SlideShare a Scribd company logo
1 of 72
1
1 3 5 7
2 4 6 8
ProgressiveGAN (Karras et al., ICLR 2018) BigGAN (Brock et al., ICLR 2019)
1 3 5 7
2 4 6 8
BigGAN (Brock et al., ICLR 2019) StyleGAN (Karras et al., CVPR 2019)
2010- : DeNA /
2011– : Mobage
2014- : DeNA
Mobage
: ( )
TokyoWebmining
-
- 2010 60
/Koichi Hamada (@hamadakoichi)
/Koichi Hamada (@hamadakoichi)
78 : : 102*0DeNA AI :
TZ ... ./ 0 KD SL KA N O
N KD SL K N W
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.
// . /
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.
BigGAN (Brock et al., ICLR 2019) StyleGAN (Karras et al., CVPR 2019)
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
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
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
BigGAN (Brock et al., ICLR 2019) StyleGAN (Karras et al., CVPR 2019)
BigGAN (Brock et al., ICLR 2019) StyleGAN (Karras et al., CVPR 2019)
https://twitter.com/goodfellow_ian/status/1060592303859916800
+ 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
+ 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
+ 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
+ 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
+ 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
+ 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
+ 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
Self-Attention Generative Adversarial Networks.
Han Zhang, Ian Goodfellow, Dimitris Metaxas, Augustus Odena. arXiv: 1805.08318. In ICML 2019.
Self-Attention Generative Adversarial Networks.
Han Zhang, Ian Goodfellow, Dimitris Metaxas, Augustus Odena. arXiv: 1805.08318. In ICML 2019.
+ 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.
Self-Attention Generative Adversarial Networks.
Han Zhang, Ian Goodfellow, Dimitris Metaxas, Augustus Odena. arXiv: 1805.08318. In ICML 2019.
+ 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
+ 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.
Large Scale GAN Training for High Fidelity Natural Image Synthesis.
Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019.
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
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
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)
(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.
(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.
(512x512)
Large Scale GAN Training for High Fidelity Natural Image Synthesis.
Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019.
49
Large Scale GAN Training for High Fidelity Natural Image Synthesis.
Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019.
50
Large Scale GAN Training for High Fidelity Natural Image Synthesis.
Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019.
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]
+ 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
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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
Flat Metric Minimization with Applications in Generative Modeling
Thomas Möllenhoff, Daniel Cremers. arXiv:1905.04730. In ICML 2019.
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
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
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
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
77 878 12 7 /.0 .1 1DeNA AI :
O * . A A TL K S :A A :L K
Generative Adversarial Networks @ ICML 2019

More Related Content

Similar to Generative Adversarial Networks @ ICML 2019

AILABS Lecture Series - Is AI The New Electricity. Topic - Deep Learning - Ev...
AILABS Lecture Series - Is AI The New Electricity. Topic - Deep Learning - Ev...AILABS Lecture Series - Is AI The New Electricity. Topic - Deep Learning - Ev...
AILABS Lecture Series - Is AI The New Electricity. Topic - Deep Learning - Ev...AILABS Academy
 
Learning do discover: machine learning in high-energy physics
Learning do discover: machine learning in high-energy physicsLearning do discover: machine learning in high-energy physics
Learning do discover: machine learning in high-energy physicsBalázs Kégl
 
Reproducibility and differential analysis with selfish
Reproducibility and differential analysis with selfishReproducibility and differential analysis with selfish
Reproducibility and differential analysis with selfishtuxette
 
"Separable Convolutions for Efficient Implementation of CNNs and Other Vision...
"Separable Convolutions for Efficient Implementation of CNNs and Other Vision..."Separable Convolutions for Efficient Implementation of CNNs and Other Vision...
"Separable Convolutions for Efficient Implementation of CNNs and Other Vision...Edge AI and Vision Alliance
 
Advancing Fusion Science with CGYRO using GPU-based Leadership Systems
Advancing Fusion Science with CGYRO using GPU-based Leadership SystemsAdvancing Fusion Science with CGYRO using GPU-based Leadership Systems
Advancing Fusion Science with CGYRO using GPU-based Leadership Systemsinside-BigData.com
 
Generative adversarial networks
Generative adversarial networksGenerative adversarial networks
Generative adversarial networksDing Li
 
COMPARISON OF COMPUTED RADIOGRAPHY(CR) AND DIGITAL RADIOGRAPHY(DR) IMAGE QUAL...
COMPARISON OF COMPUTED RADIOGRAPHY(CR) AND DIGITAL RADIOGRAPHY(DR) IMAGE QUAL...COMPARISON OF COMPUTED RADIOGRAPHY(CR) AND DIGITAL RADIOGRAPHY(DR) IMAGE QUAL...
COMPARISON OF COMPUTED RADIOGRAPHY(CR) AND DIGITAL RADIOGRAPHY(DR) IMAGE QUAL...AM Publications
 
