro Tachibana, Tianqi Li, Hiroto
More informationGenerative Adversarial Networks (GANs) Based on slides from Ian Goodfellow s NIPS 2016 tutorial
Generative Adversarial Networks (GANs) Based on slides from Ian Goodfellow s NIPS 2016 tutorial Generative Modeling Density estimation Sample generation Training examples Model samples Next Video Frame
More informationIVE-GAN: INVARIANT ENCODING GENERATIVE AD-
IVE-GAN: INVARIANT ENCODING GENERATIVE AD- VERSARIAL NETWORKS Anonymous authors Paper under double-blind review ABSTRACT Generative adversarial networks (GANs) are a powerful framework for generative tasks.
More informationThe Amortized Bootstrap
Eric Nalisnick 1 Padhraic Smyth 1 Abstract We use amortized inference in conjunction with implicit models to approximate the bootstrap distribution over model parameters. We call this the amortized bootstrap,
More informationIntroduction to GAN. Generative Adversarial Networks. Junheng(Jeff) Hao
Introduction to GAN Generative Adversarial Networks Junheng(Jeff) Hao Adversarial Training is the coolest thing since sliced bread. -- Yann LeCun Roadmap 1. Generative Modeling 2. GAN 101: What is GAN?
More informationPaired 3D Model Generation with Conditional Generative Adversarial Networks
Accepted to 3D Reconstruction in the Wild Workshop European Conference on Computer Vision (ECCV) 2018 Paired 3D Model Generation with Conditional Generative Adversarial Networks Cihan Öngün Alptekin Temizel
More informationDeep Learning for Visual Manipulation and Synthesis
Deep Learning for Visual Manipulation and Synthesis Jun-Yan Zhu 朱俊彦 UC Berkeley 2017/01/11 @ VALSE What is visual manipulation? Image Editing Program input photo User Input result Desired output: stay
More informationA New CGAN Technique for Constrained Topology Design Optimization. Abstract
A New CGAN Technique for Constrained Topology Design Optimization M.-H. Herman Shen 1 and Liang Chen Department of Mechanical and Aerospace Engineering The Ohio State University Abstract This paper presents
More informationGAN Frontiers/Related Methods
GAN Frontiers/Related Methods Improving GAN Training Improved Techniques for Training GANs (Salimans, et. al 2016) CSC 2541 (07/10/2016) Robin Swanson (robin@cs.toronto.edu) Training GANs is Difficult
More informationarxiv: v1 [cs.cv] 8 Oct 2016
Learning What and Where to Draw Scott Reed, reedscot@google.com Zeynep Akata 2 akata@mpi-inf.mpg.de Santosh Mohan santoshm@umich.edu arxiv:0.02454v [cs.cv] 8 Oct 20 Samuel Tenka samtenka@umich.edu Bernt
More informationGenerative Modeling with Convolutional Neural Networks. Denis Dus Data Scientist at InData Labs
Generative Modeling with Convolutional Neural Networks Denis Dus Data Scientist at InData Labs What we will discuss 1. 2. 3. 4. Discriminative vs Generative modeling Convolutional Neural Networks How to
More informationImplicit generative models: dual vs. primal approaches
Implicit generative models: dual vs. primal approaches Ilya Tolstikhin MPI for Intelligent Systems ilya@tue.mpg.de Machine Learning Summer School 2017 Tübingen, Germany Contents 1. Unsupervised generative
More informationBuilding an Automatic Sprite Generator with Deep Convolutional Generative Adversarial Networks
Building an Automatic Sprite Generator with Deep Convolutional Generative Adversarial Networks Lewis Horsley School of Computer Science and Electronic Engineering, University of Essex, Colchester, UK lhorsl@essex.ac.uk
More informationAutoencoders. Stephen Scott. Introduction. Basic Idea. Stacked AE. Denoising AE. Sparse AE. Contractive AE. Variational AE GAN.
