Diese Präsentation wurde erfolgreich gemeldet.
Wir verwenden Ihre LinkedIn Profilangaben und Informationen zu Ihren Aktivitäten, um Anzeigen zu personalisieren und Ihnen relevantere Inhalte anzuzeigen. Sie können Ihre Anzeigeneinstellungen jederzeit ändern.

Generative Adversarial Networks @ ICML 2019

4.090 Aufrufe

Veröffentlicht am

Generative Adversarial Networks @ ICML 2019

Generative Adversarial Networks (GANs) @ ICML 2019の論文まとめ資料です。ICML/ICLR 2019読み会@DeNAでの発表資料です

Veröffentlicht in: Wissenschaft
  • 7 Sacred "Sign Posts" From The Universe Revealed. Discover the "secret language" the Universes uses to send us guided messages and watch as your greatest desires manifest before your eyes. Claim your free report.  http://t.cn/AiuvUMl2
       Antworten 
    Sind Sie sicher, dass Sie …  Ja  Nein
    Ihre Nachricht erscheint hier
  • DOWNLOAD THAT BOOKS INTO AVAILABLE FORMAT (2019 Update) ......................................................................................................................... ......................................................................................................................... Download Full PDF EBOOK here { http://bit.ly/2m6jJ5M } ......................................................................................................................... Download Full EPUB Ebook here { http://bit.ly/2m6jJ5M } ......................................................................................................................... Download Full doc Ebook here { http://bit.ly/2m6jJ5M } ......................................................................................................................... Download PDF EBOOK here { http://bit.ly/2m6jJ5M } ......................................................................................................................... Download EPUB Ebook here { http://bit.ly/2m6jJ5M } ......................................................................................................................... Download doc Ebook here { http://bit.ly/2m6jJ5M } ......................................................................................................................... ......................................................................................................................... ................................................................................................................................... eBook is an electronic version of a traditional print book that can be read by using a personal computer or by using an eBook reader. (An eBook reader can be a software application for use on a computer such as Microsoft's free Reader application, or a book-sized computer that is used solely as a reading device such as Nuvomedia's Rocket eBook.) Users can purchase an eBook on diskette or CD, but the most popular method of getting an eBook is to purchase a downloadable file of the eBook (or other reading material) from a Web site (such as Barnes and Noble) to be read from the user's computer or reading device. Generally, an eBook can be downloaded in five minutes or less ......................................................................................................................... .............. Browse by Genre Available eBooks .............................................................................................................................. Art, Biography, Business, Chick Lit, Children's, Christian, Classics, Comics, Contemporary, Cookbooks, Manga, Memoir, Music, Mystery, Non Fiction, Paranormal, Philosophy, Poetry, Psychology, Religion, Romance, Science, Science Fiction, Self Help, Suspense, Spirituality, Sports, Thriller, Travel, Young Adult, Crime, Ebooks, Fantasy, Fiction, Graphic Novels, Historical Fiction, History, Horror, Humor And Comedy, ......................................................................................................................... ......................................................................................................................... .....BEST SELLER FOR EBOOK RECOMMEND............................................................. ......................................................................................................................... Blowout: Corrupted Democracy, Rogue State Russia, and the Richest, Most Destructive Industry on Earth,-- The Ride of a Lifetime: Lessons Learned from 15 Years as CEO of the Walt Disney Company,-- Call Sign Chaos: Learning to Lead,-- StrengthsFinder 2.0,-- Stillness Is the Key,-- She Said: Breaking the Sexual Harassment Story That Helped Ignite a Movement,-- Atomic Habits: An Easy & Proven Way to Build Good Habits & Break Bad Ones,-- Everything Is Figureoutable,-- What It Takes: Lessons in the Pursuit of Excellence,-- Rich Dad Poor Dad: What the Rich Teach Their Kids About Money That the Poor and Middle Class Do Not!,-- The Total Money Makeover: Classic Edition: A Proven Plan for Financial Fitness,-- Shut Up and Listen!: Hard Business Truths that Will Help You Succeed, ......................................................................................................................... .........................................................................................................................
