Unsupervised Cross-Domain Deep Image Generation
|
|
|
- Tabitha French
- 6 years ago
- Views:
Transcription
1 Unsupervised Cross-Domain Deep Image Generation Yaniv Taigman, Adam Polyak, Lior Wolf Facebook AI Research (FAIR) Tel Aviv
2 Supervised Learning; {Xi, yi} àf Face Recognition (DeepFace / FAIR) Kaiming et al. (MASK R-CNN / FAIR ) Speech Recognition (IBM, Google, MSFT & Baidu) Mobileye Seq2Seq for Machine Translation, Quick-Reply, etc. (Sutskever et al.)
3 What s still impossible / limited? Human-Machine communication, dialog systems ( Chatbots ) Answering free-form questions by memorizing the Web Teaching robots to learn everything. Instead of requiring millions of {X, y} samples, maybe learn to transfer knowledge between domains, modalities. This talk: Learning to transfer samples between visual domains
4 Latest Trends 3. Supervised GANs Image-to-Image Translation with Conditional Adversarial Nets Isola et al. Fully supervised (pairs given) VIDEO OF FACEBOOK STYLE TRANSFER 2. Domain adaptation Domain-adversarial training of neural networks Ganin et al. Not generative 1. Style Transfer (Gatys et al.) Replaces statistics/texture given an exemplar Not semantic
5 Latest Trends 3. Supervised GANs Image-to-Image Translation with Conditional Adversarial Nets Isola et al. Fully supervised (pairs given) 2. Domain adaptation and Domain Confusion Domain-adversarial training of neural networks Ganin et al. Not generative 1. Style Transfer (Gatys et al.) Replaces statistics/texture given an exemplar Not semantic
6 Latest Trends 3. Supervised GANs Image-to-Image Translation with Conditional Adversarial Nets Isola et al. Fully supervised (pairs given) 2. Domain adaptation Domain-adversarial training of neural networks Ganin et al. Not generative 1. Style Transfer (Gatys et al.) Replaces statistics/texture given an exemplar Not semantic
7 Pix2pix (Isola et al.) Fully Supervised: Million of (Si à Ti) pairs
8 Vision applications that require Unsupervised Image Transfer Methods Day Night Bag Shoe World VR NVIDIA SKT Brain Oculus
9 AirSim (Microsoft) Transfer Learning Playing for Data: Ground Truth from Computer Games (Intel) Yan Duan et al. OpenAI Tzeng et al. Berkley
10 True AI needs no explicit supervision Bag of face images Bag of Emoji
11 Visual Analogies: Solving the Cartooning task Transfer a sample in domain S to its corresponding sample in domain T Without any correspondences Is this even possible?
12 Experts ImageNet (Krizhevsky et al.) f := Faces (Taigman et al.) Digits (LeCun et al.)
13 Domain Transfer Problem Given two related domains S, T Learn a generative G: S T, Such that for some f: S T R *, f G x ~ f(x) Unsupervised Samples are unlabeled, either in S or T No pairs of samples are given, e.g. {(s 1, t 1 ) s 1 t 1 } f is asymmetric/unadpated, i.e. was not trained in T
14 G
15 f G f(x) g
16 G f f(x) g f f(g(f(x)) LCONST
17 LTID G f f(x) g f f(g(f(x)) LCONST
18 Background: Generative Adversarial Networks (Goodfellow et al.) Learn networks D, G together. D identifies which images are real and which created by G G tries to fool D D G
19 LTID G D LGAN f f(x) g f f(g(f(x)) D is ternary: class 1: authentic emoji class 2: emoji created by G for an emoji input class 3: emoji created by G for a photograph LCONST