Machine Learning Applications
Machine Learning ApplicationsMachine Learning Applications
Machine Learning ApplicationsSimplyInsight
 
Style gan2 review
Style gan2 reviewStyle gan2 review
Style gan2 reviewtaeseon ryu
 
21cm cosmology+machine learning_update
21cm cosmology+machine learning_update21cm cosmology+machine learning_update
21cm cosmology+machine learning_updateHayato Shimabukuro
 
AIAA Future of Fluids 2018 Balaji
AIAA Future of Fluids 2018 BalajiAIAA Future of Fluids 2018 Balaji
AIAA Future of Fluids 2018 BalajiQiqi Wang
 
Look, Radiate, and Learn: Self-Supervised Localisation via Radio-Visual Corre...
Look, Radiate, and Learn: Self-Supervised Localisation via Radio-Visual Corre...Look, Radiate, and Learn: Self-Supervised Localisation via Radio-Visual Corre...
Look, Radiate, and Learn: Self-Supervised Localisation via Radio-Visual Corre...MohammedAlloulah
 

Similar to Generative Adversarial Networks @ ICML 2019 (13)

AILABS Lecture Series - Is AI The New Electricity. Topic - Deep Learning - Ev...
AILABS Lecture Series - Is AI The New Electricity. Topic - Deep Learning - Ev...AILABS Lecture Series - Is AI The New Electricity. Topic - Deep Learning - Ev...
AILABS Lecture Series - Is AI The New Electricity. Topic - Deep Learning - Ev...
 
Learning do discover: machine learning in high-energy physics
Learning do discover: machine learning in high-energy physicsLearning do discover: machine learning in high-energy physics
Learning do discover: machine learning in high-energy physics
 
Reproducibility and differential analysis with selfish
Reproducibility and differential analysis with selfishReproducibility and differential analysis with selfish
Reproducibility and differential analysis with selfish
 
"Separable Convolutions for Efficient Implementation of CNNs and Other Vision...
"Separable Convolutions for Efficient Implementation of CNNs and Other Vision..."Separable Convolutions for Efficient Implementation of CNNs and Other Vision...
"Separable Convolutions for Efficient Implementation of CNNs and Other Vision...
 
Advancing Fusion Science with CGYRO using GPU-based Leadership Systems
Advancing Fusion Science with CGYRO using GPU-based Leadership SystemsAdvancing Fusion Science with CGYRO using GPU-based Leadership Systems
Advancing Fusion Science with CGYRO using GPU-based Leadership Systems
 
Generative adversarial networks
Generative adversarial networksGenerative adversarial networks
Generative adversarial networks
 
COMPARISON OF COMPUTED RADIOGRAPHY(CR) AND DIGITAL RADIOGRAPHY(DR) IMAGE QUAL...
COMPARISON OF COMPUTED RADIOGRAPHY(CR) AND DIGITAL RADIOGRAPHY(DR) IMAGE QUAL...COMPARISON OF COMPUTED RADIOGRAPHY(CR) AND DIGITAL RADIOGRAPHY(DR) IMAGE QUAL...
COMPARISON OF COMPUTED RADIOGRAPHY(CR) AND DIGITAL RADIOGRAPHY(DR) IMAGE QUAL...
 
Armando Benitez -- Data x Desing
Armando Benitez -- Data x DesingArmando Benitez -- Data x Desing
Armando Benitez -- Data x Desing
 
Machine Learning Applications
Machine Learning ApplicationsMachine Learning Applications
Machine Learning Applications
 
Style gan2 review
Style gan2 reviewStyle gan2 review
Style gan2 review
 
21cm cosmology+machine learning_update
21cm cosmology+machine learning_update21cm cosmology+machine learning_update
21cm cosmology+machine learning_update
 
AIAA Future of Fluids 2018 Balaji
AIAA Future of Fluids 2018 BalajiAIAA Future of Fluids 2018 Balaji
AIAA Future of Fluids 2018 Balaji
 
Look, Radiate, and Learn: Self-Supervised Localisation via Radio-Visual Corre...
Look, Radiate, and Learn: Self-Supervised Localisation via Radio-Visual Corre...Look, Radiate, and Learn: Self-Supervised Localisation via Radio-Visual Corre...
Look, Radiate, and Learn: Self-Supervised Localisation via Radio-Visual Corre...
 