       Antworten 
    Sind Sie sicher, dass Sie …  Ja  Nein
    Ihre Nachricht erscheint hier
  • Free Miracle "Angel Music" Attract abundance, happiness, and miracles into your life by listening the sounds of the Angels. Go here to listen now! ♣♣♣ https://tinyurl.com/y6pnne55
       Antworten 
    Sind Sie sicher, dass Sie …  Ja  Nein
    Ihre Nachricht erscheint hier
  • DOWNLOAD THIS BOOKS INTO AVAILABLE FORMAT (Unlimited) ......................................................................................................................... ......................................................................................................................... Download Full PDF EBOOK here { http://bit.ly/2m77EgH } ......................................................................................................................... Download Full EPUB Ebook here { http://bit.ly/2m77EgH } ......................................................................................................................... ACCESS WEBSITE for All Ebooks ......................................................................................................................... Download Full PDF EBOOK here { http://bit.ly/2m77EgH } ......................................................................................................................... Download EPUB Ebook here { http://bit.ly/2m77EgH } ......................................................................................................................... Download doc Ebook here { http://bit.ly/2m77EgH } ......................................................................................................................... ......................................................................................................................... ......................................................................................................................... .............. Browse by Genre Available eBooks ......................................................................................................................... Art, Biography, Business, Chick Lit, Children's, Christian, Classics, Comics, Contemporary, Cookbooks, Crime, Ebooks, Fantasy, Fiction, Graphic Novels, Historical Fiction, History, Horror, Humor And Comedy, Manga, Memoir, Music, Mystery, Non Fiction, Paranormal, Philosophy, Poetry, Psychology, Religion, Romance, Science, Science Fiction, Self Help, Suspense, Spirituality, Sports, Thriller, Travel, Young Adult,
       Antworten 
    Sind Sie sicher, dass Sie …  Ja  Nein
    Ihre Nachricht erscheint hier
  • DOWNLOAD FULL BOOKS, INTO AVAILABLE FORMAT ......................................................................................................................... ......................................................................................................................... 1.DOWNLOAD FULL. PDF EBOOK here { https://tinyurl.com/y6a5rkg5 } ......................................................................................................................... 1.DOWNLOAD FULL. EPUB Ebook here { https://tinyurl.com/y6a5rkg5 } ......................................................................................................................... 1.DOWNLOAD FULL. doc Ebook here { https://tinyurl.com/y6a5rkg5 } ......................................................................................................................... 1.DOWNLOAD FULL. PDF EBOOK here { https://tinyurl.com/y6a5rkg5 } ......................................................................................................................... 1.DOWNLOAD FULL. EPUB Ebook here { https://tinyurl.com/y6a5rkg5 } ......................................................................................................................... 1.DOWNLOAD FULL. doc Ebook here { https://tinyurl.com/y6a5rkg5 } ......................................................................................................................... ......................................................................................................................... ......................................................................................................................... .............. Browse by Genre Available eBooks ......................................................................................................................... Art, Biography, Business, Chick Lit, Children's, Christian, Classics, Comics, Contemporary, Cookbooks, Crime, Ebooks, Fantasy, Fiction, Graphic Novels, Historical Fiction, History, Horror, Humor And Comedy, Manga, Memoir, Music, Mystery, Non Fiction, Paranormal, Philosophy, Poetry, Psychology, Religion, Romance, Science, Science Fiction, Self Help, Suspense, Spirituality, Sports, Thriller, Travel, Young Adult,
       Antworten 
    Sind Sie sicher, dass Sie …  Ja  Nein
    Ihre Nachricht erscheint hier

Generative Adversarial Networks @ ICML 2019

  1. 1. 1
  2. 2. 1 3 5 7 2 4 6 8
  3. 3. ProgressiveGAN (Karras et al., ICLR 2018) BigGAN (Brock et al., ICLR 2019) 1 3 5 7 2 4 6 8
  4. 4. BigGAN (Brock et al., ICLR 2019) StyleGAN (Karras et al., CVPR 2019)
  5. 5. 2010- : DeNA / 2011– : Mobage 2014- : DeNA Mobage : ( ) TokyoWebmining - - 2010 60 /Koichi Hamada (@hamadakoichi)
  6. 6. /Koichi Hamada (@hamadakoichi) 78 : : 102*0DeNA AI : TZ ... ./ 0 KD SL KA N O N KD SL K N W
  7. 7. 4 02 0 5 . / 2 2/ 15 52 2:/ 21 Full-body High-resolution Anime Generation with Progressive Structure-conditional Generative Adversarial Networks Koichi Hamada, Kentaro Tachibana, Tianqi Li, Hiroto Honda, and Yusuke Uchida. In ECCVW 2018.
