GANs for Exploiting Unlabeled Data. Presented by: Uriya Pesso Nimrod Gilboa Markevich

Size: px
Start display at page:

Download "GANs for Exploiting Unlabeled Data. Presented by: Uriya Pesso Nimrod Gilboa Markevich"

Transcription

1 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

2 [ ] you could not see an article in the press [about AI] without the picture being Terminator. It was always Terminator, 100 percent. And you see less of that now, and that s a good thing Yann LeCun, Director, Facebook AI

3 Generative Adversarial Networks is the most interesting idea in the last ten years in machine learning. Yann LeCun, Director, Facebook AI

4 Presentation Overview o Motivation o Intro to GANs o Paper 1: Semi Supervised Learning o Paper 2: Simulated and Unsupervised Learning o Conclusion

5 Motivation Compensating for Missing Data o Labeled data is expensive (time, money, effort) o Unlabeled data is cheaper o Unlabeled data still contains information o How can we utilize unlabeled data? o GANs! We will present two methods from two papers

6 Generative Adversarial Networks o What does it do? Generate synthetic data that is indistinguishable from real data o Uses Super-Resolution Text-to-Speech Art Exploiting unlabeled data (for training other networks)

7 Generative Adversarial Networks o Adversarial Networks Opponent Networks Generator Create realistic samples Discriminator Distinguish generated from real o Compete with each other o The only labels are Real/Fake o Gradient Descent, Train in turns Train D Train G

8 Loss Functions o Cross-entropy loss function o o o o o Dx G z D G L L D G, x p x D D G probability of x being real generated sample from noise z network parameters discriminator loss function Generator loss function data z z L, log D log 1 D G ~ ~noise L G D L

9 Improved Techniques for Training GANs Tim Salimans, Ian Goodfellow, Wojciech Zaremba, Vicki Cheung, Alec Radford, Xi Chen

10 Semi-Supervised Learning - Idea o Objective: We want to train a classifier o We have: labeled data => supervised learning unlabeled data => unsupervised learning o Combining labeled and unlabeled data => semi-supervised

11 Semi-Supervised Learning - Idea o Combine GAN and classifier networks. o Add a label for the synthetic data - K+1 Supervised x Classifier y y 1,.., K Unsupervised z G Generator x* G(z) D Discriminator y y Generated,Real Semi-Supervised z G Generator x or x* G(z) D Classifier y y 1,.., K, K 1

12 Semi-Supervised Loss Function o Cross entropy loss over two distributions L x x log p y x, y~ p (, y) model data L log p y, y K 1 supervised x, y~ p ( x, y) model x data data G log p y K 1 x G x L log 1 p y K 1 log p y K 1 unsupervised x~ p ( x) model x~ model x~ model x supervised unsupervised L L pdata x, y - is the probability distribution of the input data. log pmodel y x - is the model probability distribution to predict label y from K labels given data X.

13 Supervised Loss o Where: p x x Classifier y data - is the probability distribution of the input data. log p y x - is the model probability distribution to predict label y from K labels given data X. model y 1,.., K, K 1 L log p y, y K 1 x x x suprvised, y~ p (, y) model data

14 Supervised Loss x Classifier y data y 1,.., K L x y x log p y x suprvised, ~ p (, y) model o pdata x - is the probability distribution of the input data. o log p y x - is the model probability distribution to predict label y from K labels given data X. model

15 Unsupervised Loss z G Generator x p x D D G data x G(z) D Discriminator y z z L, log D log 1 D G D( x) 1 p ( y K 1 x) model ~ ~noise y Generated,Real L log(1 p ( y K 1 x)) log( p ( y K 1 x)) unsuprvised x~ p ( x) model x~ G( z) model data o p ( y K 1 x) model the probability distribution to predict that the data x is unreal.

16 Punchline Classifier GAN L L L supervised unsupervised L log p y, y K 1 supervised x, y~ p ( x, y) model data data x x G x L log 1 p y K 1 log p y K 1 unsupervised x~ p ( x) model x~ model

17 Semi-Supervised Learning Intuition o How does a classifier benefit from unlabeled data? o From the unlabeled data, the classifier learns to focus on the right features, thus reducing generalization error Number Not Number

18 Results

19 Results - MNIST Generated Real

20 Results - MNIST (*) (*) number of labeled samples per class the rest are unlabeled train size: 60,000 test size: 10,000

