Generative Models II. Phillip Isola, MIT, OpenAI DLSS 7/27/18
|
|
- Albert Crawford
- 5 years ago
- Views:
Transcription
1 Generative Models II Phillip Isola, MIT, OpenAI DLSS 7/27/18
2 What s a generative model? For this talk: models that output high-dimensional data (Or, anything involving a GAN, VAE, PixelCNN, etc) Useful for lots of problems beyond density estimation and sampling random images!
3 What can you do with generative models? 1. Data prediction 2. Domain mapping 3. Representation learning 4. Model-based intelligence
4 What can you do with generative models? 1. Data prediction 2. Domain mapping 3. Representation learning 4. Model-based intelligence
5 Generative Model x z Gaussian noise Synthesized z N (~0, 1) image
6 Conditional Generative Model x y bird Synthesized image
7 Conditional Generative Model x y A yellow bird on a branch Synthesized image
8 Conditional Generative Model y x Synthesized image
9 Data prediction problems ( structured prediction ) Object labeling Edge Detection [Xie et al. 2015, ] [Long et al. 2015, ] Text-to-photo Future frame prediction this small bird has a pink breast and crown [Reed et al. 2014, ] [Mathieu et al. 2016, ]
10 Challenges in data prediction 1. Output is a high-dimensional, structured objects 2. Uncertainty in the mapping, many plausible outputs
11 Properties of generative models 1. Model high-dimensional, structured objects 2. Model uncertainty; a whole distribution of possible outputs
12 Conditional Generative Models Two ways to do it: 1. Model p(x,y), then do inference to get conditional p(y x) arg max y p(x, y) = arg max y p(y x) 2. Directly model p(y x)
13 Image-to-Image Translation Input x Output y Training data n x y o F, n o n,, o arg min F E x,y[l(f(x), y)] Objective function (loss) Neural Network [Zhang et al., ECCV 2016]
14 Image-to-Image Translation Input x Output y F arg min F E x,y[l(f(x), y)] What should I do How should I do it?
15 Designing loss functions Input Output Ground truth
16
17 Designing loss functions Input Zhang et al Ground truth Color distribution cross-entropy loss with colorfulness enhancing term.
18
19 Designing loss functions Be careful what you wish for!
20 Designing loss functions Image colorization L2 regression Super-resolution [Zhang, Isola, Efros, ECCV 2016] L2 regression [Johnson, Alahi, Li, ECCV 2016]
21 Designing loss functions Image colorization Cross entropy objective, with colorfulness term Super-resolution [Zhang, Isola, Efros, ECCV 2016] Deep feature covariance matching objective [Johnson, Alahi, Li, ECCV 2016]
22 ) Universal loss?
23 ) Generated images Generative Adversarial Network (GANs) Generated vs Real (classifier) Real photos [Goodfellow, Pouget-Abadie, Mirza, Xu, Warde-Farley, Ozair, Courville, Bengio 2014]
24 x G G(x) Generator
25 x G G(x) D real or fake? Generator Discriminator G tries to synthesize fake images that fool D D tries to identify the fakes
26 x G G(x) D fake (0.9) y D real (0.1) arg max D E x,y [ log D(G(x)) + log(1 D(y)) ]
27 x G G(x) D real or fake? G tries to synthesize fake images that fool D: arg min G E x,y [ log D(G(x)) + log(1 D(y)) ]
28 x G G(x) D real or fake? G tries to synthesize fake images that fool the best D: arg min G max D E x,y [ log D(G(x)) + log(1 D(y)) ]
29 x G G(x) Loss Function D G s perspective: D is a loss function. Rather than being hand-designed, it is learned.