  8. 8. // . /
  9. 9. Generative Adversarial Nets. Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde- Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio. arXiv:1406.2661. In NIPS 2014.
  10. 10. BigGAN (Brock et al., ICLR 2019) StyleGAN (Karras et al., CVPR 2019)
  11. 11. Long Oral Oral High-Fidelity Image Generation 2 1 1 Latent space 2 1 1 Target Metrics Optimization 1 1 Training Methodology 3 3 Unified Treatment 3 3 Inference 2 2 Loss 2 2 Missing Data 2 2 Others (Estimation, Regularization/Normalization, Domain Translation/Adaptation, Uncertainty, User Modeling Discrete Data) 5 5
  12. 12. Long Oral Oral High-Fidelity Image Generation 2 1 1 Latent space 2 1 1 Target Metrics Optimization 1 1 Training Methodology 3 3 Unified Treatment 3 3 Inference 2 2 Loss 2 2 Missing Data 2 2 Others (Estimation, Regularization/Normalization, Domain Translation/Adaptation, Uncertainty, User Modeling Discrete Data) 5 5
  13. 13. Long Oral Oral High-Fidelity Image Generation 2 1 1 Latent space 2 1 1 Target Metrics Optimization 1 1 Training Methodology 3 3 Unified Treatment 3 3 Inference 2 2 Loss 2 2 Missing Data 2 2 Others (Estimation, Regularization/Normalization, Domain Translation/Adaptation, Uncertainty, User Modeling Discrete Data) 5 5
  14. 14. BigGAN (Brock et al., ICLR 2019) StyleGAN (Karras et al., CVPR 2019)
  15. 15. BigGAN (Brock et al., ICLR 2019) StyleGAN (Karras et al., CVPR 2019)
  16. 16. https://twitter.com/goodfellow_ian/status/1060592303859916800
  17. 17. + Spectral Normalization on Generator + Self Attention + Two Time Scale Update Rule Spectral Normalization on Discriminator Projection Discriminator SNGAN with Projection (Miyato+, ICLR’18) SAGAN (Zhang+, ICML’19) BigGAN (Brock+, ICLR’19) + Large Batch Size (256→2048) + Large Channel (64→96) + Shared Embedding + Hierarchical Latent Space ACGAN (Oden+, ICML’17) Auxiliary Classier + Orthogonal Regularization + Truncation Trick + First Singular Value Clamp + Zero-centered Gradient Penalty
  18. 18. + Spectral Normalization on Generator + Self Attention + Two Time Scale Update Rule Spectral Normalization on Discriminator Projection Discriminator SNGAN with Projection (Miyato+, ICLR’18) SAGAN (Zhang+, ICML’19) BigGAN (Brock+, ICLR’19) + Large Batch Size (256→2048) + Large Channel (64→96) + Shared Embedding + Hierarchical Latent Space ACGAN (Oden+, ICML’17) Auxiliary Classier S3GAN (Lucic+, ICML’19) + Synthesis with Inferred Labels + Semi- /Self Supervised Training + Orthogonal Regularization + Truncation Trick + First Singular Value Clamp + Zero-centered Gradient Penalty
  19. 19. + Spectral Normalization on Generator + Self Attention + Two Time Scale Update Rule Spectral Normalization on Discriminator Projection Discriminator SNGAN with Projection (Miyato+, ICLR’18) SAGAN (Zhang+, ICML’19) BigGAN (Brock+, ICLR’19) + Large Batch Size (256→2048) + Large Channel (64→96) + Shared Embedding + Hierarchical Latent Space ACGAN (Oden+, ICML’17) Auxiliary Classier S3GAN (Lucic+, ICML’19) + Synthesis with Inferred Labels + Semi- /Self Supervised Training + Orthogonal Regularization + Truncation Trick + First Singular Value Clamp + Zero-centered Gradient Penalty ICLR’19/ICML’19
  20. 20. + Spectral Normalization on Generator + Self Attention + Two Time Scale Update Rule Spectral Normalization on Discriminator Projection Discriminator SNGAN with Projection (Miyato+, ICLR’18) SAGAN (Zhang+, ICML’19) BigGAN (Brock+, ICLR’19) + Large Batch Size (256→2048) + Large Channel (64→96) + Shared Embedding + Hierarchical Latent Space ACGAN (Oden+, ICML’17) Auxiliary Classier S3GAN (Lucic+, ICML’19) + Synthesis with Inferred Labels + Semi- /Self Supervised Training + Orthogonal Regularization + Truncation Trick + First Singular Value Clamp + Zero-centered Gradient Penalty ICLR’19/ICML’19