21 Results CIFAR10 CIFAR10 Generated

22 Results Imagenet DCGAN (Not Ours )

23 Results Imagenet Our Method

24 Learning from Simulated and Unsupervised Images through Adversarial Training CVPR 2017 Best Paper Award Avish Shrivastava, Tomas Pfister, Oncel Tuzel, Josh Susskind, Wenda Wang, Russ Webb Apple Inc

25 Motivation o Labeled data is expensive (time, money, effort) o Simulated data is cheap o Alternatively, we could learn using simulated data Simulator Data Set of Labeled Synthetic Images NN

26 Motivation o Drawback: Simulated data may have artifacts o We want more realistic synthetic data o We have unlabeled data o Let s build a refiner

27 Refiner Network / S+U Learning Simulator Data Set of Labeled Synthetic Images

28 SimGAN Architecture

29 SimGAN Architecture

30 Loss Function Discriminator o Adversarial Loss x p D D R real x L, log D log 1 D R x~ x x~ p x simulated o o o o Dx Rx D R L D, probability of x being real refined simulated image network parameters discriminator loss function o o preal psimulated x x pdf of real images pdf of simulated images

31 Loss Function Refiner o Refiner has two goals Generate realistic samples Adversarial Loss Preserve the label Self-regularization, x~ p x R D R L simulated real reg real log D Rx Rx x reg 1 o o o R x refined simulated image o p x pdf of simulated images D R, network parameters simulated R L refiner loss function o weight

32 Minor Improvements o Are we done? o Almost. There are two additional mechanisms: Local Adversarial Loss Using a History of Refined Images

33 Local Adversarial Loss o Discriminator outputs wxh probability map o The adversarial loss is the sum of the loss over the local patches o Localization restrains artifacts the refined image should look real in every patch

34 Local Adversarial Loss

35 Using a History of Refined Images o Problem Discriminator only focuses on the latest refined images Refiner might reintroduce artifacts that the discriminator has forgotten o Solution Buffer refined images

36 Using a History of Refined Images

37 Using a History of Refined Images

38 Results

39 Stages for SimGAN Performance Evaluation 1) Train SimGAN 2) Generate Synthetic Refined Dataset => Qualitative Results 3) Train NN (Estimator) with the Dataset 4) Test NN (Estimator) => Quantitative Results

40 Results - Performance Evaluation using Gaze Estimatior o Simulated images UnityEyes, 1.2M o Real Labeled Dataset MPIIGaze Dataset, 214K Gaze Estimator

41 Process 1. Train SimGAN UnityEyes MPIIGaze (without labels)

42 Process 2. Trained Refiner Generates DB SimGAN Refiner Data Set of Labeled Synthetic Images Data Set of Labeled Refined Synthetic Images

43 Qualitative Results

44 Process 3. Train Gaze Estimator Gaze Estimator Data Set of Labeled Synthetic Refined Images

45 Process 4. Test Gaze Estimator Gaze Estimator CNN Data Set of Real Images Output

46 Quantitative Results

47 Results Performance Evaluation using Hand Pose Estimatior o NYU hand pose dataset, 73,000 training, 8,000 testing Hand Pose Estimator Depth Image Selected Points Coordinates

48 Qualitative Result

49 Quantitative Results

50 Quantitative Results

51 Conclusion o Generative Adversarial Networks are awesome Generator vs. Discriminator o Unlabeled data can be used for supervised learning Semi-Supervised Learning Classifier combined with Discriminator Train GAN with labeled and unlabeled data Simulated and Unsupervised Learning Train Refiner Generate large synthetic refined dataset

S+U Learning through ANs - Pranjit Kalita

S+U Learning through ANs - Pranjit Kalita S+U Learning through ANs - Pranjit Kalita - (from paper) Learning from Simulated and Unsupervised Images through Adversarial Training - Ashish Shrivastava, Tomas Pfister, Oncel Tuzel, Josh Susskind, Wenda

More information

Lecture 3 GANs and Their Applications in Image Generation

Lecture 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 information

Generative Adversarial Networks (GANs) Ian Goodfellow, Research Scientist MLSLP Keynote, San Francisco

Generative 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 information

arxiv: v1 [cs.cv] 17 Nov 2016

arxiv: 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 information

arxiv: v2 [cs.cv] 19 Jul 2017

arxiv: v2 [cs.cv] 19 Jul 2017 This paper has been submitted for publication on November 15, 2016. Learning from Simulated and Unsupervised Images through Adversarial Training Ashish Shrivastava, Tomas Pfister, Oncel Tuzel, Josh Susskind,

