SlideShare ist ein Scribd-Unternehmen logo
1 von 26
Downloaden Sie, um offline zu lesen
AmbientGAN: Generative Models
From Lossy Measurements
ICLR 2018 Reading Group
Jaejun Yoo
Clova ML / NAVER
12th Mar, 2018
by A. Bora, E. Price, A.G. Dimakis
Motivation
“How can we train our generative models with
partial, noisy observations”
In many settings, it is expensive or even impossible to obtain fully-observed
samples, but economical to obtain partial, noisy samples.
Why do we care?
This paper proposes
• AmbientGAN: train the discriminator not on the raw data
domain but on the measurement domain.
• Propose the way to train the generative model with a noisy,
corrupted, or missing data.
• Prove that it is theoretically possible to recover the original
true data distribution even though the measurement process
is not invertible.
This paper proposes (preview)
This paper proposes (preview)
Model Architecture (preview)
Generative Adversarial Networsks
Diagram of
Standard GAN
Gaussian noise
as an input for G
z
G
D
x
Real or Fake?
지폐위조범
경찰
Limitation of GAN
• Training Stability
• Forgetting problem
• Requires Good (or fully observed) Training Samples!!
• To train the generator, we need a lot of good images
• In many settings, it is expensive or even impossible to obtain fully-observed samples,
but economical to obtain partial, noisy samples.
Limitation of GAN
• Training Stability
• Forgetting problem
• Requires Good (or fully observed) Training Samples!!
• To train the generator, we need a lot of good images
• In many settings, it is expensive or even impossible to obtain fully-observed samples,
but economical to obtain partial, noisy samples.
Compressed sensing attempts to address this problem
by exploiting the models of the data structure; sparsity.
Bora et al. ICML 2017, “Compressed Sensing using Generative Models”
https://www.cs.utexas.edu/~ashishb/assets/csgm/slides_google_ashish.pdf
Bora et al. 2017, “Compressed Sensing using Generative Models”
Compressed Sensing Paper in “a” Slide
Chicken and Egg problem
• Okay, they showed it is possible to solve the problem with a small number of (good)
measurements by using Generative Models!
• But, what if it is even not possible to gather the good data in the first place?
• How can we collect enough data to train a generative model to start with?
Model Architecture
Measurements? (in compressed sensing)
Measurements? (in signal processing)
Measurements? (in this paper)
• Block-Pixels: with 𝑝, make image pixel 0
• Conv + Noise: Gaussian kernel blur + add random Gaussian noise
• Block-Patch: make 𝑘 × 𝑘 patch 0
• Keep-Patch: make 0 except 𝑘 × 𝑘 patch
• Extract-Patch: use 𝑘 × 𝑘 patch as input
• Pad-Rotate-Project: zero padding + rotate + vertical 1D projection
• Pad-Rotate-Project-𝛉: Pad-Rotate-Project and include θ as an
additional information for the measurement
• Gaussian-Projection: Sample a random Gaussian vector and project
Dataset and Model Architectures
Baselines
Experimental Results
Experimental Results
Experimental Results
Experimental Results
Experimental Results
Experimental Results
Theory
In Conclusion
• Using AmbientGAN, it is possible to train the generator
without the fully-observed data
• In theory, it is possible to find the true distribution by training
the generator when the measurement process is invertible and
differentiable
• Empirically, it is possible to recover the good data distribution
even though the measurement process is not clearly known.
Possible Applications?
• OCR
• Gayoung’s Webtoon data
• Adding Reconstruction loss and Cyclic loss
• Learnable 𝒇 𝜽
−𝟏
⋅ by FC
• etc.

Weitere ähnliche Inhalte

Was ist angesagt?

Deep Belief nets
Deep Belief netsDeep Belief nets
Deep Belief nets
butest
 

Was ist angesagt? (20)

Explaining the idea behind automatic relevance determination and bayesian int...
Explaining the idea behind automatic relevance determination and bayesian int...Explaining the idea behind automatic relevance determination and bayesian int...
Explaining the idea behind automatic relevance determination and bayesian int...
 