30 x G G(x) D real or fake? arg min G max D E x,y [ log D(G(x)) + log(1 D(y)) ]
31 x G G(x) D real! ( Aquarius ) arg min G max D E x,y [ log D(G(x)) + log(1 D(y)) ]
32 x G G(x) D real or fake pair? arg min G max D E x,y [ log D(G(x)) + log(1 D(y)) ]
33 x G G(x) D real or fake pair? arg min G max D E x,y[ log D(x,G(x)) + log(1 D(x, y)) ]
34 x G G(x) D fake pair arg min G max D E x,y[ log D(x,G(x)) + log(1 D(x, y)) ]
35 x G G(x) D real pair arg min G max D E x,y[ log D(x,G(x)) + log(1 D(x, y)) ]
36 x G G(x) D real or fake pair? arg min G max D E x,y[ log D(x,G(x)) + log(1 D(x, y)) ]
37 Conditional GAN Training Details: Loss function
38 Training Details: Loss function Conditional GAN x y G G(x) - Stable training + fast convergence [c.f. Pathak et al. CVPR 2016]
39 BW Color Input Output Input Output Input Output Data from [Russakovsky et al. 2015]
40 #edges2cats [Chris Hesse]
41 Ivy Vitaly
42 Structured Prediction Input x Output ŷ Target y L(ŷ, y) =kŷ yk 2
43 Structured Prediction CRF Each pixel treated as independent Models at pairwise configuration of pixels Y i p(y i x) 1 Z Y i,j p(y i,y j x)
44 Structured Prediction A GAN, with sufficient capacity, samples from the full joint distribution (at equilibrium) Most generative models have this property! Give them sufficient Model joint configuration of all pixels p(y x) capacity and infinite data, and they are the complete solution to prediction problems.
45 Shrinking the capacity: Patch Discriminator D 1/0 N pixels Rather than penalizing if output image looks fake, penalize if each N pixels overlapping patch in output looks fake y [Li & Wand 2016] [Shrivastava et al. 2017] [Isola et al. 2017]
46 Labels Facades Input 1x1 Discriminator Data from [Tylecek, 2013]
47 Labels Facades Input 16x16 Discriminator Data from [Tylecek, 2013]
48 Labels Facades Input 70x70 Discriminator Data from [Tylecek, 2013]
49 Labels Facades Input Full image Discriminator Data from [Tylecek, 2013]
50 Patch Discriminator D 1/0 Rather than penalizing if output image N pixels looks fake, penalize if each overlapping patch in output looks fake N pixels Faster, fewer parameters More supervised observations y Applies to arbitrarily large images
51 Shrinking the capacity: model misspecification [Theis et al. 2016]
52 Mode covering versus mode seeking [Larsen et al. 2016]
53 Modeling multiple possible outputs x G G(x)
54 Modeling multiple possible outputs????? Input Possible outputs
55 Conditional Variational Autoencoders [Sohn, Yan, Lee, NIPS 2015]
56 Example from [Babaeizadeh et al., ICLR 2018] see also [Walker et al., ECCV 2016], [Xue*, Wu*, et al., NIPS 2016]
57 x Observation y Target ŷ Reconstruction z Example from [Babaeizadeh et al., ICLR 2018] see also [Walker et al., ECCV 2016], [Xue*, Wu*, et al., NIPS 2016]
58 x Observation y Target ŷ Reconstruction z Example from [Babaeizadeh et al., ICLR 2018] see also [Walker et al., ECCV 2016], [Xue*, Wu*, et al., NIPS 2016]
59 x Observation y Target ŷ Reconstruction z z learns to encode the missing information necessary to predict y from x, i.e. the direction in which the purple box moves Example from [Babaeizadeh et al., ICLR 2018] see also [Walker et al., ECCV 2016], [Xue*, Wu*, et al., NIPS 2016]
60 x Observation ŷ Prediction z z N (~0, 1) see also [Walker et al., ECCV 2016], [Xue*, Wu*, et al., NIPS 2016]
61 x Observation ŷ Prediction z z N (~0, 1) see also [Walker et al., ECCV 2016], [Xue*, Wu*, et al., NIPS 2016]
62 x Observation ŷ Prediction z z N (~0, 1) see also [Walker et al., ECCV 2016], [Xue*, Wu*, et al., NIPS 2016]
63 x Observation ŷ Prediction z z N (~0, 1) see also [Walker et al., ECCV 2016], [Xue*, Wu*, et al., NIPS 2016]
64 x G y InfoGAN [Chen et al. 2016] BiCycleGAN [Zhu et al., NIPS 2017] z q(z y) Encourages z to relay information about the target.
65 Labels Randomly generated facades [BiCycleGAN, Zhu et al., NIPS 2017]
66 What can you do with generative models? 1. Data prediction 2. Domain mapping 3. Representation learning 4. Model-based intelligence
67 What can you do with generative models? 1. Data prediction 2. Domain mapping 3. Representation learning 4. Model-based intelligence
68 Paired data
69 Paired data Unpaired data Jun-Yan Zhu Taesung Park
70 x G G(x) D real or fake pair? arg min G max D E x,y[ log D(x,G(x)) + log(1 D(x, y)) ]
71 x G G(x) D real or fake pair? arg min G max D E x,y[ log D(x,G(x)) + log(1 D(x, y)) ] No input-output pairs!