More information

Lab meeting (Paper review session) Stacked Generative Adversarial Networks

Lab 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 information

Alternatives to Direct Supervision

Alternatives 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 information

(University Improving of Montreal) Generative Adversarial Networks with Denoising Feature Matching / 17

(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 information

Introduction to Generative Adversarial Networks

Introduction 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 information

SYNTHESIS 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 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 information

Introduction to Generative Adversarial Networks

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 information

Unsupervised Learning

Unsupervised 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 information

Introduction to GAN. Generative Adversarial Networks. Junheng(Jeff) Hao

Introduction 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 information

Progress on Generative Adversarial Networks

Progress 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 information

Learning to generate 3D shapes

Learning 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 information

Lecture 19: Generative Adversarial Networks

Lecture 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 information

Image Restoration with Deep Generative Models

Image 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 information

GAN Frontiers/Related Methods

GAN 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 information

arxiv: v1 [stat.ml] 19 Aug 2017

arxiv: 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 information

GENERATIVE ADVERSARIAL NETWORKS (GAN) Presented by Omer Stein and Moran Rubin

GENERATIVE 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 information

Generative Adversarial Network

Generative 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 information

Inverting The Generator Of A Generative Adversarial Network

Inverting 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 information

Semi Supervised Semantic Segmentation Using Generative Adversarial Network

Semi 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 information

One 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 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 information

GENERATIVE ADVERSARIAL NETWORK-BASED VIR-

GENERATIVE 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 information

arxiv: v1 [cs.cv] 28 Mar 2017

arxiv: v1 [cs.cv] 28 Mar 2017 Semi and Weakly Supervised Semantic Segmentation Using Generative Adversarial Network arxiv:1703.09695v1 [cs.cv] 28 Mar 2017 Nasim Souly Center for Research in Computer Vision(CRCV) University of Central

More information

Autoencoders. Stephen Scott. Introduction. Basic Idea. Stacked AE. Denoising AE. Sparse AE. Contractive AE. Variational AE GAN.

Autoencoders. 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 information

Introduction to GAN. Generative Adversarial Networks. Junheng(Jeff) Hao

Introduction 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 information

Lip Movement Synthesis from Text

Lip 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 information

Defense Data Generation in Distributed Deep Learning System Se-Yoon Oh / ADD-IDAR

Defense Data Generation in Distributed Deep Learning System Se-Yoon Oh / ADD-IDAR Defense Data Generation in Distributed Deep Learning System Se-Yoon Oh / 2017. 10. 31 syoh@add.re.kr Page 1/36 Overview 1. Introduction 2. Data Generation Synthesis 3. Distributed Deep Learning 4. Conclusions

More information

arxiv: v1 [cs.ne] 11 Jun 2018

arxiv: 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

Conditional Generative Adversarial Networks for Particle Physics

Conditional 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 information

COMP 551 Applied Machine Learning Lecture 16: Deep Learning

COMP 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 information

A New CGAN Technique for Constrained Topology Design Optimization. Abstract

A 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 information

Introduction to GANs

Introduction 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 information

Class-Splitting Generative Adversarial Networks

Class-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 information

CS230: Lecture 4 Attacking Networks with Adversarial Examples - Generative Adversarial Networks

CS230: Lecture 4 Attacking Networks with Adversarial Examples - Generative Adversarial Networks Go to www.menti.com and use the code 91 41 37 CS230: Lecture 4 Attacking Networks with Adversarial Examples - Generative Adversarial Networks Kian Katanforoosh Today s outline I. Attacking NNs with Adversarial

More information

Generative 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 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 information

Bidirectional GAN. Adversarially Learned Inference (ICLR 2017) Adversarial Feature Learning (ICLR 2017)

Bidirectional 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 information

arxiv: v1 [eess.sp] 23 Oct 2018

arxiv: 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 information

Deep Fakes using Generative Adversarial Networks (GAN)

Deep 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 information

arxiv: v1 [cs.cv] 1 Aug 2017

arxiv: 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 information

Semi-Supervised Generative Adversarial Nets with Multiple Generators for SAR Image Recognition

Semi-Supervised Generative Adversarial Nets with Multiple Generators for SAR Image Recognition sensors Article Semi-Supervised Generative Adversarial Nets with Multiple Generators for SAR Image Recognition Fei Gao 1, *, Fei Ma 1 ID, Jun Wang 1, Jinping Sun 1 ID, Erfu Yang 2 and Huiyu Zhou 3 1 School