More from Koichi Hamada

Generative Adversarial Networks (GAN) @ NIPS2017
Generative Adversarial Networks (GAN) @ NIPS2017Generative Adversarial Networks (GAN) @ NIPS2017
Generative Adversarial Networks (GAN) @ NIPS2017Koichi Hamada
 
DeNAのAI活用したサービス開発
DeNAのAI活用したサービス開発DeNAのAI活用したサービス開発
DeNAのAI活用したサービス開発Koichi Hamada
 
対話返答生成における個性の追加反映
対話返答生成における個性の追加反映対話返答生成における個性の追加反映
対話返答生成における個性の追加反映Koichi Hamada
 
Generative Adversarial Networks (GAN) の学習方法進展・画像生成・教師なし画像変換
Generative Adversarial Networks (GAN) の学習方法進展・画像生成・教師なし画像変換Generative Adversarial Networks (GAN) の学習方法進展・画像生成・教師なし画像変換
Generative Adversarial Networks (GAN) の学習方法進展・画像生成・教師なし画像変換Koichi Hamada
 
DeNAの機械学習・深層学習活用した 体験提供の挑戦
DeNAの機械学習・深層学習活用した体験提供の挑戦DeNAの機械学習・深層学習活用した体験提供の挑戦
DeNAの機械学習・深層学習活用した 体験提供の挑戦Koichi Hamada
 
Laplacian Pyramid of Generative Adversarial Networks (LAPGAN) - NIPS2015読み会 #...
Laplacian Pyramid of Generative Adversarial Networks (LAPGAN) - NIPS2015読み会 #...Laplacian Pyramid of Generative Adversarial Networks (LAPGAN) - NIPS2015読み会 #...
Laplacian Pyramid of Generative Adversarial Networks (LAPGAN) - NIPS2015読み会 #...Koichi Hamada
 
DeNAの大規模データマイニング活用したサービス開発
DeNAの大規模データマイニング活用したサービス開発DeNAの大規模データマイニング活用したサービス開発
DeNAの大規模データマイニング活用したサービス開発Koichi Hamada
 
『MobageのAnalytics活用したサービス開発』 - データマイニングCROSS2014 #CROSS2014
『MobageのAnalytics活用したサービス開発』 - データマイニングCROSS2014 #CROSS2014『MobageのAnalytics活用したサービス開発』 - データマイニングCROSS2014 #CROSS2014
『MobageのAnalytics活用したサービス開発』 - データマイニングCROSS2014 #CROSS2014Koichi Hamada
 
『Mobageの大規模データマイニング活用と 意思決定』- #IBIS 2012 -ビジネスと機械学習の接点-
『Mobageの大規模データマイニング活用と 意思決定』- #IBIS 2012 -ビジネスと機械学習の接点- 『Mobageの大規模データマイニング活用と 意思決定』- #IBIS 2012 -ビジネスと機械学習の接点-
『Mobageの大規模データマイニング活用と 意思決定』- #IBIS 2012 -ビジネスと機械学習の接点- Koichi Hamada
 
複雑ネットワーク上の伝搬法則の数理
複雑ネットワーク上の伝搬法則の数理複雑ネットワーク上の伝搬法則の数理
複雑ネットワーク上の伝搬法則の数理Koichi Hamada
 
データマイニングCROSS 2012 Opening Talk - データマイニングの実サービス・ビジネス適用と展望
データマイニングCROSS 2012 Opening Talk - データマイニングの実サービス・ビジネス適用と展望 データマイニングCROSS 2012 Opening Talk - データマイニングの実サービス・ビジネス適用と展望
データマイニングCROSS 2012 Opening Talk - データマイニングの実サービス・ビジネス適用と展望 Koichi Hamada
 
データマイニングCROSS 第2部-機械学習・大規模分散処理
データマイニングCROSS 第2部-機械学習・大規模分散処理データマイニングCROSS 第2部-機械学習・大規模分散処理
データマイニングCROSS 第2部-機械学習・大規模分散処理Koichi Hamada
 
Large Scale Data Mining of the Mobage Service - #PRMU 2011 #Mahout #Hadoop
Large Scale Data Mining of the Mobage Service - #PRMU 2011 #Mahout #HadoopLarge Scale Data Mining of the Mobage Service - #PRMU 2011 #Mahout #Hadoop
Large Scale Data Mining of the Mobage Service - #PRMU 2011 #Mahout #HadoopKoichi Hamada
 
"Mahout Recommendation" - #TokyoWebmining 14th
"Mahout Recommendation" -  #TokyoWebmining 14th"Mahout Recommendation" -  #TokyoWebmining 14th
"Mahout Recommendation" - #TokyoWebmining 14thKoichi Hamada
 
Mahout JP - #TokyoWebmining 11th #MahoutJP
Mahout JP -  #TokyoWebmining 11th #MahoutJP Mahout JP -  #TokyoWebmining 11th #MahoutJP
Mahout JP - #TokyoWebmining 11th #MahoutJP Koichi Hamada
 
