genera ve adversarial networks
play

Genera&ve Adversarial Networks NTT - PowerPoint PPT Presentation

Sep 18, 2022 •187 likes •899 views

Genera&ve Adversarial Networks NTT 2020 6 10 @JSAI2020 KS-02 AI MIRU2020

  1. ������� Genera&ve Adversarial Networks ��������� NTT ���������������� �� �� 2020 � 6 � 10 � @JSAI2020 KS-02 ��� AI – MIRU2020 �����

  2. ���� 2014. 4 � NTT ���������������� • 2017. 4 � 2020.3 ���� �2�������� • ������ �������� ������ �������� CF GAN DTLC- GAN GAN -PF GAN -PF for STFT GAN -VC [CVPR 2017] [CVPR 2018] [ICASSP 2017] [Interspeech 2017] [Interspeech 2017] �S������� ������������� CycleGAN-VC r GAN † CP- GAN † NR- GAN † Cycle GAN -VC Cycle GAN -VC2 Star GAN -VC2 [CVPR 2019] [BMVC 2019] [CVPR 2020] [EUSIPCO 2018] [ICASSP 2019] [Interspeech 2019] �I����������� ������������������ � ���������� �

  3. ���S 2014. 4 � NTT ���������������� • 2017. 4 � 2020.3 ���� �����3���� • ��������������� ���������������� CF GAN DTLC- GAN GAN -PF GAN -PF for STFT GAN -VC [CVPR 2017] [CVPR 2018] [ICASSP 2017] [Interspeech 2017] [Interspeech 2017] ������� �� I����N��� ������������� CycleGAN-VC r GAN † CP- GAN † NR- GAN † Cycle GAN -VC Cycle GAN -VC2 Star GAN -VC2 [CVPR 2019] [BMVC 2019] [CVPR 2020] [EUSIPCO 2018] [ICASSP 2019] [Interspeech 2019] ��G������N��� ����A������������� � �3�������� �

  4. GAN ����������� �4 �� → Q1. ������������� • – �� = ������������4�������� ��������� T. Karras et al., “Analyzing and Improving the Image Quality of StyleGAN,” arXiv 2019. �

  5. GAN ����������� �� �� → Q1. 5������������ • 2���� – �� = 5�������������������� ��������� ��������� T. Karras et al., “Analyzing and Improving the Image Quality of StyleGAN,” arXiv 2019. �

  6. GAN ����������� Q2. ��������������6�����?������� • �� � � �� by Monet �� ���� � � �� ���� JY. Zhu et al., “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks,” ICCV 2017. �

  7. GAN ����������� Q2. �7�������������������������� • �� � ������ �� by Monet �� �������� ���� � �� ���� JY. Zhu et al., “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks,” ICCV 2017. �

  8. GAN ����������� Q3. ��������������� • ���� ��� �� � � ��� T. Kaneko et al., “Generative Attribute Controller with Conditional Filtered Generative Adversarial Networks,” CVPR 2017. �

  9. GAN ����������� Q3. ��������������� ���������� • ����� �� �� �� ��� �� ��� ���9� http://www.kecl.ntt.co.jp/people/kaneko.takuhiro/projects/gac/index.html T. Kaneko et al., “Genera2ve A5ribute Controller with Condi2onal Filtered Genera2ve Adversarial Networks,” CVPR 2017. �

  10. GAN ���������� ( ��� ) ���� StyleGAN2 [Karras+arXiv2019] ���� ���� CycleGAN [Zhu+ICCV2017] CFGAN [Kaneko+CVPR2017] ��

  11. GAN ���������� ( ��� ) ���� ������ StyleGAN2 [Karras+arXiv2019] ������ ���� ���� CycleGAN [Zhu+ICCV2017] CFGAN [Kaneko+CVPR2017] ��

  12. �� ��� ���� ���� ��� �� �� ��(1���� �����(��)��2 † ���� † h$p://www.kecl.n$.co.jp/people/kaneko.takuhiro/#talks ��

  13. �� ��� ���� ���� ��� �� �� ��

  14. �������� ���������1���� ����� ( Generator ) ��� • ����� ����� � ������� ������4 ������4 Pictures: A. Brock et al., “Large Scale GAN Training for High Fidelity Natural Image Synthesis,” ICLR 2019. ��

  15. ������������ ��1��������������5� • ����� ������������1�� ����1�� �������5���� ����������������1��� ������� � ������� Pictures: A. Brock et al., “Large Scale GAN Training for High Fidelity Natural Image Synthesis,” ICLR 2019. ��

  16. <latexit sha1_base64="Xnt9lX2cNEUMxaHM7bxRUcRtMvU=">AB9HicbVBNS8NAEJ3Ur1q/qh69LBahHixJFfQiFL14rGA/oI1ls920SzebuLsp1tDf4cWDIl79Md78N27bHLT1wcDjvRlm5nkRZ0rb9reVWVpeWV3Lruc2Nre2d/K7e3UVxpLQGgl5KJseVpQzQWuaU6bkaQ48DhteIPrid8YUqlYKO70KJugHuC+YxgbST3EV0i/z45cbFp+NOvmCX7CnQInFSUoAU1U7+q90NSRxQoQnHSrUcO9JugqVmhNxrh0rGmEywD3aMlTgCo3mR49RkdG6SI/lKaERlP190SCA6VGgWc6A6z7at6biP95rVj7F27CRBRrKshskR9zpEM0SQB1maRE85EhmEhmbkWkjyUm2uSUMyE48y8vknq5JyWyrdnhcpVGkcWDuAQiuDAOVTgBqpQAwIP8Ayv8GYNrRfr3fqYtWasdGYf/sD6/AHauJDa</latexit> <latexit sha1_base64="QLlkCjr28Ua3oZ3AMcbE39dZsPg=">AB73icbVBNSwMxEJ31s9avqkcvwSLUS9mtgl6EohePFewHtEvJptk2NJusSVasS/+EFw+KePXvePfmLZ70NYHA4/3ZpiZF8ScaeO6387S8srq2npuI7+5tb2zW9jb2iZKELrRHKpWgHWlDNB64YZTluxojgKOG0Gw+uJ3ygSjMp7swopn6E+4KFjGBjpdYTukRh6fGkWyi6ZXcKtEi8jBQhQ61b+Or0JEkiKgzhWOu258bGT7EyjHA6zncSTWNMhrhP25YKHFHtp9N7x+jYKj0USmVLGDRVf0+kONJ6FAW2M8JmoOe9ifif105MeOGnTMSJoYLMFoUJR0aiyfOoxQlho8swUQxeysiA6wMTaivA3Bm395kTQqZe+0XLk9K1avsjhycAhHUAIPzqEKN1CDOhDg8Ayv8ObcOy/Ou/Mxa1yspkD+APn8wd9o70</latexit> ������� �M���V�N�A�� AR , Flow , VAE , GAN • �M�G� ��M� ��M� ���� ���� ��� ��6��-��-����-����-1 �� ��� �����6����1���6�-����-� �-�-��6��-����-������1��-6����� ��� (Chain Rule) ���� �F��� ����� �1������-�����-1 ���N x = f − 1 ( z ) z = f ( x ) Reference: I. Goodfellow, “NIPS 2016 Tutorial: GeneraBve Aversarial Networks,” NIPS 2016. �

  17. ������� �����c����M� AR , Flow , VAE , GAN • ��A������Nd ��F������ ����� e��� ���� �i�� �i�G ��� �7���-��-����-����-1 �� ��� ����������1��7��-����-� �-�-�����-����-������1��-������ ��� (Chain Rule) �N�i g��Va ����� �1������-�����-1 �b�� Reference: I. Goodfellow, “NIPS 2016 Tutorial: GeneraBve Aversarial Networks,” NIPS 2016. �

  18. GAN 1/4 Generative Adversarial Networks [Goodfellow+2014] • – ��� ( Generator ) ���� ( Discriminator ) � ��� ��� D Random Real image G x Real/Fake Discriminator Latent code Fake image D ( x ) Generator z G ( z ) – Min-Max ���� Generator vs. Discriminator � I. Goodfellow et al., “Generative Adversarial Nets,” NIPS 2014. ��

  19. GAN 2/4 Genera&ve Adversarial Networks [Goodfellow+2014] • – ��� ( Generator ) ���� ( Discriminator ) � ��� ��� D Random Real image G x Real/Fake Discriminator Latent code Fake image D ( x ) Generator z G ( z ) �1���9�� – Min-Max ���� Generator vs. Discriminator � Fake ����� Discriminator � ��� ��� ��� I. Goodfellow et al., “Generative Adversarial Nets,” NIPS 2014. ��

  20. GAN 3/4 Genera&ve Adversarial Networks [Goodfellow+2014] • – ��� ( Generator ) ���� ( Discriminator ) � ��� ��� D Random Real image G x Real/Fake Discriminator Latent code Fake image D ( x ) Generator z G ( z ) Real/Fake ��� – Min-Max �0�� Generator vs. Discriminator � Real/Fake ����� Generator � �������� �0� I. Goodfellow et al., “Generative Adversarial Nets,” NIPS 2014. ��

  21. GAN 4/4 Genera&ve Adversarial Networks [Goodfellow+2014] • – ��� ( Generator ) ���� ( Discriminator ) � ��� ��� D Random Real image G x Real/Fake Discriminator Latent code Fake image D ( x ) Generator z G ( z ) �������� 21 Real/Fake ��� – Min-Max ���� Generator vs. Discriminator � Generator � Discriminator � Min-Max �21 ���� Generator ����������������� I. Goodfellow et al., “Generative Adversarial Nets,” NIPS 2014. ��

  22. �� ��� ���� ���� ��� �� �� ��

Recommend

Adversarial Training Attacks on Deep Networks and Generative Adversarial Networks Erkut Erdem

Adversarial Training Attacks on Deep Networks and Generative Adversarial Networks Erkut Erdem

images from Geris Game (Pixar, 1997) Adversarial Training Attacks on Deep Networks and Generative Adversarial Networks Erkut Erdem Aykut Erdem Levent Karacan Computer Vision Lab, Hacettepe University Outline Part 1: Attacks on

1.11k views • 72 slides
Generative Adversarial Networks, Wasserstein Distance, and Adversarial Loss Zhiyu Min Alibaba

Generative Adversarial Networks, Wasserstein Distance, and Adversarial Loss Zhiyu Min Alibaba

Generative Adversarial Networks, Wasserstein Distance, and Adversarial Loss Zhiyu Min Alibaba AliMe X-Lab Outline GAN Definition and formulation Saddle point optimization Vanishing gradient Alternative objective for Generator

516 views • 25 slides
Automa'c Genera'on Control Using Ar'ficial Neural Networks By-

Automa'c Genera'on Control Using Ar'ficial Neural Networks By-

Automa'c Genera'on Control Using Ar'ficial Neural Networks By- Harkirat Singh Choong Introduc'on What is Automa'c Genera'on Control (AGC)? There is

736 views • 47 slides
Neglected topics CS 446 Adversarial examples and deep networks 1 / 23 Adversarial

Neglected topics CS 446 Adversarial examples and deep networks 1 / 23 Adversarial

Neglected topics CS 446 Adversarial examples and deep networks 1 / 23 Adversarial examples? Standard ML setup: We have training data; try to do well on withheld testing data. Adversarial/robust ML setup: We have training

672 views • 27 slides
LAB MEETING: A Connection Between Generative Adversarial Networks, Inverse Reinforcement Learning

LAB MEETING: A Connection Between Generative Adversarial Networks, Inverse Reinforcement Learning

LAB MEETING: A Connection Between Generative Adversarial Networks, Inverse Reinforcement Learning and Energy-Based models Suwon Suh POSTECH MLG Feb, 13, 2017 Goal Understanding Basic Models 1) Generative Adversarial Networks (GAN) 2)

722 views • 12 slides
Introduction to Generative Adversarial Networks Ian Goodfellow, OpenAI Research Scientist NIPS

Introduction to Generative Adversarial Networks Ian Goodfellow, OpenAI Research Scientist NIPS

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 flux; a new term that applies to both

792 views • 25 slides
Robust Statistics and Generative Adversarial Networks Yuan YAO HKUST Chao Gao (Chicago) Jiyu