  21. 21. + Spectral Normalization on Generator + Self Attention + Two Time Scale Update Rule Spectral Normalization on Discriminator Projection Discriminator SNGAN with Projection (Miyato+, ICLR’18) SAGAN (Zhang+, ICML’19) BigGAN (Brock+, ICLR’19) + Large Batch Size (256→2048) + Large Channel (64→96) + Shared Embedding + Hierarchical Latent Space ACGAN (Oden+, ICML’17) Auxiliary Classier S3GAN (Lucic+, ICML’19) + Synthesis with Inferred Labels + Semi- /Self Supervised Training + Orthogonal Regularization + Truncation Trick + First Singular Value Clamp + Zero-centered Gradient Penalty ICLR’19/ICML’19
  22. 22. + Spectral Normalization on Generator + Self Attention + Two Time Scale Update Rule Spectral Normalization on Discriminator Projection Discriminator SNGAN with Projection (Miyato+, ICLR’18) SAGAN (Zhang+, ICML’19) BigGAN (Brock+, ICLR’19) + Large Batch Size (256→2048) + Large Channel (64→96) + Shared Embedding + Hierarchical Latent Space ACGAN (Oden+, ICML’17) Auxiliary Classier S3GAN (Lucic+, ICML’19) + Synthesis with Inferred Labels + Semi- /Self Supervised Training + Orthogonal Regularization + Truncation Trick + First Singular Value Clamp + Zero-centered Gradient Penalty ICLR’19/ICML’19
  23. 23. + Spectral Normalization on Generator + Self Attention + Two Time Scale Update Rule Spectral Normalization on Discriminator Projection Discriminator SNGAN with Projection (Miyato+, ICLR’18) SAGAN (Zhang+, ICML’19) BigGAN (Brock+, ICLR’19) + Large Batch Size (256→2048) + Large Channel (64→96) + Shared Embedding + Hierarchical Latent Space ACGAN (Oden+, ICML’17) Auxiliary Classier S3GAN (Lucic+, ICML’19) + Synthesis with Inferred Labels + Semi- /Self Supervised Training + Orthogonal Regularization + Truncation Trick + First Singular Value Clamp + Zero-centered Gradient Penalty ICLR’19/ICML’19
  24. 24. Self-Attention Generative Adversarial Networks. Han Zhang, Ian Goodfellow, Dimitris Metaxas, Augustus Odena. arXiv: 1805.08318. In ICML 2019.
  25. 25. Self-Attention Generative Adversarial Networks. Han Zhang, Ian Goodfellow, Dimitris Metaxas, Augustus Odena. arXiv: 1805.08318. In ICML 2019.
  26. 26. + Spectral Normalization on Generator + Two Time Scale Update Rule (Heusel+, NeuIPS’17) Learning Rate - Discriminator: Generator = 4:1 Self-Attention Generative Adversarial Networks. Han Zhang, Ian Goodfellow, Dimitris Metaxas, Augustus Odena. arXiv: 1805.08318. In ICML 2019.
  27. 27. Self-Attention Generative Adversarial Networks. Han Zhang, Ian Goodfellow, Dimitris Metaxas, Augustus Odena. arXiv: 1805.08318. In ICML 2019.
  28. 28. + Spectral Normalization on Generator + Self Attention + Two Time Scale Update Rule Spectral Normalization on Discriminator Projection Discriminator SNGAN with Projection (Miyato+, ICLR’18) SAGAN (Zhang+, ICML’19) BigGAN (Brock+, ICLR’19) + Large Batch Size (256→2048) + Large Channel (64→96) + Shared Embedding + Hierarchical Latent Space ACGAN (Oden+, ICML’17) Auxiliary Classier S3GAN (Lucic+, ICML’19) + Synthesis with Inferred Labels + Semi- /Self Supervised Training + Orthogonal Regularization + Truncation Trick + First Singular Value Clamp + Zero-centered Gradient Penalty ICLR’19/ICML’19
  29. 29. + Spectral Normalization on Generator + Self Attention + Two Time Scale Update Rule (Heusel+NIPS’17) (512x512) + Spectral Normalization on Discriminator + Projection Discriminator SNGAN with Projection (Miyato+, ICLR’18) SAGAN (Zhang+, ICML’19) BigGAN (Brock+, ICLR’19) + Large Batch Size (256→2048) + Large Channel (64→96) + Shared Embedding + Hierarchical Latent Space + Truncation Trick + Orthogonal Regularization + First Singular Value Clamp + Zero-centered Gradient Penalty Large Scale GAN Training for High Fidelity Natural Image Synthesis. Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019.