10回開催記念 「データマイニング+WEB ~データマイニング・機械学習活用による継続進化~」ー第10回データマイニング+WEB勉強会@東京ー #Toky...
10回開催記念 「データマイニング+WEB ~データマイニング・機械学習活用による継続進化~」ー第10回データマイニング+WEB勉強会@東京ー #Toky...10回開催記念 「データマイニング+WEB ~データマイニング・機械学習活用による継続進化~」ー第10回データマイニング+WEB勉強会@東京ー #Toky...
10回開催記念 「データマイニング+WEB ~データマイニング・機械学習活用による継続進化~」ー第10回データマイニング+WEB勉強会@東京ー #Toky...Koichi Hamada
 
『モバゲーの大規模データマイニング基盤におけるHadoop活用』-Hadoop Conference Japan 2011- #hcj2011
『モバゲーの大規模データマイニング基盤におけるHadoop活用』-Hadoop Conference Japan 2011- #hcj2011 『モバゲーの大規模データマイニング基盤におけるHadoop活用』-Hadoop Conference Japan 2011- #hcj2011
『モバゲーの大規模データマイニング基盤におけるHadoop活用』-Hadoop Conference Japan 2011- #hcj2011 Koichi Hamada
 
「R言語による Random Forest 徹底入門 -集団学習による分類・予測-」 - #TokyoR #11
「R言語による Random Forest 徹底入門 -集団学習による分類・予測-」 - #TokyoR  #11「R言語による Random Forest 徹底入門 -集団学習による分類・予測-」 - #TokyoR  #11
「R言語による Random Forest 徹底入門 -集団学習による分類・予測-」 - #TokyoR #11Koichi Hamada
 
Mahout Canopy Clustering - #TokyoWebmining 9
Mahout Canopy Clustering - #TokyoWebmining 9Mahout Canopy Clustering - #TokyoWebmining 9
Mahout Canopy Clustering - #TokyoWebmining 9Koichi Hamada
 
Apache Mahout - Random Forests - #TokyoWebmining #8
Apache Mahout - Random Forests - #TokyoWebmining #8 Apache Mahout - Random Forests - #TokyoWebmining #8
Apache Mahout - Random Forests - #TokyoWebmining #8 Koichi Hamada
 

More from Koichi Hamada (20)

Generative Adversarial Networks (GAN) @ NIPS2017
Generative Adversarial Networks (GAN) @ NIPS2017Generative Adversarial Networks (GAN) @ NIPS2017
Generative Adversarial Networks (GAN) @ NIPS2017
 
DeNAのAI活用したサービス開発
DeNAのAI活用したサービス開発DeNAのAI活用したサービス開発
DeNAのAI活用したサービス開発
 
対話返答生成における個性の追加反映
対話返答生成における個性の追加反映対話返答生成における個性の追加反映
対話返答生成における個性の追加反映
 
Generative Adversarial Networks (GAN) の学習方法進展・画像生成・教師なし画像変換
Generative Adversarial Networks (GAN) の学習方法進展・画像生成・教師なし画像変換Generative Adversarial Networks (GAN) の学習方法進展・画像生成・教師なし画像変換
Generative Adversarial Networks (GAN) の学習方法進展・画像生成・教師なし画像変換
 
DeNAの機械学習・深層学習活用した 体験提供の挑戦
DeNAの機械学習・深層学習活用した体験提供の挑戦DeNAの機械学習・深層学習活用した体験提供の挑戦
DeNAの機械学習・深層学習活用した 体験提供の挑戦
 
Laplacian Pyramid of Generative Adversarial Networks (LAPGAN) - NIPS2015読み会 #...
Laplacian Pyramid of Generative Adversarial Networks (LAPGAN) - NIPS2015読み会 #...Laplacian Pyramid of Generative Adversarial Networks (LAPGAN) - NIPS2015読み会 #...
Laplacian Pyramid of Generative Adversarial Networks (LAPGAN) - NIPS2015読み会 #...
 