20 Domain Transfer Network
21 Evaluation of the DTN 1. Digits : SVHN à MNIST 2. Faces: Faces à Emoji
22 f := ConvNet(S)à{0,..,9} S is SVHN G T is MNIST Not really MNIST
23 Zero Shot DTN GAN
24 Faces à Emoji ~ 5-10 minutes for an expert Limited selection of templates Cartooning an open problem Input Manual
25 Input Manual DTN Input Manual DTN Input Manual DTN Input Manual DTN
26 How identifiable are those generations?
27 All 80 identities in Facescrub (No Cherry-Picking)
28 Are we being totally faithful to the T? DTN Emoji
29 The target domain is generated by an engine Emoji 3D Avatars 3D Computer Graphics Engine: configuration image
30 Domain Transfer Revisited Given two related domains S, T Learn a generative G: S T, Such that for some f: S T R *, f G x is close to f x And for a given engine E, there exist a configuration u such that G(x) = E(u)
31 Tied Output Synthesis (TOS) Unsupervised Creation of Parameterized Avatars; In submission
32
33 What s ahead? Unsupervised (Transfer) Learning in new domains Knowledge 2 (Data 2 + Expert 2) Knowledge 4 (Data 4 + Expert 4) Data 2 Data 4 Knowledge 1 (Data 1 + Expert 1) Knowledge 3 (Data 3 + Expert 3)
34 Thank you {yaniv, adampolyak, References: Unsupervised Cross-Domain Image Generation; Taigman, Polyak, Wolf [ICLR 2017] Unsupervised Creation of Parameterized Avatars; Wolf, Taigman, Polyak [In submission]
THe artist Hanoch Piven creates caricatures by arranging
1 Unsupervised Generation of Free-Form and Parameterized Avatars Adam Polyak, Yaniv Taigman, and Lior Wolf, Member, IEEE Abstract We study two problems involving the task of mapping images between different
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
arxiv: v2 [cs.cv] 9 Jul 2017
![arxiv: v2 [cs.cv] 9 Jul 2017](/thumbs/72/66916544.jpg "arxiv: v2 [cs.cv] 9 Jul 2017")
Unsupervised Creation of Parameterized Avatars Lior Wolf1,2, Yaniv Taigman1, and Adam Polyak1 1 arxiv:1704.05693v2 [cs.cv] 9 Jul 2017 2 Facebook AI Research School of Computer Science, Tel Aviv University
NAM: 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
Two Routes for Image to Image Translation: Rule based vs. Learning based. Minglun Gong, Memorial Univ. Collaboration with Mr.
Two Routes for Image to Image Translation: Rule based vs. Learning based Minglun Gong, Memorial Univ. Collaboration with Mr. Zili Yi Introduction A brief history of image processing Image to Image translation
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]
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,
Generative 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
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,
A 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
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
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
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
Unsupervised Creation of Parameterized Avatars
Unsupervised Creation of Parameterized Avatars Lior Wolf 1,2, Yaniv Taigman 1, and Adam Polyak 1 1 Facebook AI Research 2 The School of Computer Science, Tel Aviv University Abstract We study the problem
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
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
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
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
Computer vision: teaching computers to see
Computer vision: teaching computers to see Mats Sjöberg Department of Computer Science Aalto University mats.sjoberg@aalto.fi Turku.AI meetup June 5, 2018 Computer vision Giving computers the ability to
New Research Trends in Cybersecurity Privacy Attacks on Decentralized Deep Learning
New Research Trends in Cybersecurity Privacy Attacks on Decentralized Deep Learning Prof. Luigi V. Mancini Tel. +39 06 4991 8421 E-mail: mancini@di.uniroma1.it http://www.di.uniroma1.it/mancini Machine
DL Tutorial. Xudong Cao
DL Tutorial Xudong Cao Historical Line 1960s Perceptron 1980s MLP BP algorithm 2006 RBM unsupervised learning 2012 AlexNet ImageNet Comp. 2014 GoogleNet VGGNet ImageNet Comp. Rule based AI algorithm Game
Adapting Deep Networks Across Domains, Modalities, and Tasks Judy Hoffman!