Robust Statistics and Generative Adversarial Networks Yuan YAO HKUST Chao Gao (Chicago) Jiyu

Robust Statistics and Generative Adversarial Networks Yuan YAO HKUST Chao Gao (Chicago) Jiyu Liu (Yale) Weizhi Zhu (HKUST) Deep Learning is Notoriously Not Robust! Imperceivable adversarial examples are ubiquitous to fail neural networks

1.8k views • 133 slides
Genera&amp;ve Stochas&amp;c Networks Trainable by Backprop Yoshua

Genera&amp;ve Stochas&amp;c Networks Trainable by Backprop Yoshua

Genera&amp;ve Stochas&amp;c Networks Trainable by Backprop Yoshua Bengio with Eric Laufer, Li Yao,

651 views • 43 slides
Generative Adversarial Networks presented by Ian Goodfellow presentation co-developed with Aaron

Generative Adversarial Networks presented by Ian Goodfellow presentation co-developed with Aaron

Generative Adversarial Networks presented by Ian Goodfellow presentation co-developed with Aaron Courville 1 In todays talk Generative Adversarial Networks Goodfellow et al., NIPS 2014 Conditional Generative

2.84k views • 40 slides
Generative Adversarial Networks Aaron Mishkin UBC MLRG 2018W2 1 Generative Adversial Networks

Generative Adversarial Networks Aaron Mishkin UBC MLRG 2018W2 1 Generative Adversial Networks

Generative Adversarial Networks Aaron Mishkin UBC MLRG 2018W2 1 Generative Adversial Networks Two imaginary celebrities that were dreamed up by a random number generator. https://research.nvidia.com/publication/2017-10

665 views • 39 slides
Adversarial Examples and Adversarial Training Ian Goodfellow, OpenAI Research Scientist Security

Adversarial Examples and Adversarial Training Ian Goodfellow, OpenAI Research Scientist Security

Adversarial Examples and Adversarial Training Ian Goodfellow, OpenAI Research Scientist Security Seminar, Stanford University, 2017-01-17 In this presentation Intriguing Properties of Neural Networks Szegedy et al, 2013

939 views • 44 slides
Adversarial Examples and Adversarial Training Ian Goodfellow, OpenAI Research Scientist Guest

Adversarial Examples and Adversarial Training Ian Goodfellow, OpenAI Research Scientist Guest

Adversarial Examples and Adversarial Training Ian Goodfellow, OpenAI Research Scientist Guest lecture for CS 294-131, UC Berkeley, 2016-10-05 In this presentation Intriguing Properties of Neural Networks Szegedy et al, 2013

660 views • 44 slides
Robust Statistics and Generative Adversarial Networks Yuan YAO HKUST 1 Chao GAO Jiyi LIU

Robust Statistics and Generative Adversarial Networks Yuan YAO HKUST 1 Chao GAO Jiyi LIU

Robust Statistics and Generative Adversarial Networks Yuan YAO HKUST 1 Chao GAO Jiyi LIU Weizhi ZHU U. Chicago Yale U. HKUST 2 Deep Learning is Notoriously Not Robust! Imperceivable adversarial examples are ubiquitous to fail

833 views • 72 slides
CVPR 2020 Universal Adversarial Attacks Image agnostic and transferable across networks

CVPR 2020 Universal Adversarial Attacks Image agnostic and transferable across networks

1 1,4 2,3 2 3 4 1 CVPR 2020 Universal Adversarial Attacks Image agnostic and transferable across networks Adversarial No defense: Baseline DNN perturbation Input image Classification Feature extraction dense Perturbed image

592 views • 6 slides
Adversarial Examples and Adversarial Training Ian Goodfellow, OpenAI Research Scientist

Adversarial Examples and Adversarial Training Ian Goodfellow, OpenAI Research Scientist

Adversarial Examples and Adversarial Training Ian Goodfellow, OpenAI Research Scientist Presentation at San Francisco AI Meetup, 2016-08-18 In this presentation Intriguing Properties of Neural Networks Szegedy et al, 2013

690 views • 32 slides
ON THE ADVERSARIAL ROBUSTNESS OF UNCERTAINTY AWARE DEEP NEURAL NETWORKS APRIL 29 TH , 2019

ON THE ADVERSARIAL ROBUSTNESS OF UNCERTAINTY AWARE DEEP NEURAL NETWORKS APRIL 29 TH , 2019

ON THE ADVERSARIAL ROBUSTNESS OF UNCERTAINTY AWARE DEEP NEURAL NETWORKS APRIL 29 TH , 2019 PREPARED BY: ALI HARAKEH QUESTION Can a neural network mitigate the effects of adversarial attacks by estimating the uncertainty in its predictions ?