MobileNet - PR044
MobileNet - PR044MobileNet - PR044
MobileNet - PR044
 
Structure from motion
Structure from motionStructure from motion
Structure from motion
 
Image pyramid
Image pyramidImage pyramid
Image pyramid
 
You Only Look Once: Unified, Real-Time Object Detection
You Only Look Once: Unified, Real-Time Object DetectionYou Only Look Once: Unified, Real-Time Object Detection
You Only Look Once: Unified, Real-Time Object Detection
 
Diffusion models beat gans on image synthesis
Diffusion models beat gans on image synthesisDiffusion models beat gans on image synthesis
Diffusion models beat gans on image synthesis
 
Unified Approach to Interpret Machine Learning Model: SHAP + LIME
Unified Approach to Interpret Machine Learning Model: SHAP + LIMEUnified Approach to Interpret Machine Learning Model: SHAP + LIME
Unified Approach to Interpret Machine Learning Model: SHAP + LIME
 
Explicit Density Models
Explicit Density ModelsExplicit Density Models
Explicit Density Models
 
Introduction to Diffusion Models
Introduction to Diffusion ModelsIntroduction to Diffusion Models
Introduction to Diffusion Models
 
Shap
ShapShap
Shap
 
Introduction to OpenCV
Introduction to OpenCVIntroduction to OpenCV
Introduction to OpenCV
 
Generative Adversarial Networks GAN - Xavier Giro - UPC TelecomBCN Barcelona ...
Generative Adversarial Networks GAN - Xavier Giro - UPC TelecomBCN Barcelona ...Generative Adversarial Networks GAN - Xavier Giro - UPC TelecomBCN Barcelona ...
Generative Adversarial Networks GAN - Xavier Giro - UPC TelecomBCN Barcelona ...
 
A Deep Journey into Super-resolution
A Deep Journey into Super-resolutionA Deep Journey into Super-resolution
A Deep Journey into Super-resolution
 
C2 ae open set recognition
C2 ae open set recognitionC2 ae open set recognition
C2 ae open set recognition
 
Variational Autoencoder
Variational AutoencoderVariational Autoencoder
Variational Autoencoder
 
Fashion-Gen: The Generative Fashion Dataset and Challenge by Negar Rostamzade...
Fashion-Gen: The Generative Fashion Dataset and Challenge by Negar Rostamzade...Fashion-Gen: The Generative Fashion Dataset and Challenge by Negar Rostamzade...
Fashion-Gen: The Generative Fashion Dataset and Challenge by Negar Rostamzade...
 
Cheat sheets for AI
Cheat sheets for AICheat sheets for AI
Cheat sheets for AI
 
Deep Belief nets
Deep Belief netsDeep Belief nets
Deep Belief nets
 
2018AOI論壇_深度學習於表面瑕疪檢測_元智大學蔡篤銘
2018AOI論壇_深度學習於表面瑕疪檢測_元智大學蔡篤銘2018AOI論壇_深度學習於表面瑕疪檢測_元智大學蔡篤銘
2018AOI論壇_深度學習於表面瑕疪檢測_元智大學蔡篤銘
 
Representation learning in limited-data settings
Representation learning in limited-data settingsRepresentation learning in limited-data settings
Representation learning in limited-data settings
 

Ähnlich wie Introduction to ambient GAN

Jakub Langr (University of Oxford) - Overview of Generative Adversarial Netwo...
Jakub Langr (University of Oxford) - Overview of Generative Adversarial Netwo...Jakub Langr (University of Oxford) - Overview of Generative Adversarial Netwo...
Jakub Langr (University of Oxford) - Overview of Generative Adversarial Netwo...
Codiax
 
Cross-domain complementary learning with synthetic data for multi-person part...
Cross-domain complementary learning with synthetic data for multi-person part...Cross-domain complementary learning with synthetic data for multi-person part...
Cross-domain complementary learning with synthetic data for multi-person part...
哲东 郑
 