More information

arxiv: v1 [cs.cv] 5 Jul 2017

arxiv: 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 information

Improved Techniques for Training GANs

Improved Techniques for Training GANs Improved Techniques for Training GANs Tim Salimans tim@openai.com Ian Goodfellow ian@openai.com Wojciech Zaremba woj@openai.com Vicki Cheung vicki@openai.com Alec Radford alec@openai.com Xi Chen peter@openai.com

More information

GENERATIVE ADVERSARIAL NETWORKS FOR IMAGE STEGANOGRAPHY

GENERATIVE 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 information

Learning to generate with adversarial networks

Learning 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 information

SEMI-SUPERVISED LEARNING WITH GANS:

SEMI-SUPERVISED LEARNING WITH GANS: SEMI-SUPERVISED LEARNING WITH GANS: REVISITING MANIFOLD REGULARIZATION Bruno Lecouat,1,2 Chuan-Sheng Foo,2, Houssam Zenati 2,3, Vijay R. Chandrasekhar 2,4 1 Télécom ParisTech, bruno.lecouat@gmail.com.

More information

Deep Learning for Visual Manipulation and Synthesis

Deep 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 information

(x,y) G(x,y) Generating a Fusion Image: One s Identity and Another s Shape

(x,y) G(x,y) Generating a Fusion Image: One s Identity and Another s Shape enerating a Fusion Image: One s Identity and Another s Shape Donggyu Joo Doyeon Kim Junmo Kim School of Electrical Engineering, KAIST, South Korea {jdg105, doyeon kim, junmo.kim}@kaist.ac.kr Abstract enerating

More information

Unsupervised Image-to-Image Translation Networks

Unsupervised 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 information

What was Monet seeing while painting? Translating artworks to photo-realistic images M. Tomei, L. Baraldi, M. Cornia, R. Cucchiara

What was Monet seeing while painting? Translating artworks to photo-realistic images M. Tomei, L. Baraldi, M. Cornia, R. Cucchiara What was Monet seeing while painting? Translating artworks to photo-realistic images M. Tomei, L. Baraldi, M. Cornia, R. Cucchiara COMPUTER VISION IN THE ARTISTIC DOMAIN The effectiveness of Computer Vision

More information

AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimation

AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimation AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimation Introduction Supplementary material In the supplementary material, we present additional qualitative results of the proposed AdaDepth

More information

An Empirical Study of Generative Adversarial Networks for Computer Vision Tasks

An 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 information

Unsupervised Domain Adaptation by Backpropagation. Chih-Hui Ho, Xingyu Gu, Yuan Qi

Unsupervised Domain Adaptation by Backpropagation. Chih-Hui Ho, Xingyu Gu, Yuan Qi Unsupervised Domain Adaptation by Backpropagation Chih-Hui Ho, Xingyu Gu, Yuan Qi Problems Deep network: requires massive labeled training data. Labeled data: Available sometimes: Image recognition Speech

More information

Generative Adversarial Nets. Priyanka Mehta Sudhanshu Srivastava

Generative 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 information

arxiv: v1 [cs.mm] 16 Mar 2017

arxiv: 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 information

GAN Related Works. CVPR 2018 & Selective Works in ICML and NIPS. Zhifei Zhang

GAN Related Works. CVPR 2018 & Selective Works in ICML and NIPS. Zhifei Zhang GAN Related Works CVPR 2018 & Selective Works in ICML and NIPS Zhifei Zhang Generative Adversarial Networks (GANs) 9/12/2018 2 Generative Adversarial Networks (GANs) Feedforward Backpropagation Real? z

More information

Visual Recommender System with Adversarial Generator-Encoder Networks

Visual 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 information

arxiv: v1 [cs.cv] 7 Mar 2018

arxiv: 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 information

Generative Adversarial Networks (GANs)

Generative 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 information

Multi-Modal Generative Adversarial Networks

Multi-Modal Generative Adversarial Networks Multi-Modal Generative Adversarial Networks By MATAN BEN-YOSEF Under the supervision of PROF. DAPHNA WEINSHALL Faculty of Computer Science and Engineering THE HEBREW UNIVERSITY OF JERUSALEM A thesis submitted

More information

arxiv: v2 [cs.cv] 1 Dec 2017

arxiv: v2 [cs.cv] 1 Dec 2017 Discriminative Region Proposal Adversarial Networks for High-Quality Image-to-Image Translation Chao Wang Haiyong Zheng Zhibin Yu Ziqiang Zheng Zhaorui Gu Bing Zheng Ocean University of China Qingdao,