72 Gaussian Target distribution z Y
73 Horses Zebras X Y
74 x G G(x) D real or fake? arg min G max D E x,y [ log D(G(x)) + log(1 D(y)) ] Usually loss functions check if output matches a target instance GAN loss checks if output is part of an admissible set
75 x G G(x) D Real!
76 x G G(x) D Real too! Nothing to force output to correspond to input
77 Cycle-Consistent Adversarial Networks [Zhu et al. 2017], [Yi et al. 2017], [Kim et al. 2017]
78 Cycle-Consistent Adversarial Networks
79 Cycle Consistency Loss
80 Cycle Consistency Loss
81
82
83 Failure case
84 Failure case
85 Why does CycleGAN work?
86 Slide credit: Ming-Yu Liu
87 Slide credit: Ming-Yu Liu
88 Simplicity hypothesis [Galanti, Wolf, Benaim, 2018]
89 Cycle Loss upper bounds Conditional Entropy Conditional Entropy High Conditional Entropy Low Conditional Entropy ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matching [Li et al. NIPS 2017]. Also see [Tiao et al. 2018] CycleGAN as Approximate Bayesian Inference
90 Cycle Loss upper bounds Conditional Entropy Conditional Entropy ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matching [Li et al. NIPS 2017]. Also see [Tiao et al. 2018] CycleGAN as Approximate Bayesian Inference
91 CycleGAN at School Course assignment code and handout designed by Prof. Roger Grosse for CSC321 Intro to Neural Networks and Machine Learning at University of Toronto.
92 Can other generative models do this? Unsupervised image-to-image translation networks [Liu, Breuel, Kautz, 2017]
93 Domain Adaptation [Tzeng et al. 2014]
94 Sim2real Simulated data Real data,,? [Richter*, Vineet* et al. 2016] [Krähenbühl et al. 2018]
95 CycleGAN Training data, [Hoffman, Tzeng, Park, Zhu, Isola, Saenko, Darrell, Efros, 2018]
96 CycleGAN Training data, [Hoffman, Tzeng, Park, Zhu, Isola, Saenko, Darrell, Efros, 2018]
97 CycleGAN FCN Training data, [Hoffman, Tzeng, Park, Zhu, Isola, Saenko, Darrell, Efros, 2018]
98 Medical domain adaptation Input MR Generated CT Ground truth CT MRI reconstruction [Quan et al.] arxiv: Cardiac MR images from CT [Chartsias et al. 2017]
99 What can you do with generative models? 1. Data prediction 2. Domain mapping 3. Representation learning 4. Model-based intelligence
100 What can you do with generative models? 1. Data prediction 2. Domain mapping 3. Representation learning 4. Model-based intelligence
101 Representation Learning X Coral Fish Image Compact mental representation
102 Representation Learning compressed image code (vector z) X Image
103 Representation Learning compressed image code (vector z) X ˆX Image Reconstructed image Autoencoder
104 Autoencoder X F ˆX = F(X) Image Reconstructed image
105 X F ˆX = F(X) Image Reconstructed image Fish Coral
106 MNIST manifold learned by a VAE [Kingma & Welling, 2014]
107 Progressive GAN [Karras et al., 2018]
108 Progressive GAN [Karras et al., 2018]
109 Data compression X ˆX Data Data
110 Data prediction X 1 ˆX2 Some data Other data see also Predictive coding, Denoising autoencoders [Vincent et al., 2008]
111 Grayscale image: L channel Semantics? Higherlevel abstraction? Color information: ab channels L ab [Zhang, Isola, Efros, ECCV 2016]
112
113 Instructive failure
114 Instructive failure
115 Deep Net Electrophysiology [Zeiler & Fergus, ECCV 2014] [Zhou et al., ICLR 2015]
116 Stimuli that drive selected neurons (conv5 layer) faces dog faces flowers
117 Representation Learning with Contrastive Predictive Coding [van den Oord, Li, and Vinyals, 2018]
118 Representation Learning with Contrastive Predictive Coding [van den Oord, Li, and Vinyals, 2018] Sound representation Image representation Each color represents a different speaker
119 What can you do with generative models? 1. Data prediction 2. Domain mapping 3. Representation learning 4. Model-based intelligence
120 What can you do with generative models? 1. Data prediction 2. Domain mapping 3. Representation learning 4. Model-based intelligence
121 Model-based intelligence Predict consequences of my actions. Then use that predictive model to plan good actions (or learn good policies). Can be faster, safer, and more abstracted than directly trying actions in real world (or in simulator). Yann LeCun s cake
122 Deep Visual Foresight For Robotic Planning [Finn & Levine 2017] 1. Train model to predict future frame given action 2. Specify target future frame 3. Use prediction model to pick action that maximizes probability of reaching target frame c.f. [Weber et al., 2017], [ ]
123 World Models [Ha & Schmidhuber 2018] 1. Train an RNN to simulate a video game 2. Do policy optimization using the RNN simulate trajectories, rather than the actual game (policy reasons on top of latent space)
124 Incentivizing exploration in reinforcement learning with deep predictive models [Stadie et al., 2015] 1. Train model to predict next state given action and previous state: p(s t+1 s t,a t ) 2. Reward agent for reaching states that surprise it: r t = log p(s t+1 s t,a t ) [Pathak et al., 2017]
125 What can you do with generative models? 1. Data prediction 2. Domain mapping 3. Representation learning 4. Model-based intelligence