DeNAの大規模データマイニング活用したサービス開発
DeNAの大規模データマイニング活用したサービス開発DeNAの大規模データマイニング活用したサービス開発
DeNAの大規模データマイニング活用したサービス開発
 
『MobageのAnalytics活用したサービス開発』 - データマイニングCROSS2014 #CROSS2014
『MobageのAnalytics活用したサービス開発』 - データマイニングCROSS2014 #CROSS2014『MobageのAnalytics活用したサービス開発』 - データマイニングCROSS2014 #CROSS2014
『MobageのAnalytics活用したサービス開発』 - データマイニングCROSS2014 #CROSS2014
 
『Mobageの大規模データマイニング活用と 意思決定』- #IBIS 2012 -ビジネスと機械学習の接点-
『Mobageの大規模データマイニング活用と 意思決定』- #IBIS 2012 -ビジネスと機械学習の接点- 『Mobageの大規模データマイニング活用と 意思決定』- #IBIS 2012 -ビジネスと機械学習の接点-
『Mobageの大規模データマイニング活用と 意思決定』- #IBIS 2012 -ビジネスと機械学習の接点-
 
複雑ネットワーク上の伝搬法則の数理
複雑ネットワーク上の伝搬法則の数理複雑ネットワーク上の伝搬法則の数理
複雑ネットワーク上の伝搬法則の数理
 
データマイニングCROSS 2012 Opening Talk - データマイニングの実サービス・ビジネス適用と展望
データマイニングCROSS 2012 Opening Talk - データマイニングの実サービス・ビジネス適用と展望 データマイニングCROSS 2012 Opening Talk - データマイニングの実サービス・ビジネス適用と展望
データマイニングCROSS 2012 Opening Talk - データマイニングの実サービス・ビジネス適用と展望
 
データマイニングCROSS 第2部-機械学習・大規模分散処理
データマイニングCROSS 第2部-機械学習・大規模分散処理データマイニングCROSS 第2部-機械学習・大規模分散処理
データマイニングCROSS 第2部-機械学習・大規模分散処理
 
Large Scale Data Mining of the Mobage Service - #PRMU 2011 #Mahout #Hadoop
Large Scale Data Mining of the Mobage Service - #PRMU 2011 #Mahout #HadoopLarge Scale Data Mining of the Mobage Service - #PRMU 2011 #Mahout #Hadoop
Large Scale Data Mining of the Mobage Service - #PRMU 2011 #Mahout #Hadoop
 
"Mahout Recommendation" - #TokyoWebmining 14th
"Mahout Recommendation" -  #TokyoWebmining 14th"Mahout Recommendation" -  #TokyoWebmining 14th
"Mahout Recommendation" - #TokyoWebmining 14th
 
Mahout JP - #TokyoWebmining 11th #MahoutJP
Mahout JP -  #TokyoWebmining 11th #MahoutJP Mahout JP -  #TokyoWebmining 11th #MahoutJP
Mahout JP - #TokyoWebmining 11th #MahoutJP
 
10回開催記念 「データマイニング+WEB ~データマイニング・機械学習活用による継続進化~」ー第10回データマイニング+WEB勉強会@東京ー #Toky...
10回開催記念 「データマイニング+WEB ~データマイニング・機械学習活用による継続進化~」ー第10回データマイニング+WEB勉強会@東京ー #Toky...10回開催記念 「データマイニング+WEB ~データマイニング・機械学習活用による継続進化~」ー第10回データマイニング+WEB勉強会@東京ー #Toky...
10回開催記念 「データマイニング+WEB ~データマイニング・機械学習活用による継続進化~」ー第10回データマイニング+WEB勉強会@東京ー #Toky...
 
『モバゲーの大規模データマイニング基盤におけるHadoop活用』-Hadoop Conference Japan 2011- #hcj2011
『モバゲーの大規模データマイニング基盤におけるHadoop活用』-Hadoop Conference Japan 2011- #hcj2011 『モバゲーの大規模データマイニング基盤におけるHadoop活用』-Hadoop Conference Japan 2011- #hcj2011
『モバゲーの大規模データマイニング基盤におけるHadoop活用』-Hadoop Conference Japan 2011- #hcj2011
 
「R言語による Random Forest 徹底入門 -集団学習による分類・予測-」 - #TokyoR #11
「R言語による Random Forest 徹底入門 -集団学習による分類・予測-」 - #TokyoR  #11「R言語による Random Forest 徹底入門 -集団学習による分類・予測-」 - #TokyoR  #11
「R言語による Random Forest 徹底入門 -集団学習による分類・予測-」 - #TokyoR #11
 
Mahout Canopy Clustering - #TokyoWebmining 9
Mahout Canopy Clustering - #TokyoWebmining 9Mahout Canopy Clustering - #TokyoWebmining 9
Mahout Canopy Clustering - #TokyoWebmining 9
 
Apache Mahout - Random Forests - #TokyoWebmining #8
Apache Mahout - Random Forests - #TokyoWebmining #8 Apache Mahout - Random Forests - #TokyoWebmining #8
Apache Mahout - Random Forests - #TokyoWebmining #8
 

Recently uploaded

ONLINE VOTING SYSTEM SE Project for vote
ONLINE VOTING SYSTEM SE Project for voteONLINE VOTING SYSTEM SE Project for vote
ONLINE VOTING SYSTEM SE Project for voteRaunakRastogi4
 