Adapting Deep Networks Across Domains, Modalities, and Tasks Judy Hoffman! Eric Tzeng Saurabh Gupta Kate Saenko Trevor Darrell Recent Visual Recognition Progress ImageNet Performance 100 Accuracy 95 90
Generative 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
Introduction to Deep Learning
ENEE698A : Machine Learning Seminar Introduction to Deep Learning Raviteja Vemulapalli Image credit: [LeCun 1998] Resources Unsupervised feature learning and deep learning (UFLDL) tutorial (http://ufldl.stanford.edu/wiki/index.php/ufldl_tutorial)
Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
OUTPUT OUTPUT Learning to Discover Cross-Domain Relations with Generative Adversarial Networks Taeksoo Kim 1 Moonsu Cha 1 Hyunsoo Kim 1 Jung Kwon Lee 1 Jiwon Kim 1 Abstract While humans easily recognize
arxiv: v1 [cs.lg] 3 Jun 2018
![arxiv: v1 [cs.lg] 3 Jun 2018](/thumbs/79/79493702.jpg "arxiv: v1 [cs.lg] 3 Jun 2018")
NAM: Non-Adversarial Unsupervised Domain Mapping Yedid Hoshen Facebook AI Research Lior Wolf Facebook AI Research, Tel Aviv University yedidh@fb.com wolf@fb.com arxiv:1806.00804v1 [cs.lg] 3 Jun 2018 Abstract
Deep Neural Networks:
Deep Neural Networks: Part II Convolutional Neural Network (CNN) Yuan-Kai Wang, 2016 Web site of this course: http://pattern-recognition.weebly.com source: CNN for ImageClassification, by S. Lazebnik,
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
arxiv: v1 [cs.cv] 7 Feb 2018
![arxiv: v1 [cs.cv] 7 Feb 2018](/thumbs/86/94474126.jpg "arxiv: v1 [cs.cv] 7 Feb 2018")
Unsupervised Typography Transfer Hanfei Sun Carnegie Mellon University hanfeis@andrew.cmu.edu Yiming Luo Carnegie Mellon University yimingl1@andrew.cmu.edu Ziang Lu Carnegie Mellon University ziangl@andrew.cmu.edu
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
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
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
SEMANTIC COMPUTING. Lecture 8: Introduction to Deep Learning. TU Dresden, 7 December Dagmar Gromann International Center For Computational Logic
SEMANTIC COMPUTING Lecture 8: Introduction to Deep Learning Dagmar Gromann International Center For Computational Logic TU Dresden, 7 December 2018 Overview Introduction Deep Learning General Neural Networks
XGAN: UNSUPERVISED IMAGE-TO-IMAGE TRANSLA- TION FOR MANY-TO-MANY MAPPINGS
XGAN: UNSUPERVISED IMAGE-TO-IMAGE TRANSLA- TION FOR MANY-TO-MANY MAPPINGS Anonymous authors Paper under double-blind review ABSTRACT Style transfer usually refers to the task of applying color and texture
GANs 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 [
10/6/2017. What is deep learning Some motivation Enablers Data Computation Structure Software Closing examples
What is deep learning Some motivation Enablers Data Computation Structure Software Closing examples 2 1 The development of full artificial intelligence could spell the end of the human race it would take
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
Computer Vision Lecture 16
Announcements Computer Vision Lecture 16 Deep Learning Applications 11.01.2017 Seminar registration period starts on Friday We will offer a lab course in the summer semester Deep Robot Learning Topic:
arxiv: v1 [cs.cv] 5 Jul 2017
![arxiv: v1 [cs.cv] 5 Jul 2017](/thumbs/95/123923253.jpg "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
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
Computer Vision Lecture 16
Computer Vision Lecture 16 Deep Learning Applications 11.01.2017 Bastian Leibe RWTH Aachen http://www.vision.rwth-aachen.de leibe@vision.rwth-aachen.de Announcements Seminar registration period starts