  30. 30. Large Scale GAN Training for High Fidelity Natural Image Synthesis. Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019.
  31. 31. Large Scale GAN Training for High Fidelity Natural Image Synthesis. Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019. Typical Architecture Res Block up Res Block down 4. Truncation Trick 2. Shared Embedding 3. Orthogonal Regularization (without diagonal terms) 5. First Singular Value Clamp Z sampling 6. Zero-centered Gradient Penalty Spectral norm Generator Discriminator 1. Hierarchical Latent Space Architecture for ImageNet at 512x512
  32. 32. Large Scale GAN Training for High Fidelity Natural Image Synthesis. Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019. Typical Architecture Res Block up Res Block down 4. Truncation Trick 2. Shared Embedding 3. Orthogonal Regularization (without diagonal terms) 5. First Singular Value Clamp Z sampling 6. Zero-centered Gradient Penalty Spectral norm Architecture for ImageNet at 512x512 Generator Discriminator 1. Hierarchical Latent Space BigGAN - deep
  33. 33. Large Scale GAN Training for High Fidelity Natural Image Synthesis. Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019. Inception Score SNGAN SAGAN BiGGAN BiGGAN-Deep 30 140 250 42.5 25.0 5.0 FID FID vs Inception Score at 128x128FID / Inception Score (without Truncation)
  34. 34. (512x512) Large Scale GAN Training for High Fidelity Natural Image Synthesis. Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019.
  35. 35. (512x512) Large Scale GAN Training for High Fidelity Natural Image Synthesis. Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019.
  36. 36. (512x512) Large Scale GAN Training for High Fidelity Natural Image Synthesis. Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019. (512x512) Large Scale GAN Training for High Fidelity Natural Image Synthesis. Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019.
  37. 37. (512x512) Large Scale GAN Training for High Fidelity Natural Image Synthesis. Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019.
  38. 38. 49 Large Scale GAN Training for High Fidelity Natural Image Synthesis. Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019.
  39. 39. 50 Large Scale GAN Training for High Fidelity Natural Image Synthesis. Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019.
  40. 40. 51 Progressive Structure-conditional GANs (PSGAN) Full-body High-resolution Anime Generation with Progressive Structure-conditional Generative Adversarial Networks. Koichi Hamada, Kentaro Tachibana, Tianqi Li, Hiroto Honda, and Yusuke Uchida. arXiv:1809.01890. In ECCV Workshop 2018. // . 0/0 https://youtu.be/MXWm6w4E5q0 Semantic Image Synthesis with Spatially-Adaptive Normalization. Taesung Park, Ming-Yu Liu, Ting-Chun Wang, Jun-Yan Zhu. arXiv:1903.07291. In CVPR 2019. SPatially-Adaptive (DE)normalization (SPADE) [GauGAN]
  41. 41. + Spectral Normalization on Generator + Self Attention + Two Time Scale Update Rule Spectral Normalization on Discriminator Projection Discriminator SNGAN with Projection (Miyato+, ICLR’18) SAGAN (Zhang+, ICML’19) BigGAN (Brock+, ICLR’19) + Large Batch Size (256→2048) + Large Channel (64→96) + Shared Embedding + Hierarchical Latent Space ACGAN (Oden+, ICML’17) Auxiliary Classier S3GAN (Lucic+, ICML’19) + Synthesis with Inferred Labels + Semi- /Self Supervised Training + Orthogonal Regularization + Truncation Trick + First Singular Value Clamp + Zero-centered Gradient Penalty ICLR’19/ICML’19
  42. 42. High-Fidelity Image Generation With Fewer Labels. Mario Lucic, Michael Tschannen, Marvin Ritter, Xiaohua Zhai, Olivier Bachem, Sylvain Gelly. arXiv:1903.02271. In ICML 2019.
