InfoGAN : Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
0 likes310 views
The document discusses Infogan, a method for interpretable representation learning utilizing generative adversarial networks (GANs). It reviews basic GAN concepts, including mutual information and the variational approach, and presents experimental results utilizing datasets like MNIST and Fashion-MNIST. The summary highlights the need for new learning techniques to incorporate additional latent codes for improved generative outcomes.
]([log),(maxmin )(~)(~ zGDExDEGDV zpzxpx
DG zdata
−+=
Smart D
)))]((1[log()]([log )(~)(~ zGDExDE zpzxpx zdata
−+Real case
Fake case
1
)))]((1[log()]([log )(~)(~ zGDExDE zpzxpx zdata
−+
0
should be 0
should be 0
1
Log(x)
cf.
Stupid D
)))]((1[log()]([log )(~)(~ zGDExDE zpzxpx zdata
−+Real case
Fake case
0
)))]((1[log()]([log )(~)(~ zGDExDE zpzxpx zdata
−+
1
should be negative infinity
should be negative infinity
D perspective,
it should be maximum.](https://image.slidesharecdn.com/infogan-190408061341/85/InfoGAN-Interpretable-Representation-Learning-by-Information-Maximizing-Generative-Adversarial-Nets-6-320.jpg)
]([log),(maxmin )(~)(~ zGDExDEGDV zpzxpx
DG zdata
−+=
Generator
)))]((1[log()]([log )(~)(~ zGDExDE zpzxpx zdata
−+
1
should be negative infinity
1
Log(x)
cf.
G perspective,
it should be minimum.
Smart G
Stupid G )))]((1[log()]([log )(~)(~ zGDExDE zpzxpx zdata
−+
0
should be 0](https://image.slidesharecdn.com/infogan-190408061341/85/InfoGAN-Interpretable-Representation-Learning-by-Information-Maximizing-Generative-Adversarial-Nets-7-320.jpg)
![InfoGAN
2019-04-08
17
• Concept
GNoise
Latent code
0.001
0.008
1.000
0.007
…
0.005
? : 실제 latent code의 구조는 복잡하여
해석이 어려움(entangled).
Let's make the latent code simple.
The proper generation is difficult.
[0.001, 0.008, …, 005] [005]
Latent code
0.001
0.008
1.000
0.007
…
0.005
0
0
0
0
…
1
Z C
Z C : Condition
How about adding latent code?
Idea](https://image.slidesharecdn.com/infogan-190408061341/85/InfoGAN-Interpretable-Representation-Learning-by-Information-Maximizing-Generative-Adversarial-Nets-17-320.jpg)
![InfoGAN
2019-04-08
18
• Concept
G
Latent code
Z C
“뭐야? 그러면 C를 Z 옆에 바로
붙이면 되는 거야?”
[0.001, 0.008, …, 005 | 0, 0, … 1]
z c
[0.001, 0.008, …, 005 | 1, 0, … 0]
z c
[0.001, 0.008, …, 005 ]
z
[0.001, 0.008, …, 005 ]
z
Ignore the additional latent code c
Cost function을 수정하여 c의 영향을 만듦.),(maxmin GDV
DG
(Mutual Information)](https://image.slidesharecdn.com/infogan-190408061341/85/InfoGAN-Interpretable-Representation-Learning-by-Information-Maximizing-Generative-Adversarial-Nets-18-320.jpg)
InfoGAN : Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
- 1. InfoGAN : Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets ISL Lab Seminar Hansol Kang : Mutual Information
- 3. I. Review Review Vanilla GAN, DCGAN
- 4. Review • Concept of GAN 2019-04-08 4 VsD GF1 F1 F1 F1 FakeR1
- 5. Review • Concept of GAN 2019-04-08 5 VsD G Fake?R1 @ F1
- 6. Review • Adversarial nets 2019-04-08 6 )))]((1[log()]([log),(maxmin )(~)(~ zGDExDEGDV zpzxpx DG zdata −+= Smart D )))]((1[log()]([log )(~)(~ zGDExDE zpzxpx zdata −+Real case Fake case 1 )))]((1[log()]([log )(~)(~ zGDExDE zpzxpx zdata −+ 0 should be 0 should be 0 1 Log(x) cf. Stupid D )))]((1[log()]([log )(~)(~ zGDExDE zpzxpx zdata −+Real case Fake case 0 )))]((1[log()]([log )(~)(~ zGDExDE zpzxpx zdata −+ 1 should be negative infinity should be negative infinity D perspective, it should be maximum.