Human & Veterinary Respiratory Physilogy_DR.E.Muralinath_Associate Professor....
Human & Veterinary Respiratory Physilogy_DR.E.Muralinath_Associate Professor....Human & Veterinary Respiratory Physilogy_DR.E.Muralinath_Associate Professor....
Human & Veterinary Respiratory Physilogy_DR.E.Muralinath_Associate Professor....muralinath2
 
module for grade 9 for distance learning
module for grade 9 for distance learningmodule for grade 9 for distance learning
module for grade 9 for distance learninglevieagacer
 
Bhiwandi Bhiwandi ❤CALL GIRL 7870993772 ❤CALL GIRLS ESCORT SERVICE In Bhiwan...
Bhiwandi Bhiwandi ❤CALL GIRL 7870993772 ❤CALL GIRLS  ESCORT SERVICE In Bhiwan...Bhiwandi Bhiwandi ❤CALL GIRL 7870993772 ❤CALL GIRLS  ESCORT SERVICE In Bhiwan...
Bhiwandi Bhiwandi ❤CALL GIRL 7870993772 ❤CALL GIRLS ESCORT SERVICE In Bhiwan...Monika Rani
 
development of diagnostic enzyme assay to detect leuser virus
development of diagnostic enzyme assay to detect leuser virusdevelopment of diagnostic enzyme assay to detect leuser virus
development of diagnostic enzyme assay to detect leuser virusNazaninKarimi6
 
Terpineol and it's characterization pptx
Terpineol and it's characterization pptxTerpineol and it's characterization pptx
Terpineol and it's characterization pptxMuhammadRazzaq31
 
POGONATUM : morphology, anatomy, reproduction etc.
POGONATUM : morphology, anatomy, reproduction etc.POGONATUM : morphology, anatomy, reproduction etc.
POGONATUM : morphology, anatomy, reproduction etc.Cherry
 
PODOCARPUS...........................pptx
PODOCARPUS...........................pptxPODOCARPUS...........................pptx
PODOCARPUS...........................pptxCherry
 
Site specific recombination and transposition.........pdf
Site specific recombination and transposition.........pdfSite specific recombination and transposition.........pdf
Site specific recombination and transposition.........pdfCherry
 
Efficient spin-up of Earth System Models usingsequence acceleration
Efficient spin-up of Earth System Models usingsequence accelerationEfficient spin-up of Earth System Models usingsequence acceleration
Efficient spin-up of Earth System Models usingsequence accelerationSérgio Sacani
 
Cot curve, melting temperature, unique and repetitive DNA
Cot curve, melting temperature, unique and repetitive DNACot curve, melting temperature, unique and repetitive DNA
Cot curve, melting temperature, unique and repetitive DNACherry
 
Role of AI in seed science Predictive modelling and Beyond.pptx
Role of AI in seed science  Predictive modelling and  Beyond.pptxRole of AI in seed science  Predictive modelling and  Beyond.pptx
Role of AI in seed science Predictive modelling and Beyond.pptxArvind Kumar
 
(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...
(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...
(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...Scintica Instrumentation
 
Dr. E. Muralinath_ Blood indices_clinical aspects
Dr. E. Muralinath_ Blood indices_clinical  aspectsDr. E. Muralinath_ Blood indices_clinical  aspects
Dr. E. Muralinath_ Blood indices_clinical aspectsmuralinath2
 
Cyathodium bryophyte: morphology, anatomy, reproduction etc.
Cyathodium bryophyte: morphology, anatomy, reproduction etc.Cyathodium bryophyte: morphology, anatomy, reproduction etc.
Cyathodium bryophyte: morphology, anatomy, reproduction etc.Cherry
 
Call Girls Ahmedabad +917728919243 call me Independent Escort Service
Call Girls Ahmedabad +917728919243 call me Independent Escort ServiceCall Girls Ahmedabad +917728919243 call me Independent Escort Service
Call Girls Ahmedabad +917728919243 call me Independent Escort Serviceshivanisharma5244
 
Factory Acceptance Test( FAT).pptx .
Factory Acceptance Test( FAT).pptx       .Factory Acceptance Test( FAT).pptx       .
Factory Acceptance Test( FAT).pptx .Poonam Aher Patil
 
TransientOffsetin14CAftertheCarringtonEventRecordedbyPolarTreeRings
TransientOffsetin14CAftertheCarringtonEventRecordedbyPolarTreeRingsTransientOffsetin14CAftertheCarringtonEventRecordedbyPolarTreeRings
TransientOffsetin14CAftertheCarringtonEventRecordedbyPolarTreeRingsSérgio Sacani
 