arxiv: v1 [cs.cv] 17 Nov 2016
![arxiv: v1 [cs.cv] 17 Nov 2016](/thumbs/86/93859848.jpg "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
1 Overview Definitions (read this section carefully) 2
MLPerf User Guide Version 0.5 May 2nd, 2018 1 Overview 2 1.1 Definitions (read this section carefully) 2 2 General rules 3 2.1 Strive to be fair 3 2.2 System and framework must be consistent 4 2.3 System
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
Image to Image Translation for Domain Adaptation
Image to Image Translation for Domain Adaptation Zak Murez 1,2 Soheil Kolouri 2 David Kriegman 1 Ravi Ramamoorthi 1 Kyungnam Kim 2 1 University of California, San Diego; 2 HRL Laboratories, LLC; {zmurez,kriegman,ravir}@cs.ucsd.edu,
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
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
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
arxiv: v1 [cs.cv] 7 Mar 2018
![arxiv: v1 [cs.cv] 7 Mar 2018](/thumbs/95/125565711.jpg "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
IDENTIFYING 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
Human-Robot Interaction
Human-Robot Interaction Elective in Artificial Intelligence Lecture 6 Visual Perception Luca Iocchi DIAG, Sapienza University of Rome, Italy With contributions from D. D. Bloisi and A. Youssef Visual Perception
Exploring Style Transfer: Extensions to Neural Style Transfer
Exploring Style Transfer: Extensions to Neural Style Transfer Noah Makow Stanford University nmakow@stanford.edu Pablo Hernandez Stanford University pabloh2@stanford.edu Abstract Recent work by Gatys et
AudioSet: Real-world Audio Event Classification
AudioSet: Real-world Audio Event Classification g.co/audioset Rif A. Saurous, Shawn Hershey, Dan Ellis, Aren Jansen and the Google Sound Understanding Team 2017-10-20 Outline The Early Years: Weakly-Supervised
arxiv: v1 [cs.lg] 12 Jul 2018
![arxiv: v1 [cs.lg] 12 Jul 2018](/thumbs/81/84726020.jpg "arxiv: v1 [cs.lg] 12 Jul 2018")
arxiv:1807.04585v1 [cs.lg] 12 Jul 2018 Deep Learning for Imbalance Data Classification using Class Expert Generative Adversarial Network Fanny a, Tjeng Wawan Cenggoro a,b a Computer Science Department,
Deep Learning for Vision
Deep Learning for Vision Presented by Kevin Matzen Quick Intro - DNN Feed-forward Sparse connectivity (layer to layer) Different layer types Recently popularized for vision [Krizhevsky, et. al. NIPS 2012]
Deep Model Compression
Deep Model Compression Xin Wang Oct.31.2016 Some of the contents are borrowed from Hinton s and Song s slides. Two papers Distilling the Knowledge in a Neural Network by Geoffrey Hinton et al What s the
CyCADA: Cycle-Consistent Adversarial Domain Adaptation
Judy Hoffman 1 Eric Tzeng 1 Taesung Park 1 Jun-Yan Zhu 1 Phillip Isola 12 Kate Saenko 3 Alexei A. Efros 1 Trevor Darrell 1 Abstract Domain adaptation is critical for success in new, unseen environments.
Deep Learning Basic Lecture - Complex Systems & Artificial Intelligence 2017/18 (VO) Asan Agibetov, PhD.
Deep Learning 861.061 Basic Lecture - Complex Systems & Artificial Intelligence 2017/18 (VO) Asan Agibetov, PhD asan.agibetov@meduniwien.ac.at Medical University of Vienna Center for Medical Statistics,
Fashion Analytics and Systems
Learning and Vision Group, NUS (NUS-LV) Fashion Analytics and Systems Shuicheng YAN eleyans@nus.edu.sg National University of Singapore [ Special thanks to Luoqi LIU, Xiaodan LIANG, Si LIU, Jianshu LI]
arxiv: v1 [cs.cv] 1 Dec 2017
![arxiv: v1 [cs.cv] 1 Dec 2017](/thumbs/86/93359750.jpg "arxiv: v1 [cs.cv] 1 Dec 2017")