Ähnlich wie Introduction to ambient GAN (20)

Data-driven hypothesis generation using deep neural nets
Data-driven hypothesis generation using deep neural netsData-driven hypothesis generation using deep neural nets
Data-driven hypothesis generation using deep neural nets
 
Generative Adversarial Networks and Their Applications in Medical Imaging
Generative Adversarial Networks  and Their Applications in Medical ImagingGenerative Adversarial Networks  and Their Applications in Medical Imaging
Generative Adversarial Networks and Their Applications in Medical Imaging
 
Machine learning in the life sciences with knime
Machine learning in the life sciences with knimeMachine learning in the life sciences with knime
Machine learning in the life sciences with knime
 
Variants of GANs - Jaejun Yoo
Variants of GANs - Jaejun YooVariants of GANs - Jaejun Yoo
Variants of GANs - Jaejun Yoo
 
Icml2017 overview
Icml2017 overviewIcml2017 overview
Icml2017 overview
 
Domain Transfer and Adaptation Survey
Domain Transfer and Adaptation SurveyDomain Transfer and Adaptation Survey
Domain Transfer and Adaptation Survey
 
Generative Adversarial Networks 2
Generative Adversarial Networks 2Generative Adversarial Networks 2
Generative Adversarial Networks 2
 
Lecture 1
Lecture 1Lecture 1
Lecture 1
 
lec1.ppt
lec1.pptlec1.ppt
lec1.ppt
 
Jakub Langr (University of Oxford) - Overview of Generative Adversarial Netwo...
Jakub Langr (University of Oxford) - Overview of Generative Adversarial Netwo...Jakub Langr (University of Oxford) - Overview of Generative Adversarial Netwo...
Jakub Langr (University of Oxford) - Overview of Generative Adversarial Netwo...
 
Cross-domain complementary learning with synthetic data for multi-person part...
Cross-domain complementary learning with synthetic data for multi-person part...Cross-domain complementary learning with synthetic data for multi-person part...
Cross-domain complementary learning with synthetic data for multi-person part...
 
Tutorial on Theory and Application of Generative Adversarial Networks
Tutorial on Theory and Application of Generative Adversarial NetworksTutorial on Theory and Application of Generative Adversarial Networks
Tutorial on Theory and Application of Generative Adversarial Networks
 
To bag, or to boost? A question of balance
To bag, or to boost? A question of balanceTo bag, or to boost? A question of balance
To bag, or to boost? A question of balance
 
Reading group gan - 20170417
Reading group   gan - 20170417Reading group   gan - 20170417
Reading group gan - 20170417
 
2014 pycon-talk
2014 pycon-talk2014 pycon-talk
2014 pycon-talk
 
H2O with Erin LeDell at Portland R User Group
H2O with Erin LeDell at Portland R User GroupH2O with Erin LeDell at Portland R User Group
H2O with Erin LeDell at Portland R User Group
 
Technical computing in Julia
Technical computing in JuliaTechnical computing in Julia
Technical computing in Julia
 
in5490-classification (1).pptx
in5490-classification (1).pptxin5490-classification (1).pptx
in5490-classification (1).pptx
 
Narjess Afzaly: Model Your Problem with Graphs and Generate your objects
Narjess Afzaly: Model Your Problem with Graphs and Generate your objectsNarjess Afzaly: Model Your Problem with Graphs and Generate your objects
Narjess Afzaly: Model Your Problem with Graphs and Generate your objects
 
Hacking Predictive Modeling - RoadSec 2018
Hacking Predictive Modeling - RoadSec 2018Hacking Predictive Modeling - RoadSec 2018
Hacking Predictive Modeling - RoadSec 2018
 

Mehr von JaeJun Yoo

Super resolution in deep learning era - Jaejun Yoo
Super resolution in deep learning era - Jaejun YooSuper resolution in deep learning era - Jaejun Yoo
Super resolution in deep learning era - Jaejun Yoo
JaeJun Yoo
 

Mehr von JaeJun Yoo (13)

[PR12] Generative Models as Distributions of Functions
[PR12] Generative Models as Distributions of Functions[PR12] Generative Models as Distributions of Functions
[PR12] Generative Models as Distributions of Functions
 
[CVPR2020] Simple but effective image enhancement techniques
[CVPR2020] Simple but effective image enhancement techniques[CVPR2020] Simple but effective image enhancement techniques
[CVPR2020] Simple but effective image enhancement techniques
 
Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Anal...
Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Anal...Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Anal...
Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Anal...
 