GBSN - Biochemistry (Unit 2) Basic concept of organic chemistry
GBSN - Biochemistry (Unit 2) Basic concept of organic chemistry GBSN - Biochemistry (Unit 2) Basic concept of organic chemistry
GBSN - Biochemistry (Unit 2) Basic concept of organic chemistry Areesha Ahmad
 

Recently uploaded (20)

ONLINE VOTING SYSTEM SE Project for vote
ONLINE VOTING SYSTEM SE Project for voteONLINE VOTING SYSTEM SE Project for vote
ONLINE VOTING SYSTEM SE Project for vote
 
Human & Veterinary Respiratory Physilogy_DR.E.Muralinath_Associate Professor....
Human & Veterinary Respiratory Physilogy_DR.E.Muralinath_Associate Professor....Human & Veterinary Respiratory Physilogy_DR.E.Muralinath_Associate Professor....
Human & Veterinary Respiratory Physilogy_DR.E.Muralinath_Associate Professor....
 
module for grade 9 for distance learning
module for grade 9 for distance learningmodule for grade 9 for distance learning
module for grade 9 for distance learning
 
Bhiwandi Bhiwandi ❤CALL GIRL 7870993772 ❤CALL GIRLS ESCORT SERVICE In Bhiwan...
Bhiwandi Bhiwandi ❤CALL GIRL 7870993772 ❤CALL GIRLS  ESCORT SERVICE In Bhiwan...Bhiwandi Bhiwandi ❤CALL GIRL 7870993772 ❤CALL GIRLS  ESCORT SERVICE In Bhiwan...
Bhiwandi Bhiwandi ❤CALL GIRL 7870993772 ❤CALL GIRLS ESCORT SERVICE In Bhiwan...
 
development of diagnostic enzyme assay to detect leuser virus
development of diagnostic enzyme assay to detect leuser virusdevelopment of diagnostic enzyme assay to detect leuser virus
development of diagnostic enzyme assay to detect leuser virus
 
Terpineol and it's characterization pptx
Terpineol and it's characterization pptxTerpineol and it's characterization pptx
Terpineol and it's characterization pptx
 
POGONATUM : morphology, anatomy, reproduction etc.
POGONATUM : morphology, anatomy, reproduction etc.POGONATUM : morphology, anatomy, reproduction etc.
POGONATUM : morphology, anatomy, reproduction etc.
 
PODOCARPUS...........................pptx
PODOCARPUS...........................pptxPODOCARPUS...........................pptx
PODOCARPUS...........................pptx
 
Site specific recombination and transposition.........pdf
Site specific recombination and transposition.........pdfSite specific recombination and transposition.........pdf
Site specific recombination and transposition.........pdf
 
Efficient spin-up of Earth System Models usingsequence acceleration
Efficient spin-up of Earth System Models usingsequence accelerationEfficient spin-up of Earth System Models usingsequence acceleration
Efficient spin-up of Earth System Models usingsequence acceleration
 
Cot curve, melting temperature, unique and repetitive DNA
Cot curve, melting temperature, unique and repetitive DNACot curve, melting temperature, unique and repetitive DNA
Cot curve, melting temperature, unique and repetitive DNA
 
Role of AI in seed science Predictive modelling and Beyond.pptx
Role of AI in seed science  Predictive modelling and  Beyond.pptxRole of AI in seed science  Predictive modelling and  Beyond.pptx
Role of AI in seed science Predictive modelling and Beyond.pptx
 
(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...
(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...
(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...
 
Dr. E. Muralinath_ Blood indices_clinical aspects
Dr. E. Muralinath_ Blood indices_clinical  aspectsDr. E. Muralinath_ Blood indices_clinical  aspects
Dr. E. Muralinath_ Blood indices_clinical aspects
 
Cyathodium bryophyte: morphology, anatomy, reproduction etc.
Cyathodium bryophyte: morphology, anatomy, reproduction etc.Cyathodium bryophyte: morphology, anatomy, reproduction etc.
Cyathodium bryophyte: morphology, anatomy, reproduction etc.
 
Call Girls Ahmedabad +917728919243 call me Independent Escort Service
Call Girls Ahmedabad +917728919243 call me Independent Escort ServiceCall Girls Ahmedabad +917728919243 call me Independent Escort Service
Call Girls Ahmedabad +917728919243 call me Independent Escort Service
 
Factory Acceptance Test( FAT).pptx .
Factory Acceptance Test( FAT).pptx       .Factory Acceptance Test( FAT).pptx       .
Factory Acceptance Test( FAT).pptx .
 