Image to Image Translation for Domain Adaptation Zak Murez 1,2 Soheil Kolouri 2 David Kriegman 1 Ravi Ramamoorthi 1 Kyungnam Kim 2 1 University of California, San Diego; 2 HRL Laboratories, LLC; {zmurez,kriegman,ravir}@cs.ucsd.edu,
FaceNet. Florian Schroff, Dmitry Kalenichenko, James Philbin Google Inc. Presentation by Ignacio Aranguren and Rahul Rana
FaceNet Florian Schroff, Dmitry Kalenichenko, James Philbin Google Inc. Presentation by Ignacio Aranguren and Rahul Rana Introduction FaceNet learns a mapping from face images to a compact Euclidean Space
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
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
CS 4510/9010 Applied Machine Learning. Deep Learning. Paula Matuszek Fall copyright Paula Matuszek 2016
CS 4510/9010 Applied Machine Learning 1 Deep Learning Paula Matuszek Fall 2016 Beyond Simple Neural Nets 2 In the last few ideas we have seen some surprisingly rapid progress in some areas of AI Image
Neural Nets & Deep Learning
Neural Nets & Deep Learning The Inspiration Inputs Outputs Our brains are pretty amazing, what if we could do something similar with computers? Image Source: http://ib.bioninja.com.au/_media/neuron _med.jpeg
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
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,
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
Characterization and Benchmarking of Deep Learning. Natalia Vassilieva, PhD Sr. Research Manager
Characterization and Benchmarking of Deep Learning Natalia Vassilieva, PhD Sr. Research Manager Deep learning applications Vision Speech Text Other Search & information extraction Security/Video surveillance
Deep Learning Workshop. Nov. 20, 2015 Andrew Fishberg, Rowan Zellers
Deep Learning Workshop Nov. 20, 2015 Andrew Fishberg, Rowan Zellers Why deep learning? The ImageNet Challenge Goal: image classification with 1000 categories Top 5 error rate of 15%. Krizhevsky, Alex,
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
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
arxiv: v3 [cs.lg] 7 Aug 2018
![arxiv: v3 [cs.lg] 7 Aug 2018](/thumbs/91/107180132.jpg "arxiv: v3 [cs.lg] 7 Aug 2018")
Augmented Cyclic Adversarial Learning for Domain Adaptation arxiv:1807.00374v3 [cs.lg] 7 Aug 2018 Ehsan Hosseini-Asl, Yingbo Zhou, Caiming Xiong, Richard Socher Salesforce Research {ehosseiniasl,yingbo.zhou,cxiong,rsocher}@salesforce.com
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
Deep Learning in Image Processing
Deep Learning in Image Processing Roland Memisevic University of Montreal & TwentyBN ICISP 2016 Roland Memisevic Deep Learning in Image Processing ICISP 2016 f 2? cathedral high-rise f 1 It s the features,
arxiv: v2 [cs.cv] 23 Dec 2017
![arxiv: v2 [cs.cv] 23 Dec 2017](/thumbs/75/72736245.jpg "arxiv: v2 [cs.cv] 23 Dec 2017")
TextureGAN: Controlling Deep Image Synthesis with Texture Patches Wenqi Xian 1 Patsorn Sangkloy 1 Varun Agrawal 1 Amit Raj 1 Jingwan Lu 2 Chen Fang 2 Fisher Yu 3 James Hays 1 1 Georgia Institute of Technology
Neural Networks for Machine Learning. Lecture 15a From Principal Components Analysis to Autoencoders
Neural Networks for Machine Learning Lecture 15a From Principal Components Analysis to Autoencoders Geoffrey Hinton Nitish Srivastava, Kevin Swersky Tijmen Tieleman Abdel-rahman Mohamed Principal Components
Convolutional Neural Networks
Lecturer: Barnabas Poczos Introduction to Machine Learning (Lecture Notes) Convolutional Neural Networks Disclaimer: These notes have not been subjected to the usual scrutiny reserved for formal publications.