126 Thank you!
Learning to Generate Images
Learning to Generate Images Jun-Yan Zhu Ph.D. at UC Berkeley Postdoc at MIT CSAIL Computer Vision before 2012 Cat Features Clustering Pooling Classification [LeCun et al, 1998], [Krizhevsky et al, 2012]
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 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 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 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 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 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 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 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 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 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 informationarxiv: v1 [cs.cv] 4 Apr 2018
arxiv:1804.01523v1 [cs.cv] 4 Apr 2018 Stochastic Adversarial Video Prediction Alex X. Lee, Richard Zhang, Frederik Ebert, Pieter Abbeel, Chelsea Finn, and Sergey Levine University of California, Berkeley
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 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 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] 1 Nov 2018
Examining Performance of Sketch-to-Image Translation Models with Multiclass Automatically Generated Paired Training Data Dichao Hu College of Computing, Georgia Institute of Technology, 801 Atlantic Dr
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 informationGenerative Adversarial Network
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 Generative adversarial
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 informationUnsupervised Deep Learning. James Hays slides from Carl Doersch and Richard Zhang
Unsupervised Deep Learning James Hays slides from Carl Doersch and Richard Zhang Recap from Previous Lecture We saw two strategies to get structured output while using deep learning With object detection,
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 informationA Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation
A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation Alexander H. Liu 1 Yen-Cheng Liu 2 Yu-Ying Yeh 3 Yu-Chiang Frank Wang 1,4 1 National Taiwan University, Taiwan 2 Georgia
More informationComposable Unpaired Image to Image Translation
Composable Unpaired Image to Image Translation Laura Graesser New York University lhg256@nyu.edu Anant Gupta New York University ag4508@nyu.edu Abstract There has been remarkable recent work in unpaired
More informationarxiv: v2 [cs.cv] 16 Dec 2017
CycleGAN, a Master of Steganography Casey Chu Stanford University caseychu@stanford.edu Andrey Zhmoginov Google Inc. azhmogin@google.com Mark Sandler Google Inc. sandler@google.com arxiv:1712.02950v2 [cs.cv]
More informationAmortised MAP Inference for Image Super-resolution. Casper Kaae Sønderby, Jose Caballero, Lucas Theis, Wenzhe Shi & Ferenc Huszár ICLR 2017
Amortised MAP Inference for Image Super-resolution Casper Kaae Sønderby, Jose Caballero, Lucas Theis, Wenzhe Shi & Ferenc Huszár ICLR 2017 Super Resolution Inverse problem: Given low resolution representation
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 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 informationGAN and Feature Representation. Hung-yi Lee
GAN and Feature Representation Hung-yi Lee Outline Generator (Decoder) Discrimi nator + Encoder GAN+Autoencoder x InfoGAN Encoder z Generator Discrimi (Decoder) x nator scalar Discrimi z Generator x scalar
More informationControllable Generative Adversarial Network
Controllable Generative Adversarial Network arxiv:1708.00598v2 [cs.lg] 12 Sep 2017 Minhyeok Lee 1 and Junhee Seok 1 1 School of Electrical Engineering, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul,
More informationIntroduction 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 informationDEEP LEARNING PART THREE - DEEP GENERATIVE MODELS CS/CNS/EE MACHINE LEARNING & DATA MINING - LECTURE 17
DEEP LEARNING PART THREE - DEEP GENERATIVE MODELS CS/CNS/EE 155 - MACHINE LEARNING & DATA MINING - LECTURE 17 GENERATIVE MODELS DATA 3 DATA 4 example 1 DATA 5 example 2 DATA 6 example 3 DATA 7 number of
More informationRecovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform. Xintao Wang Ke Yu Chao Dong Chen Change Loy
Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform Xintao Wang Ke Yu Chao Dong Chen Change Loy Problem enlarge 4 times Low-resolution image High-resolution image Previous
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 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 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 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 informationarxiv: v1 [cs.cv] 8 May 2018
arxiv:1805.03189v1 [cs.cv] 8 May 2018 Learning image-to-image translation using paired and unpaired training samples Soumya Tripathy 1, Juho Kannala 2, and Esa Rahtu 1 1 Tampere University of Technology
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 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 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 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 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 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 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 informationIntroduction to GANs
MedGAN ID-CGAN CoGAN LR-GAN CGAN IcGAN b-gan LS-GAN LAPGAN DiscoGANMPM-GAN AdaGAN LSGAN InfoGAN CatGAN AMGAN igan Introduction to GANs IAN SAGAN McGAN Ian Goodfellow, Staff Research Scientist, Google Brain
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 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 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 informationUnsupervised Image-to-Image Translation with Stacked Cycle-Consistent Adversarial Networks
Unsupervised Image-to-Image Translation with Stacked Cycle-Consistent Adversarial Networks Minjun Li 1,2, Haozhi Huang 2, Lin Ma 2, Wei Liu 2, Tong Zhang 2, Yu-Gang Jiang 1 1 Shanghai Key Lab of Intelligent
More informationSupplementary Material: Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos
Supplementary Material: Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos Kihyuk Sohn 1 Sifei Liu 2 Guangyu Zhong 3 Xiang Yu 1 Ming-Hsuan Yang 2 Manmohan Chandraker 1,4 1 NEC Labs
More informationToward Multimodal Image-to-Image Translation
Toward Multimodal Image-to-Image Translation Jun-Yan Zhu UC Berkeley Richard Zhang UC Berkeley Deepak Pathak UC Berkeley Trevor Darrell UC Berkeley Alexei A. Efros UC Berkeley Oliver Wang Adobe Research
More informationDay 3 Lecture 1. Unsupervised Learning
Day 3 Lecture 1 Unsupervised Learning Semi-supervised and transfer learning Myth: you can t do deep learning unless you have a million labelled examples for your problem. Reality You can learn useful representations
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 informationUnsupervised Cross-Domain Deep Image Generation
Unsupervised Cross-Domain Deep Image Generation Yaniv Taigman, Adam Polyak, Lior Wolf Facebook AI Research (FAIR) Tel Aviv Supervised Learning; {Xi, yi} àf Face Recognition (DeepFace / FAIR) Kaiming et
More informationResembled Generative Adversarial Networks: Two Domains with Similar Attributes
DUHYEON BANG, HYUNJUNG SHIM: RESEMBLED GAN 1 Resembled Generative Adversarial Networks: Two Domains with Similar Attributes Duhyeon Bang duhyeonbang@yonsei.ac.kr Hyunjung Shim kateshim@yonsei.ac.kr School
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 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 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 informationOne Network to Solve Them All Solving Linear Inverse Problems using Deep Projection Models
One Network to Solve Them All Solving Linear Inverse Problems using Deep Projection Models [Supplemental Materials] 1. Network Architecture b ref b ref +1 We now describe the architecture of the networks
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 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 informationUnsupervised Image-to-Image Translation Networks
Unsupervised Image-to-Image Translation Networks Ming-Yu Liu, Thomas Breuel, Jan Kautz NVIDIA {mingyul,tbreuel,jkautz}@nvidia.com Abstract Unsupervised image-to-image translation aims at learning a joint
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 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 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 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 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 informationExtracting and Composing Robust Features with Denoising Autoencoders