PATNA CALL GIRLS 8617370543 LOW PRICE ESCORT SERVICE
PATNA CALL GIRLS 8617370543 LOW PRICE ESCORT SERVICEPATNA CALL GIRLS 8617370543 LOW PRICE ESCORT SERVICE
PATNA CALL GIRLS 8617370543 LOW PRICE ESCORT SERVICE
 
TransientOffsetin14CAftertheCarringtonEventRecordedbyPolarTreeRings
TransientOffsetin14CAftertheCarringtonEventRecordedbyPolarTreeRingsTransientOffsetin14CAftertheCarringtonEventRecordedbyPolarTreeRings
TransientOffsetin14CAftertheCarringtonEventRecordedbyPolarTreeRings
 
GBSN - Biochemistry (Unit 2) Basic concept of organic chemistry
GBSN - Biochemistry (Unit 2) Basic concept of organic chemistry GBSN - Biochemistry (Unit 2) Basic concept of organic chemistry
GBSN - Biochemistry (Unit 2) Basic concept of organic chemistry
 

Generative Adversarial Networks @ ICML 2019

  • 1. 1
  • 2.
  • 3.
  • 4. 1 3 5 7 2 4 6 8
  • 5. ProgressiveGAN (Karras et al., ICLR 2018) BigGAN (Brock et al., ICLR 2019) 1 3 5 7 2 4 6 8
  • 6. BigGAN (Brock et al., ICLR 2019) StyleGAN (Karras et al., CVPR 2019)
  • 7.
  • 8. 2010- : DeNA / 2011– : Mobage 2014- : DeNA Mobage : ( ) TokyoWebmining - - 2010 60 /Koichi Hamada (@hamadakoichi)
  • 9. /Koichi Hamada (@hamadakoichi) 78 : : 102*0DeNA AI : TZ ... ./ 0 KD SL KA N O N KD SL K N W
  • 10. 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.
  • 12.
  • 13.
  • 14. 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.
  • 15.
  • 16. BigGAN (Brock et al., ICLR 2019) StyleGAN (Karras et al., CVPR 2019)
  • 17.
  • 18.
  • 19.
  • 20. 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
  • 21. 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
  • 22.
  • 23.
  • 24. 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
  • 25. BigGAN (Brock et al., ICLR 2019) StyleGAN (Karras et al., CVPR 2019)
  • 26. BigGAN (Brock et al., ICLR 2019) StyleGAN (Karras et al., CVPR 2019)
  • 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 + Orthogonal Regularization + Truncation Trick + First Singular Value Clamp + Zero-centered Gradient Penalty
  • 29. + 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
  • 30. + 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
  • 31. + 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
  • 32. + 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
  • 33. + 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
  • 34. + 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
  • 35. Self-Attention Generative Adversarial Networks. Han Zhang, Ian Goodfellow, Dimitris Metaxas, Augustus Odena. arXiv: 1805.08318. In ICML 2019.
  • 36. Self-Attention Generative Adversarial Networks. Han Zhang, Ian Goodfellow, Dimitris Metaxas, Augustus Odena. arXiv: 1805.08318. In ICML 2019.
  • 37. + 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.
  • 38. Self-Attention Generative Adversarial Networks. Han Zhang, Ian Goodfellow, Dimitris Metaxas, Augustus Odena. arXiv: 1805.08318. In ICML 2019.
  • 39. + 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
  • 40. + 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.
  • 41. Large Scale GAN Training for High Fidelity Natural Image Synthesis. Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019.
  • 42. 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
  • 43. 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
  • 44. 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)
  • 45. (512x512) Large Scale GAN Training for High Fidelity Natural Image Synthesis. Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019.
  • 46. (512x512) Large Scale GAN Training for High Fidelity Natural Image Synthesis. Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019.
  • 47. (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.
  • 48. (512x512) Large Scale GAN Training for High Fidelity Natural Image Synthesis. Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019.
  • 49. 49 Large Scale GAN Training for High Fidelity Natural Image Synthesis. Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019.
  • 50. 50 Large Scale GAN Training for High Fidelity Natural Image Synthesis. Andrew Brock, Jeff Donahue, Karen Simonyan. arXiv:1809.11096. In ICLR 2019.
  • 51. 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]
  • 52. + 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
  • 53. 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.
  • 54. 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.
  • 55. 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.
  • 56. 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.
  • 57. 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.
  • 58. 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.
  • 59. 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.
  • 60. 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.
  • 61. 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.
  • 62. 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.
  • 63.
  • 64. 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
  • 65. Flat Metric Minimization with Applications in Generative Modeling Thomas Möllenhoff, Daniel Cremers. arXiv:1905.04730. In ICML 2019.
  • 66. 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
  • 67. 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
  • 68. 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
  • 69. 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
  • 70.
  • 71. 77 878 12 7 /.0 .1 1DeNA AI : O * . A A TL K S :A A :L K