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
Mocha.jl. Deep Learning in Julia. Chiyuan Zhang CSAIL, MIT
Mocha.jl Deep Learning in Julia Chiyuan Zhang (@pluskid) CSAIL, MIT Deep Learning Learning with multi-layer (3~30) neural networks, on a huge training set. State-of-the-art on many AI tasks Computer Vision:
Deep Learning for Computer Vision with MATLAB By Jon Cherrie
Deep Learning for Computer Vision with MATLAB By Jon Cherrie 2015 The MathWorks, Inc. 1 Deep learning is getting a lot of attention "Dahl and his colleagues won $22,000 with a deeplearning system. 'We
Deep Learning. Volker Tresp Summer 2017
Deep Learning Volker Tresp Summer 2017 1 Neural Network Winter and Revival While Machine Learning was flourishing, there was a Neural Network winter (late 1990 s until late 2000 s) Around 2010 there
Experiments with Tensor Flow
Experiments with Tensor Flow 06.07.2017 Roman Weber (Geschäftsführer) Richard Schmid (Senior Consultant) A Smart Home? 2 WEBGATE WELTWEIT WebGate USA Boston WebGate Support Center Brno, Tschechische Republik
ROB 537: Learning-Based Control
ROB 537: Learning-Based Control Week 6, Lecture 1 Deep Learning (based on lectures by Fuxin Li, CS 519: Deep Learning) Announcements: HW 3 Due TODAY Midterm Exam on 11/6 Reading: Survey paper on Deep Learning
arxiv: v1 [cs.cv] 1 May 2018
![arxiv: v1 [cs.cv] 1 May 2018](/thumbs/83/88735687.jpg "arxiv: v1 [cs.cv] 1 May 2018")
Conditional Image-to-Image Translation Jianxin Lin 1 Yingce Xia 1 Tao Qin 2 Zhibo Chen 1 Tie-Yan Liu 2 1 University of Science and Technology of China 2 Microsoft Research Asia linjx@mail.ustc.edu.cn {taoqin,
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
Structured Prediction using Convolutional Neural Networks
Overview Structured Prediction using Convolutional Neural Networks Bohyung Han bhhan@postech.ac.kr Computer Vision Lab. Convolutional Neural Networks (CNNs) Structured predictions for low level computer
arxiv: v1 [stat.ml] 14 Sep 2017
![arxiv: v1 [stat.ml] 14 Sep 2017](/thumbs/78/77167912.jpg "arxiv: 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
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
Todo before next class
Todo before next class Each project group should submit a short project report (4 pages presentation slides) including 1. Problem definition 2. Related work 3. Preliminary results 4. Future plan Submission:
arxiv: v1 [cs.cv] 7 Dec 2017
![arxiv: v1 [cs.cv] 7 Dec 2017](/thumbs/94/121316865.jpg "arxiv: v1 [cs.cv] 7 Dec 2017")
TV-GAN: Generative Adversarial Network Based Thermal to Visible Face Recognition arxiv:1712.02514v1 [cs.cv] 7 Dec 2017 Teng Zhang, Arnold Wiliem*, Siqi Yang and Brian C. Lovell The University of Queensland,
DOMAIN-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,
CS 523: Multimedia Systems
CS 523: Multimedia Systems Angus Forbes creativecoding.evl.uic.edu/courses/cs523 Today - Convolutional Neural Networks - Work on Project 1 http://playground.tensorflow.org/ Convolutional Neural Networks
Object Detection Lecture Introduction to deep learning (CNN) Idar Dyrdal
Object Detection Lecture 10.3 - Introduction to deep learning (CNN) Idar Dyrdal Deep Learning Labels Computational models composed of multiple processing layers (non-linear transformations) Used to learn
Structured 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
arxiv: v1 [cs.cv] 29 Nov 2017
![arxiv: v1 [cs.cv] 29 Nov 2017](/thumbs/75/72595429.jpg "arxiv: v1 [cs.cv] 29 Nov 2017")
Photo-to-Caricature Translation on Faces in the Wild Ziqiang Zheng Haiyong Zheng Zhibin Yu Zhaorui Gu Bing Zheng Ocean University of China arxiv:1711.10735v1 [cs.cv] 29 Nov 2017 Abstract Recently, image-to-image
SUPERCHARGE DEEP LEARNING WITH DGX-1. Markus Weber SC16 - November 2016
SUPERCHARGE DEEP LEARNING WITH DGX-1 Markus Weber SC16 - November 2016 NVIDIA Pioneered GPU Computing Founded 1993 $7B 9,500 Employees 100M NVIDIA GeForce Gamers The world s largest gaming platform Pioneering
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
Deep Neural Network Hyperparameter Optimization with Genetic Algorithms
Deep Neural Network Hyperparameter Optimization with Genetic Algorithms EvoDevo A Genetic Algorithm Framework Aaron Vose, Jacob Balma, Geert Wenes, and Rangan Sukumar Cray Inc. October 2017 Presenter Vose,
DOMAIN-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,