- 7. Review • Adversarial nets 2019-04-08 7 )))]((1[log()]([log),(maxmin )(~)(~ zGDExDEGDV zpzxpx DG zdata −+= Generator )))]((1[log()]([log )(~)(~ zGDExDE zpzxpx zdata −+ 1 should be negative infinity 1 Log(x) cf. G perspective, it should be minimum. Smart G Stupid G )))]((1[log()]([log )(~)(~ zGDExDE zpzxpx zdata −+ 0 should be 0
- 8. Review 2019-04-08 8 • GAN 1) Global Optimality of datag pp = 2) Convergence of Algorithm D GVs x )(xpdata “Generative Adversarial Networks” Goal Method
- 9. Review 2019-04-08 9 • DCGAN : network D G “쟤들 뭐하냐?” “CNN이 MLP보다 훨씬 낫지롱” D “우리가 짱이야.” G Vanilla GAN DCGAN
- 10. Review 2019-04-08 10 • DCGAN : latent space 0 1 0.1 0.15 0.18 0.143 0.5 0.45 0.47 0.473 0.9 0.95 0.96 0.937 0.607±
- 11. II. InfoGAN InfoGAN Concept, Mutual Information, Variational method, Results
- 12. InfoGAN 2019-04-08 12 • Concept D GNoise Real(Kurt Cobain) Fake(Not Kurt Cobain) … Latent code Dataset
- 13. InfoGAN 2019-04-08 13 • Concept D GNoise Real(Kurt Cobain) Fake(Not Kurt Cobain) … Latent code Dataset 0 Simplify
- 14. InfoGAN 2019-04-08 14 • Concept D GNoise Real(Kurt Cobain) Fake(Not Kurt Cobain) … Latent code Dataset 0.5 Simplify
- 15. InfoGAN 2019-04-08 15 • Concept D GNoise Real(Kurt Cobain) Fake(Not Kurt Cobain) … Latent code Dataset 1 Simplify
- 16. InfoGAN 2019-04-08 16 • Concept D GNoise Real(Kurt Cobain) Fake(Not Kurt Cobain) … Latent code Dataset 0.001 0.008 1.000 0.007 … 0.005 But… ? : 실제 latent code의 구조는 복잡하여 해석이 어려움(entangled).
- 17. InfoGAN 2019-04-08 17 • Concept GNoise Latent code 0.001 0.008 1.000 0.007 … 0.005 ? : 실제 latent code의 구조는 복잡하여 해석이 어려움(entangled). Let's make the latent code simple. The proper generation is difficult. [0.001, 0.008, …, 005] [005] Latent code 0.001 0.008 1.000 0.007 … 0.005 0 0 0 0 … 1 Z C Z C : Condition How about adding latent code? Idea
- 18. InfoGAN 2019-04-08 18 • Concept G Latent code Z C “뭐야? 그러면 C를 Z 옆에 바로 붙이면 되는 거야?” [0.001, 0.008, …, 005 | 0, 0, … 1] z c [0.001, 0.008, …, 005 | 1, 0, … 0] z c [0.001, 0.008, …, 005 ] z [0.001, 0.008, …, 005 ] z Ignore the additional latent code c Cost function을 수정하여 c의 영향을 만듦.),(maxmin GDV DG (Mutual Information)
- 19. InfoGAN 2019-04-08 19 • Mutual Information )|()();( YXHXHYXI −= )()( )( );( YPXP YXP YXI = ISL Browser https://isl.cnu.ac.kr Supervised Learning 검색 결과 약 107,000,000개 Unsupervised Learning 검색 결과 약 13,400,000개 Clustering 검색 결과 약 40,900,000개 Supervised Learning Clustering 검색 결과 약 25,300,000개 Unsupervised Learning Clustering 검색 결과 약 7,770,000개 Deep Learning 검색 결과 약 1,380,000,000개 07754.0)( =SLP 00971.0)( =ULP 02964.0)( =CP 0.01833)( =CSLP 0.00563)( =CULP 97551.7 02964.007754.0 01833.0 )()( )( = = CPSLP CSLP 56190.19 02964.000971.0 00563.0 )()( )( = = CPULP CULP “두 사건 사이의 연관성 파악”
- 20. InfoGAN 2019-04-08 20 • Mutual Information : Generator와 c 사이의 연관성을 cost로 정의( )),(;),(),(maxmin czGcIGDVGDVI DG −= Maximize Hard to maximize directly as it requires access to the posterior )|( xcP ( ) ( ))(||)|()(|log),,( )|( zpxzqKLzgxExL xzq +−= ),,(min xL Reconstruction Error Regularization VAE Seminar (18.07.23)