Stacked Denoising Sparse Variational (Adapted from Paul Quint and Ian Goodfellow) Stacked Denoising Sparse Variational Autoencoding is training a network to replicate its input to its output Applications:
More informationAutoencoder. Representation learning (related to dictionary learning) Both the input and the output are x
Deep Learning 4 Autoencoder, Attention (spatial transformer), Multi-modal learning, Neural Turing Machine, Memory Networks, Generative Adversarial Net Jian Li IIIS, Tsinghua Autoencoder Autoencoder Unsupervised
More informationLab meeting (Paper review session) Stacked Generative Adversarial Networks
Lab meeting (Paper review session) Stacked Generative Adversarial Networks 2017. 02. 01. Saehoon Kim (Ph. D. candidate) Machine Learning Group Papers to be covered Stacked Generative Adversarial Networks
More informationImage Restoration with Deep Generative Models
Image Restoration with Deep Generative Models Raymond A. Yeh *, Teck-Yian Lim *, Chen Chen, Alexander G. Schwing, Mark Hasegawa-Johnson, Minh N. Do Department of Electrical and Computer Engineering, University
More informationarxiv: v4 [cs.lg] 1 May 2018
Controllable Generative Adversarial Network arxiv:1708.00598v4 [cs.lg] 1 May 2018 Minhyeok Lee School of Electrical Engineering Korea University Seoul, Korea 02841 suam6409@korea.ac.kr Abstract Junhee
More informationarxiv: v2 [cs.lg] 7 Jun 2017
Pixel Deconvolutional Networks Hongyang Gao Washington State University Pullman, WA 99164 hongyang.gao@wsu.edu Hao Yuan Washington State University Pullman, WA 99164 hao.yuan@wsu.edu arxiv:1705.06820v2
More informationANY image data set only covers a fixed domain. This
Extra Domain Data Generation with Generative Adversarial Nets Luuk Boulogne Bernoulli Institute Department of Artificial Intelligence University of Groningen Groningen, The Netherlands lhboulogne@gmail.com
More informationLip Movement Synthesis from Text
Lip Movement Synthesis from Text 1 1 Department of Computer Science and Engineering Indian Institute of Technology, Kanpur July 20, 2017 (1Department of Computer Science Lipand Movement Engineering Synthesis
More informationarxiv: v5 [cs.cv] 16 May 2018
Image Colorization using Generative Adversarial Networks Kamyar Nazeri, Eric Ng, and Mehran Ebrahimi Faculty of Science, University of Ontario Institute of Technology 2000 Simcoe Street North, Oshawa,
More informationarxiv: v2 [cs.cv] 26 Mar 2017
TAC-GAN Text Conditioned Auxiliary Classifier Generative Adversarial Network arxiv:1703.06412v2 [cs.cv] 26 ar 2017 Ayushman Dash 1 John Gamboa 1 Sheraz Ahmed 3 arcus Liwicki 14 uhammad Zeshan Afzal 12
More informationConditional Generative Adversarial Networks for Particle Physics
Conditional Generative Adversarial Networks for Particle Physics Capstone 2016 Charles Guthrie ( cdg356@nyu.edu ) Israel Malkin ( im965@nyu.edu ) Alex Pine ( akp258@nyu.edu ) Advisor: Kyle Cranmer ( kyle.cranmer@nyu.edu
More informationGenerative Adversarial Nets. Priyanka Mehta Sudhanshu Srivastava
Generative Adversarial Nets Priyanka Mehta Sudhanshu Srivastava Outline What is a GAN? How does GAN work? Newer Architectures Applications of GAN Future possible applications Generative Adversarial Networks
More informationWhen Variational Auto-encoders meet Generative Adversarial Networks
When Variational Auto-encoders meet Generative Adversarial Networks Jianbo Chen Billy Fang Cheng Ju 14 December 2016 Abstract Variational auto-encoders are a promising class of generative models. In this
More informationDeep Generative Models and a Probabilistic Programming Library
Deep Generative Models and a Probabilistic Programming Library Discriminative (Deep) Learning Learn a (differentiable) function mapping from input to output x f(x; θ) y Gradient back-propagation Generative
More informationLearning Social Graph Topologies using Generative Adversarial Neural Networks
Learning Social Graph Topologies using Generative Adversarial Neural Networks Sahar Tavakoli 1, Alireza Hajibagheri 1, and Gita Sukthankar 1 1 University of Central Florida, Orlando, Florida sahar@knights.ucf.edu,alireza@eecs.ucf.edu,gitars@eecs.ucf.edu
More informationSemantic Image Synthesis via Adversarial Learning
Semantic Image Synthesis via Adversarial Learning Hao Dong, Simiao Yu, Chao Wu, Yike Guo Imperial College London {hao.dong11, simiao.yu13, chao.wu, y.guo}@imperial.ac.uk Abstract In this paper, we propose
More informationIntroduction to GAN. Generative Adversarial Networks. Junheng(Jeff) Hao
Introduction to GAN Generative Adversarial Networks Junheng(Jeff) Hao Adversarial Training is the coolest thing since sliced bread. -- Yann LeCun Roadmap 1. Generative Modeling 2. GAN 101: What is GAN?