  43. 43. High-Fidelity Image Generation With Fewer Labels. Mario Lucic, Michael Tschannen, Marvin Ritter, Xiaohua Zhai, Olivier Bachem, Sylvain Gelly. arXiv:1903.02271. In ICML 2019.
  44. 44. High-Fidelity Image Generation With Fewer Labels. Mario Lucic, Michael Tschannen, Marvin Ritter, Xiaohua Zhai, Olivier Bachem, Sylvain Gelly. arXiv:1903.02271. In ICML 2019.
  45. 45. High-Fidelity Image Generation With Fewer Labels. Mario Lucic, Michael Tschannen, Marvin Ritter, Xiaohua Zhai, Olivier Bachem, Sylvain Gelly. arXiv:1903.02271. In ICML 2019.
  46. 46. High-Fidelity Image Generation With Fewer Labels. Mario Lucic, Michael Tschannen, Marvin Ritter, Xiaohua Zhai, Olivier Bachem, Sylvain Gelly. arXiv:1903.02271. In ICML 2019.
  47. 47. High-Fidelity Image Generation With Fewer Labels. Mario Lucic, Michael Tschannen, Marvin Ritter, Xiaohua Zhai, Olivier Bachem, Sylvain Gelly. arXiv:1903.02271. In ICML 2019.
  48. 48. High-Fidelity Image Generation With Fewer Labels. Mario Lucic, Michael Tschannen, Marvin Ritter, Xiaohua Zhai, Olivier Bachem, Sylvain Gelly. arXiv:1903.02271. In ICML 2019.
  49. 49. High-Fidelity Image Generation With Fewer Labels. Mario Lucic, Michael Tschannen, Marvin Ritter, Xiaohua Zhai, Olivier Bachem, Sylvain Gelly. arXiv:1903.02271. In ICML 2019.
  50. 50. High-Fidelity Image Generation With Fewer Labels. Mario Lucic, Michael Tschannen, Marvin Ritter, Xiaohua Zhai, Olivier Bachem, Sylvain Gelly. arXiv:1903.02271. In ICML 2019.
  51. 51. High-Fidelity Image Generation With Fewer Labels. Mario Lucic, Michael Tschannen, Marvin Ritter, Xiaohua Zhai, Olivier Bachem, Sylvain Gelly. arXiv:1903.02271. In ICML 2019.
  52. 52. Long Oral Oral High-Fidelity Image Generation 2 1 1 Latent space 2 1 1 Target Metrics Optimization 1 1 Training Methodology 3 3 Unified Treatment 3 3 Inference 2 2 Loss 2 2 Missing Data 2 2 Others (Estimation, Regularization/Normalization, Domain Translation/Adaptation, Uncertainty, User Modeling Discrete Data) 5 5
  53. 53. Flat Metric Minimization with Applications in Generative Modeling Thomas Möllenhoff, Daniel Cremers. arXiv:1905.04730. In ICML 2019.
  54. 54. Non-Parametric Priors For Generative Adversarial Networks. Rajhans Singh, Pavan Turaga, Suren Jayasuriya, Ravi Garg, Martin W. Braun. arXiv:1905.07061. In ICML 2019. Interpolation Inception Score / FID Non-Prarametric Prior
  55. 55. MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement Szu-Wei Fu, Chien-Feng Liao, Yu Tsao, Shou-De Lin. arXiv:1905.04874. In ICML 2019. Discriminator Generator Learning Curve of Objective Function (Validation set) (S ) Evaluation
  56. 56. Long Oral Oral High-Fidelity Image Generation 2 1 1 Latent space 2 1 1 Target Metrics Optimization 1 1 Training Methodology 3 3 Unified Treatment 3 3 Inference 2 2 Loss 2 2 Missing Data 2 2 Others (Estimation, Regularization/Normalization, Domain Translation/Adaptation, Uncertainty, User Modeling Discrete Data) 5 5
  57. 57. Long Oral Oral High-Fidelity Image Generation 2 1 1 Latent space 2 1 1 Target Metrics Optimization 1 1 Training Methodology 3 3 Unified Treatment 3 3 Inference 2 2 Loss 2 2 Missing Data 2 2 Others (Estimation, Regularization/Normalization, Domain Translation/Adaptation, Uncertainty, User Modeling Discrete Data) 5 5
  58. 58. 77 878 12 7 /.0 .1 1DeNA AI : O * . A A TL K S :A A :L K

×