More information

arxiv: v2 [cs.cv] 26 Mar 2017

arxiv: 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 information

Deep Generative Models and a Probabilistic Programming Library

Deep 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 information

Mode Regularized Generative Adversarial Networks

Mode Regularized Generative Adversarial Networks Mode Regularized Generative Adversarial Networks Tong Che 1 Yanran Li 2 Athul Paul Jacob 3 Yoshua Bengio 1 Wenjie Li 2 1 Montreal Institute for Learning Algorithms, Universite de Montreal, Montreal, Canada

More information

Learning Adversarial 3D Model Generation with 2D Image Enhancer

Learning Adversarial 3D Model Generation with 2D Image Enhancer The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18) Learning Adversarial 3D Model Generation with 2D Image Enhancer Jing Zhu, Jin Xie, Yi Fang NYU Multimedia and Visual Computing Lab

More information

Recovering 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 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 information

IVE-GAN: INVARIANT ENCODING GENERATIVE AD-

IVE-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 information

Generative Adversarial Text to Image Synthesis

Generative 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 information

Adversarially Learned Inference

Adversarially 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 information

Unsupervised Cross-Domain Deep Image Generation

Unsupervised 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 information

arxiv: v1 [cs.cv] 8 Jan 2019

arxiv: 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 information

Progressive Generative Hashing for Image Retrieval

Progressive 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 information

Supplementary Material: Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos

Supplementary 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 information

From attribute-labels to faces: face generation using a conditional generative adversarial network

From attribute-labels to faces: face generation using a conditional generative adversarial network From attribute-labels to faces: face generation using a conditional generative adversarial network Yaohui Wang 1,2, Antitza Dantcheva 1,2, and Francois Bremond 1,2 1 Inria, Sophia Antipolis, France 2 Université

More information

Deep Model Adaptation using Domain Adversarial Training

Deep Model Adaptation using Domain Adversarial Training Deep Model Adaptation using Domain Adversarial Training Victor Lempitsky, joint work with Yaroslav Ganin Skolkovo Institute of Science and Technology ( Skoltech ) Moscow region, Russia Deep supervised

More information

Day 3 Lecture 1. Unsupervised Learning

Day 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 information

Building an Automatic Sprite Generator with Deep Convolutional Generative Adversarial Networks

Building 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 information

Ways of Conditioning Generative Adversarial Networks

Ways 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 information

Countering Adversarial Images using Input Transformations

Countering Adversarial Images using Input Transformations Countering Adversarial Images using Input Transformations Chuan Guo, Mayank Rana, Moustapha Cisse, Laurens Van Der Maaten Presented by Hari Venugopalan, Zainul Abi Din Motivation: Why is this a hard problem

More information

Neural Networks. Single-layer neural network. CSE 446: Machine Learning Emily Fox University of Washington March 10, /10/2017

Neural Networks. Single-layer neural network. CSE 446: Machine Learning Emily Fox University of Washington March 10, /10/2017 3/0/207 Neural Networks Emily Fox University of Washington March 0, 207 Slides adapted from Ali Farhadi (via Carlos Guestrin and Luke Zettlemoyer) Single-layer neural network 3/0/207 Perceptron as a neural

More information

Adversarial Machine Learning

Adversarial 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 information

arxiv: v1 [cs.cv] 7 Jun 2018

arxiv: v1 [cs.cv] 7 Jun 2018 CapsGAN: Using Dynamic Routing for Generative Adversarial Networks arxiv:1806.03968v1 [cs.cv] 7 Jun 2018 Raeid Saqur Department of Computer Science University of Toronto raeidsaqur@cs.toronto.edu Abstract

More information

Quantitative Evaluation of Generative Adversarial Networks and Improved Training Techniques

Quantitative Evaluation of Generative Adversarial Networks and Improved Training Techniques Quantitative Evaluation of Generative Adversarial Networks and Improved Training Techniques by Yadong Li to obtain the degree of Master of Science at the Delft University of Technology, to be defended

More information

Variational Autoencoders. Sargur N. Srihari

Variational 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

Generalized Loss-Sensitive Adversarial Learning with Manifold Margins

Generalized Loss-Sensitive Adversarial Learning with Manifold Margins Generalized Loss-Sensitive Adversarial Learning with Manifold Margins Marzieh Edraki and Guo-Jun Qi Laboratory for MAchine Perception and LEarning (MAPLE) http://maple.cs.ucf.edu/ University of Central