More informationarxiv: v4 [cs.lg] 29 May 2016
Generating images with recurrent adversarial networks arxiv:1602.05110v4 [cs.lg] 29 May 2016 Daniel Jiwoong Im Montreal Institute for Learning Algorithm University of Montreal imdaniel@iro.umontreal.ca
More informationDOMAIN-ADAPTIVE GENERATIVE ADVERSARIAL NETWORKS FOR SKETCH-TO-PHOTO INVERSION
DOMAIN-ADAPTIVE GENERATIVE ADVERSARIAL NETWORKS FOR SKETCH-TO-PHOTO INVERSION Yen-Cheng Liu 1, Wei-Chen Chiu 2, Sheng-De Wang 1, and Yu-Chiang Frank Wang 1 1 Graduate Institute of Electrical Engineering,
More informationTag Disentangled Generative Adversarial Networks for Object Image Re-rendering
Tag Disentangled Generative Adversarial Networks for Object Image Re-rendering Chaoyue Wang, Chaohui Wang, Chang Xu, Dacheng Tao Centre for Artificial Intelligence, School of Software, University of Technology
More informationGenerative Adversarial Text to Image Synthesis
Scott Reed, Zeynep Akata, Xinchen Yan, Lajanugen Logeswaran REEDSCOT 1, AKATA 2, XCYAN 1, LLAJAN 1 Honglak Lee, Bernt Schiele HONGLAK 1, SCHIELE 2 1 University of Michigan, Ann Arbor, MI, USA (UMICH.EDU)
More informationGenerative Models II. Phillip Isola, MIT, OpenAI DLSS 7/27/18
Generative Models II Phillip Isola, MIT, OpenAI DLSS 7/27/18 What s a generative model? For this talk: models that output high-dimensional data (Or, anything involving a GAN, VAE, PixelCNN, etc) Useful
More informationFine-grained Multi-attribute Adversarial Learning for Face Generation of Age, Gender and Ethnicity
Fine-grained Multi-attribute Adversarial Learning for Face Generation of Age, Gender and Ethnicity Lipeng Wan 1+, Jun Wan 2+, Yi Jin 1, Zichang Tan 2, Stan Z. Li 2 1 School of Computer and Information
More informationDOMAIN-ADAPTIVE GENERATIVE ADVERSARIAL NETWORKS FOR SKETCH-TO-PHOTO INVERSION
2017 IEEE INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING, SEPT. 25 28, 2017, TOKYO, JAPAN DOMAIN-ADAPTIVE GENERATIVE ADVERSARIAL NETWORKS FOR SKETCH-TO-PHOTO INVERSION Yen-Cheng Liu 1,
More informationStacking VAE and GAN for Context-aware Text-to-Image Generation
2018 IEEE Fourth International Conference on Multimedia Big Data (BigMM) Stacking VAE and GAN for Context-aware Text-to-Image Generation Chenrui Zhang and Yuxin Peng* Institute of Computer Science and
More informationDeep Generative Models Variational Autoencoders
Deep Generative Models Variational Autoencoders Sudeshna Sarkar 5 April 2017 Generative Nets Generative models that represent probability distributions over multiple variables in some way. Directed Generative
More informationarxiv: v1 [cs.cv] 1 Aug 2017
Deep Generative Adversarial Neural Networks for Realistic Prostate Lesion MRI Synthesis Andy Kitchen a, Jarrel Seah b a,* Independent Researcher b STAT Innovations Pty. Ltd., PO Box 274, Ashburton VIC
More informationsong2vec: Determining Song Similarity using Deep Unsupervised Learning
song2vec: Determining Song Similarity using Deep Unsupervised Learning CS229 Final Project Report (category: Music & Audio) Brad Ross (bross35), Prasanna Ramakrishnan (pras1712) 1 Introduction Humans are
More informationarxiv: v1 [stat.ml] 15 Feb 2018
Conditioning of three-dimensional generative adversarial networks for pore and reservoir-scale models arxiv:1802.05622v1 [stat.ml] 15 Feb 2018 Lukas J. Mosser lukas.mosser15@imperial.ac.uk Martin J. Blunt
More informationFeature Super-Resolution: Make Machine See More Clearly
Feature Super-Resolution: Make Machine See More Clearly Weimin Tan, Bo Yan, Bahetiyaer Bare School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University {wmtan14,
More informationVariational Autoencoders. Sargur N. Srihari
Variational Autoencoders Sargur N. srihari@cedar.buffalo.edu Topics 1. Generative Model 2. Standard Autoencoder 3. Variational autoencoders (VAE) 2 Generative Model A variational autoencoder (VAE) is a
More informationGANosaic: Mosaic Creation with Generative Texture Manifolds