Presenter: Alexander Truong March 16, 2017 Extracting and Composing Robust Features with Denoising Autoencoders Pascal Vincent, Hugo Larochelle, Yoshua Bengio, Pierre-Antoine Manzagol 1 Outline Introduction
More informationarxiv: v1 [cs.cv] 30 Jul 2017
Virtual PET Images from CT Data Using Deep Convolutional Networks: Initial Results Avi Ben-Cohen 1, Eyal Klang 2, Stephen P. Raskin 2, Michal Marianne Amitai 2, and Hayit Greenspan 1 arxiv:1707.09585v1
More informationAdversarial Machine Learning
MedGAN Progressive GAN CoGAN LR-GAN CGAN IcGAN BIM LS-GAN AffGAN LAPGAN DiscoGANMPM-GAN AdaGAN LSGAN InfoGAN ATN FGSM igan IAN Adversarial Machine Learning McGAN Ian Goodfellow, Staff Research Scientist,
More informationIDENTIFYING ANALOGIES ACROSS DOMAINS
IDENTIFYING ANALOGIES ACROSS DOMAINS Yedid Hoshen 1 and Lior Wolf 1,2 1 Facebook AI Research 2 Tel Aviv University ABSTRACT Identifying analogies across domains without supervision is an important task
More informationAuto-Encoding Variational Bayes
Auto-Encoding Variational Bayes Diederik P (Durk) Kingma, Max Welling University of Amsterdam Ph.D. Candidate, advised by Max Durk Kingma D.P. Kingma Max Welling Problem class Directed graphical model:
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 informationA Method for Restoring the Training Set Distribution in an Image Classifier
A Method for Restoring the Training Set Distribution in an Image Classifier An Extension of the Classifier-To-Generator Method Alexey Chaplygin & Joshua Chacksfield Data Science Research Group, Department
More informationGenerative Face Completion
Generative Face Completion Yijun Li 1, Sifei Liu 1, Jimei Yang 2, and Ming-Hsuan Yang 1 1 University of California, Merced 2 Adobe Research {yli62,sliu32,mhyang}@ucmerced.edu jimyang@adobe.com Abstract
More informationGenerative Semantic Manipulation with Contrasting GAN
Generative Semantic Manipulation with Contrasting GAN Xiaodan Liang, Hao Zhang, Eric P. Xing Carnegie Mellon University and Petuum Inc. {xiaodan1, hao, epxing}@cs.cmu.edu arxiv:1708.00315v1 [cs.cv] 1 Aug
More informationShadow Detection with Conditional Generative Adversarial Networks
Shadow Detection with Conditional Generative Adversarial Networks Vu Nguyen, Tomas F. Yago Vicente, Maozheng Zhao, Minh Hoai, Dimitris Samaras Stony Brook University, Stony Brook, NY 11794, USA {vhnguyen,
More informationLecture 3 GANs and Their Applications in Image Generation
Lecture 3 GANs and Their Applications in Image Generation Lin ZHANG, PhD School of Software Engineering Tongji University Fall 2017 Outline Introduction Theoretical Part Application Part Existing Implementations
More informationarxiv: v1 [cs.cv] 19 Apr 2017
Generative Face Completion Yijun Li 1, Sifei Liu 1, Jimei Yang 2, and Ming-Hsuan Yang 1 1 University of California, Merced 2 Adobe Research {yli62,sliu32,mhyang}@ucmerced.edu jimyang@adobe.com arxiv:1704.05838v1
More informationFace Transfer with Generative Adversarial Network
Face Transfer with Generative Adversarial Network Runze Xu, Zhiming Zhou, Weinan Zhang, Yong Yu Shanghai Jiao Tong University We explore the impact of discriminators with different receptive field sizes
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 informationPixel-level Generative Model
Pixel-level Generative Model Generative Image Modeling Using Spatial LSTMs (2015NIPS) L. Theis and M. Bethge University of Tübingen, Germany Pixel Recurrent Neural Networks (2016ICML) A. van den Oord,
More informationarxiv: v2 [cs.cv] 2 Dec 2017
Learning to Generate Time-Lapse Videos Using Multi-Stage Dynamic Generative Adversarial Networks Wei Xiong, Wenhan Luo, Lin Ma, Wei Liu, and Jiebo Luo Department of Computer Science, University of Rochester,
More informationUnsupervised Person Image Synthesis in Arbitrary Poses
Unsupervised Person Image Synthesis in Arbitrary Poses Albert Pumarola Antonio Agudo Alberto Sanfeliu Francesc Moreno-Noguer Institut de Robòtica i Informàtica Industrial (CSIC-UPC) 08028, Barcelona, Spain
More informationFully Convolutional Networks for Semantic Segmentation