- 21. InfoGAN 2019-04-08 21 • Variational method )|( xcP )|( xcQ Intractable(Very complicated) Tractable(e.g Gaussian) ( )),(;),(),(maxmin czGcIGDVGDVI DG −= ( ) ( )),(|)(),(; czGcHcHczGcI −= ( ) ( ) ( ) ),(),(|ln),(,),(| czdcdGczGcPczGcPczGcH −= ( ) dydxxyPxyPxyH )|(ln),(| −= dydxxyPxPxyP )|(ln)()|(−= c.f Conditional Entropy Product rule ( ) ( ) ( ) ),(),(|ln),(),(| czdcdGczGcPczGPczGcP−= ( ) ( ) ( ) ),(),(|ln),(|),( czdcdGczGcPczGcPczGP−= ( ) ),()|'(ln),( )|(~' czdGxcPEczGP xcPc−= )|'(ln)|(~'),(~ xcPEE xcPcczGx−= ( ) )|'(ln)(),(; )|(~'),(~ xcPEEcHczGcI xcPcczGx+= (1) (2)
- 22. InfoGAN 2019-04-08 22 • Variational method ( ) )|'(ln)(),(; )|(~'),(~ xcPEEcHczGcI xcPcczGx+= (2) ( ) = )'( )|'( ln)|'(||)|'( )|(~' xcQ xcP ExcQxcPD xcPcKL )|'(ln)'(ln )|(~')|(~' xcQExcPE xcPcxcPc −= ( ) )|'(ln)|'(||)|'()'(ln )|(~')|(~' xcQExcQxcPDxcPE xcPcKLxcPc += ( ) ( ) )|'(ln)|'(||)|'()(),(; )|(~'),(~ xcQExcQxcPDEcHczGcI xcPcKLczGx ++= (3) 0 ( ) = )( )( ln|| ~ xQ xP EQPD PxKL c.f KL Divergence ( ) 0|| =QPDKL : 동일 분포 )|'(ln)( )|(~'),(~ xcQEEcH xcPcczGx+ (4) )|( xcQ Tractable distribution
- 23. InfoGAN 2019-04-08 23 • Variational method ( ) )|'(ln)(),(; )|(~'),(~ xcQEEcHczGcI xcPcczGx+ (4) )|( xcP : 여전히 남음. ),'(),( |~',|~,~|~,~ yxfEyxfE yXxxYyXxxYyXx = Lemma )|(ln)(),( ),(~),(~ xcQEcHQGL czGxcPcI += )|'(ln)( )|(~'),(~ xcQEEcH xcPcczGx+= ),(),(),,(maxmin QGLGDVQGDV IInfoGAN DG −= (5)
- 29. Experiment • Results#1 MNIST (continuous) 2019-04-08 29 Epoch 1 Epoch 5 Epoch 10 Epoch 30 Epoch 50 GIF
- 30. Experiment • Results#1 MNIST (categorical) 2019-04-08 30 Epoch 1 Epoch 5 Epoch 10 Epoch 30 Epoch 50 GIF
- 31. Experiment • Results#2 Fashion MNIST (continuous) 2019-04-08 31 Epoch 1 Epoch 5 Epoch 10 Epoch 30 Epoch 50 GIF
- 32. Experiment • Results#2 Fashion MNIST (categorical) 2019-04-08 32 Epoch 1 Epoch 5 Epoch 10 Epoch 30 Epoch 50 GIF
- 33. Experiment • Results#3 LSUN (continuous) 2019-04-08 33 Epoch 1 Epoch 2 Epoch 3 Epoch 4 Epoch 5
- 34. Experiment • Results#3 LSUN (categorical) 2019-04-08 34 Epoch 1 Epoch 2 Epoch 3 Epoch 4 Epoch 5
- 35. Experiment • Results#3 LSUN (categorical, ep 5) 2019-04-08 35
- 36. IV. Summary Summary Summary, Future Work
- 37. Summary 2019-04-08 37 • Latent code에 추가적인 code를 할당하여 학습함. • 기존의 GAN 학습법으로는 추가된 code를 무시하기에 새로운 학습 방법이 필요함. • Mutual information을 통해 추가된 code와 네트워크 간의 상호 연관성을 부여함. • 주어진 code는 그 형태에 따라 categorical(discrete)or continuous로 구분되며, 실제 실험을 통 해 적절히 학습되는 것을 확인함. (cGAN과 비슷한 접근법)
- 38. Future work 2019-04-08 38 GAN Research Vanilla GAN DCGAN InfoGAN LS GAN BEGAN Pix2Pix Cycle GAN Novel GAN(about depth) Tools Document Programming PyTorch Python executable & UI I Know What You Did Last Faculty C++ Coding Standard Mathematical theory LSM applications Other Research Level Processor Ice Propagation
- 39. &