GANosaic: Mosaic Creation with Generative Texture Manifolds Nikolay Jetchev nikolay.jetchev@zalando.de Zalando Research Urs Bergmann urs.bergmann@zalando.de Zalando Research Abstract Calvin Seward calvin.seward@zalando.de
More informationDeep Learning Approaches to 3D Shape Completion
Deep Learning Approaches to 3D Shape Completion Prafull Sharma Stanford University prafull7@stanford.edu Jarrod Cingel Stanford University jcingel@stanford.edu Abstract This project explores various methods
More informationarxiv: v1 [stat.ml] 14 Sep 2017
The Conditional Analogy GAN: Swapping Fashion Articles on People Images Nikolay Jetchev Zalando Research nikolay.jetchev@zalando.de Urs Bergmann Zalando Research urs.bergmann@zalando.de arxiv:1709.04695v1
More informationInfrared Image Colorization based on a Triplet DCGAN Architecture
Infrared Image Colorization based on a Triplet DCGAN Architecture Patricia L. Suárez plsuarez@espol.edu.ec Angel D. Sappa,2 sappa@ieee.org Boris X. Vintimilla boris.vintimilla@espol.edu.ec Escuela Superior
More informationarxiv: v1 [cs.gr] 22 Jan 2019
Generation High resolution 3D model from natural language by Generative Adversarial Network Kentaro Fukamizu, Masaaki Kondo, Ryuichi Sakamoto arxiv:1901.07165v1 [cs.gr] 22 Jan 2019 Abstract Since creating
More informationarxiv: v3 [cs.lg] 10 Apr 2016
arxiv:1602.05110v3 [cs.lg] 10 Apr 2016 Daniel Jiwoong Im 1 Chris Dongjoo Kim 2 Hui Jiang 2 Roland Memisevic 1 1 Montreal Institute for Learning Algorithms, University of Montreal 2 Department of Engineering
More informationStochastic Simulation with Generative Adversarial Networks
Stochastic Simulation with Generative Adversarial Networks Lukas Mosser, Olivier Dubrule, Martin J. Blunt lukas.mosser15@imperial.ac.uk, o.dubrule@imperial.ac.uk, m.blunt@imperial.ac.uk (Deep) Generative
More informationSemi Supervised Semantic Segmentation Using Generative Adversarial Network
Semi Supervised Semantic Segmentation Using Generative Adversarial Network Nasim Souly Concetto Spampinato Mubarak Shah nsouly@eecs.ucf.edu cspampin@dieei.unict.it shah@crcv.ucf.edu Abstract Unlabeled
More informationBidirectional GAN. Adversarially Learned Inference (ICLR 2017) Adversarial Feature Learning (ICLR 2017)
Bidirectional GAN Adversarially Learned Inference (ICLR 2017) V. Dumoulin 1, I. Belghazi 1, B. Poole 2, O. Mastropietro 1, A. Lamb 1, M. Arjovsky 3 and A. Courville 1 1 Universite de Montreal & 2 Stanford
More informationDCGANs for image super-resolution, denoising and debluring
DCGANs for image super-resolution, denoising and debluring Qiaojing Yan Stanford University Electrical Engineering qiaojing@stanford.edu Wei Wang Stanford University Electrical Engineering wwang23@stanford.edu
More informationGenerating Image Sequence from Description with LSTM Conditional GAN
Generating Image Sequence from escription with LSTM Conditional GAN Xu Ouyang, Xi Zhang, i Ma, Gady Agam Illinois Institute of Technology Chicago, IL 60616 {xouyang3, xzhang22, dma2}@hawk.iit.edu, agam@iit.edu
More informationAutomatic Colorization with Deep Convolutional Generative Adversarial Networks
Automatic Colorization with Deep Convolutional Generative Adversarial Networks Stephen Koo Stanford University Stanford, CA sckoo@cs.stanford.edu Abstract We attempt to use DCGANs (deep convolutional generative
More informationGANs for Exploiting Unlabeled Data. Presented by: Uriya Pesso Nimrod Gilboa Markevich
GANs for Exploiting Unlabeled Data Improved Techniques for Training GANs Learning from Simulated and Unsupervised Images through Adversarial Training Presented by: Uriya Pesso Nimrod Gilboa Markevich [
More informationarxiv: v1 [cs.cv] 26 Jul 2016
Semantic Image Inpainting with Perceptual and Contextual Losses arxiv:1607.07539v1 [cs.cv] 26 Jul 2016 Raymond Yeh Chen Chen Teck Yian Lim, Mark Hasegawa-Johnson Minh N. Do Dept. of Electrical and Computer
More informationarxiv: v1 [cs.lg] 19 Jul 2017
Weiyi Liu 2 Pin-Yu Chen 2 Hal Cooper 3 Min Hwan Oh 3 Sailung Yeung 4 Toyotaro Suzumura 2 arxiv:707.0697v [cs.lg] 9 Jul 207 Abstract This paper is first-line research expanding GANs into graph topology
More information