More information

Metric Learning for Large-Scale Image Classification:

Metric Learning for Large-Scale Image Classification: Metric Learning for Large-Scale Image Classification: Generalizing to New Classes at Near-Zero Cost Florent Perronnin 1 work published at ECCV 2012 with: Thomas Mensink 1,2 Jakob Verbeek 2 Gabriela Csurka

More information

IMPROVING SAR AUTOMATIC TARGET RECOGNITION USING SIMULATED IMAGES UNDER DEEP RESIDUAL REFINEMENTS

IMPROVING SAR AUTOMATIC TARGET RECOGNITION USING SIMULATED IMAGES UNDER DEEP RESIDUAL REFINEMENTS IMPROVING SAR AUTOMATIC TARGET RECOGNITION USING SIMULATED IMAGES UNDER DEEP RESIDUAL REFINEMENTS Miriam Cha 1,2, Arjun Majumdar 2, H.T. Kung 1, Jarred Barber 2 1 Harvard University, 2 MIT Lincoln Laboratory

More information

Capsule Networks. Eric Mintun

Capsule Networks. Eric Mintun Capsule Networks Eric Mintun Motivation An improvement* to regular Convolutional Neural Networks. Two goals: Replace max-pooling operation with something more intuitive. Keep more info about an activated

More information

Geometric Enclosing Networks

Geometric Enclosing Networks Geometric Enclosing Networks Trung Le, Hung Vu, Tu Dinh Nguyen and Dinh Phung Faculty of Information Technology, Monash University Center for Pattern Recognition and Data Analytics, Deakin University,

More information

Deep Learning with Tensorflow AlexNet

Deep Learning with Tensorflow   AlexNet Machine Learning and Computer Vision Group Deep Learning with Tensorflow http://cvml.ist.ac.at/courses/dlwt_w17/ AlexNet Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton, "Imagenet classification

More information

ANY image data set only covers a fixed domain. This

ANY 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 information

arxiv: v5 [cs.cv] 16 May 2018

arxiv: 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 information

When Big Datasets are Not Enough: The need for visual virtual worlds.

When Big Datasets are Not Enough: The need for visual virtual worlds. When Big Datasets are Not Enough: The need for visual virtual worlds. Alan Yuille Bloomberg Distinguished Professor Departments of Cognitive Science and Computer Science Johns Hopkins University Computational

More information

Computer Vision Lecture 16

Computer Vision Lecture 16 Computer Vision Lecture 16 Deep Learning for Object Categorization 14.01.2016 Bastian Leibe RWTH Aachen http://www.vision.rwth-aachen.de leibe@vision.rwth-aachen.de Announcements Seminar registration period

More information

arxiv: v1 [cs.lg] 6 Nov 2018

arxiv: v1 [cs.lg] 6 Nov 2018 Student s t-generative Adversarial Networks arxiv:1811.013v1 [cs.lg] 6 Nov 018 Jinxuan Sun sunjinxuan1014@gmail.com Yongbin Liu liuyongbin@stu.ouc.edu.cn Guoqiang Zhong gqzhong@ouc.edu.cn Tao Li 140337104@qq.com

More information

POINT CLOUD DEEP LEARNING

POINT CLOUD DEEP LEARNING POINT CLOUD DEEP LEARNING Innfarn Yoo, 3/29/28 / 57 Introduction AGENDA Previous Work Method Result Conclusion 2 / 57 INTRODUCTION 3 / 57 2D OBJECT CLASSIFICATION Deep Learning for 2D Object Classification

More information

Machine Learning With Python. Bin Chen Nov. 7, 2017 Research Computing Center

Machine Learning With Python. Bin Chen Nov. 7, 2017 Research Computing Center Machine Learning With Python Bin Chen Nov. 7, 2017 Research Computing Center Outline Introduction to Machine Learning (ML) Introduction to Neural Network (NN) Introduction to Deep Learning NN Introduction

More information

CENG 783. Special topics in. Deep Learning. AlchemyAPI. Week 11. Sinan Kalkan

CENG 783. Special topics in. Deep Learning. AlchemyAPI. Week 11. Sinan Kalkan CENG 783 Special topics in Deep Learning AlchemyAPI Week 11 Sinan Kalkan TRAINING A CNN Fig: http://www.robots.ox.ac.uk/~vgg/practicals/cnn/ Feed-forward pass Note that this is written in terms of the

More information