1.14k views • 26 slides
Generative Adversarial Networks Wanyue Li

Generative Adversarial Networks Wanyue Li

Generating Fundus Fluorescence Angiography Images from Structure Fundus Images Using Generative Adversarial Networks Wanyue Li (wanyueli93@126.com) University of Science and Technology of China (USTC)

144 views • 10 slides
ShenaniGANs: A Discussion of Generative Adversarial Networks Quinn Meier and John Pace

ShenaniGANs: A Discussion of Generative Adversarial Networks Quinn Meier and John Pace

ShenaniGANs: A Discussion of Generative Adversarial Networks Quinn Meier and John Pace https://arxiv.org/pdf/1406.2661.pdf Review of Neural Networks Feature Vector -&gt; Feed Into First Layer -&gt; Matrix Multiplication with Weights -&gt;

654 views • 16 slides
Adversarial Examples and Adversarial Training Ian Goodfellow, OpenAI Research Scientist

Adversarial Examples and Adversarial Training Ian Goodfellow, OpenAI Research Scientist

Adversarial Examples and Adversarial Training Ian Goodfellow, OpenAI Research Scientist Presentation at HORSE 2016 London, 2016-09-19 In this presentation Intriguing Properties of Neural Networks Szegedy et al, 2013 Explaining

497 views • 22 slides
Model-Assisted Generative Adversarial Networks Leigh Whitehead ICL Seminar 05/06/20

Model-Assisted Generative Adversarial Networks Leigh Whitehead ICL Seminar 05/06/20

Model-Assisted Generative Adversarial Networks Leigh Whitehead ICL Seminar 05/06/20 Overview What are Generative Adversarial Networks (GANs)? The Model-Assisted GAN Case Studies Case Study I (from the paper) Case

834 views • 50 slides
Generative Adversarial Networks (GANs) Prof. Seungchul Lee Industrial AI Lab. Source 1

Generative Adversarial Networks (GANs) Prof. Seungchul Lee Industrial AI Lab. Source 1

Generative Adversarial Networks (GANs) Prof. Seungchul Lee Industrial AI Lab. Source 1 GAN (Generative Adversarial Network) by YouTube: https://www.youtube.com/watch?v=odpjk7_tGY0 Slides:

2.44k views • 49 slides
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks David Bau, Jun-Yan

GAN Dissection: Visualizing and Understanding Generative Adversarial Networks David Bau, Jun-Yan

GAN Dissection: Visualizing and Understanding Generative Adversarial Networks David Bau, Jun-Yan Zhu, Hendrik Strobelt, Bolei Zhou, Joshua B. Tenenbaum, William T. Freeman, Antonio Torralba Ing. Jakub Zitn y Faculty of Information

391 views • 21 slides
Conditional Adversarial Networks (or mapping from A to B) CS448V Computational Video

Conditional Adversarial Networks (or mapping from A to B) CS448V Computational Video

Conditional Adversarial Networks (or mapping from A to B) CS448V Computational Video Manipulation May 22 th , 2019 Why? - Cool! Trendy! - Google Scholar Pix2Pix CycleGAN Hundreds of applications and follow-up works Why? -

1.61k views • 90 slides
Bregman and Wasserstein, with Applications to Generative Adversarial Networks (GANs) and beyond

Bregman and Wasserstein, with Applications to Generative Adversarial Networks (GANs) and beyond

Bregman Divergence Function Generative Adversarial Networks (GANs) Wasserstein Divergence and GANs Relaxed Wasserstein Empirical Results Conclusions Bregman and Wasserstein, with Applications to Generative Adversarial Networks (GANs) and

1.62k views • 148 slides

More recommend