Fully Convolutional Networks for Semantic Segmentation Jonathan Long* Evan Shelhamer* Trevor Darrell UC Berkeley Chaim Ginzburg for Deep Learning seminar 1 Semantic Segmentation Define a pixel-wise labeling
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 informationRadialGAN: Leveraging multiple datasets to improve target-specific predictive models using Generative Adversarial Networks
RadialGAN: Leveraging multiple datasets to improve target-specific predictive models using Generative Adversarial Networs Jinsung Yoon 1 James Jordon 2 Mihaela van der Schaar 1 2 3 Abstract Training complex
More informationVisual Prediction with Action Feedback
Visual Prediction with Action Feedback Pascal Pompey Stanford, cs231n papompey@stanford.edu Sudeep Sudhir Jain Stanford, cs231n sudeepj@stanford.edu Andrei Bajenov Stanford, cs231n abajenov@stanford.edu
More informationNAM: Non-Adversarial Unsupervised Domain Mapping
NAM: Non-Adversarial Unsupervised Domain Mapping Yedid Hoshen 1 and Lior Wolf 1,2 1 Facebook AI Research 2 Tel Aviv University Abstract. Several methods were recently proposed for the task of translating
More informationTowards Automatic Icon Design using Machine Learning
Moses Soh (msoh) moses.soh@gmail.com Abstract We propose a deep learning approach for automatic colorization of icons. The system maps grayscale outlines to fully colored and stylized icons using a Convolutional
More informationDual Learning of the Generator and Recognizer for Chinese Characters
2017 4th IAPR Asian Conference on Pattern Recognition Dual Learning of the Generator and Recognizer for Chinese Characters Yixing Zhu, Jun Du and Jianshu Zhang National Engineering Laboratory for Speech
More informationSupervised Learning of Classifiers
Supervised Learning of Classifiers Carlo Tomasi Supervised learning is the problem of computing a function from a feature (or input) space X to an output space Y from a training set T of feature-output
More informationGenerating Images with Perceptual Similarity Metrics based on Deep Networks
Generating Images with Perceptual Similarity Metrics based on Deep Networks Alexey Dosovitskiy and Thomas Brox University of Freiburg {dosovits, brox}@cs.uni-freiburg.de Abstract We propose a class of
More informationCOMP 551 Applied Machine Learning Lecture 16: Deep Learning
COMP 551 Applied Machine Learning Lecture 16: Deep Learning Instructor: Ryan Lowe (ryan.lowe@cs.mcgill.ca) Slides mostly by: Class web page: www.cs.mcgill.ca/~hvanho2/comp551 Unless otherwise noted, all
More informationInstance Map based Image Synthesis with a Denoising Generative Adversarial Network
Instance Map based Image Synthesis with a Denoising Generative Adversarial Network Ziqiang Zheng, Chao Wang, Zhibin Yu*, Haiyong Zheng, Bing Zheng College of Information Science and Engineering Ocean University
More informationarxiv: v3 [cs.cv] 13 Jul 2017
Semantic Image Inpainting with Deep Generative Models Raymond A. Yeh, Chen Chen, Teck Yian Lim, Alexander G. Schwing, Mark Hasegawa-Johnson, Minh N. Do University of Illinois at Urbana-Champaign {yeh17,
More informationLearning to generate 3D shapes
Learning to generate 3D shapes Subhransu Maji College of Information and Computer Sciences University of Massachusetts, Amherst http://people.cs.umass.edu/smaji August 10, 2018 @ Caltech Creating 3D shapes
More informationBayesian model ensembling using meta-trained recurrent neural networks
Bayesian model ensembling using meta-trained recurrent neural networks Luca Ambrogioni l.ambrogioni@donders.ru.nl Umut Güçlü u.guclu@donders.ru.nl Yağmur Güçlütürk y.gucluturk@donders.ru.nl Julia Berezutskaya
More informationUnpaired Multi-Domain Image Generation via Regularized Conditional GANs
Unpaired Multi-Domain Image Generation via Regularized Conditional GANs Xudong Mao and Qing Li Department of Computer Science, City University of Hong Kong xudong.xdmao@gmail.com, itqli@cityu.edu.hk information
More informationA GAN framework for Instance Segmentation using the Mutex Watershed Algorithm
A GAN framework for Instance Segmentation using the Mutex Watershed Algorithm Mandikal Vikram National Institute of Technology Karnataka, India 15it217.vikram@nitk.edu.in Steffen Wolf HCI/IWR, University
More information