Super resolution in deep learning era - Jaejun Yoo
Super resolution in deep learning era - Jaejun YooSuper resolution in deep learning era - Jaejun Yoo
Super resolution in deep learning era - Jaejun Yoo
 
A beginner's guide to Style Transfer and recent trends
A beginner's guide to Style Transfer and recent trendsA beginner's guide to Style Transfer and recent trends
A beginner's guide to Style Transfer and recent trends
 
[PR12] Spectral Normalization for Generative Adversarial Networks
[PR12] Spectral Normalization for Generative Adversarial Networks[PR12] Spectral Normalization for Generative Adversarial Networks
[PR12] Spectral Normalization for Generative Adversarial Networks
 
[PR12] categorical reparameterization with gumbel softmax
[PR12] categorical reparameterization with gumbel softmax[PR12] categorical reparameterization with gumbel softmax
[PR12] categorical reparameterization with gumbel softmax
 
[PR12] understanding deep learning requires rethinking generalization
[PR12] understanding deep learning requires rethinking generalization[PR12] understanding deep learning requires rethinking generalization
[PR12] understanding deep learning requires rethinking generalization
 
[PR12] Capsule Networks - Jaejun Yoo
[PR12] Capsule Networks - Jaejun Yoo[PR12] Capsule Networks - Jaejun Yoo
[PR12] Capsule Networks - Jaejun Yoo
 
[PR12] Inception and Xception - Jaejun Yoo
[PR12] Inception and Xception - Jaejun Yoo[PR12] Inception and Xception - Jaejun Yoo
[PR12] Inception and Xception - Jaejun Yoo
 
[PR12] PixelRNN- Jaejun Yoo
[PR12] PixelRNN- Jaejun Yoo[PR12] PixelRNN- Jaejun Yoo
[PR12] PixelRNN- Jaejun Yoo
 
[Pr12] dann jaejun yoo
[Pr12] dann   jaejun yoo[Pr12] dann   jaejun yoo
[Pr12] dann jaejun yoo
 
[PR12] intro. to gans jaejun yoo
[PR12] intro. to gans   jaejun yoo[PR12] intro. to gans   jaejun yoo
[PR12] intro. to gans jaejun yoo
 

Kürzlich hochgeladen

Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 bAsymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Sérgio Sacani
 
CYTOGENETIC MAP................ ppt.pptx
CYTOGENETIC MAP................ ppt.pptxCYTOGENETIC MAP................ ppt.pptx
CYTOGENETIC MAP................ ppt.pptx
Silpa
 
LUNULARIA -features, morphology, anatomy ,reproduction etc.
LUNULARIA -features, morphology, anatomy ,reproduction etc.LUNULARIA -features, morphology, anatomy ,reproduction etc.
LUNULARIA -features, morphology, anatomy ,reproduction etc.
Silpa
 
Human genetics..........................pptx
Human genetics..........................pptxHuman genetics..........................pptx
Human genetics..........................pptx
Silpa
 
Reboulia: features, anatomy, morphology etc.
Reboulia: features, anatomy, morphology etc.Reboulia: features, anatomy, morphology etc.
Reboulia: features, anatomy, morphology etc.
Silpa
 
Phenolics: types, biosynthesis and functions.
Phenolics: types, biosynthesis and functions.Phenolics: types, biosynthesis and functions.
Phenolics: types, biosynthesis and functions.
Silpa
 
Cyathodium bryophyte: morphology, anatomy, reproduction etc.
Cyathodium bryophyte: morphology, anatomy, reproduction etc.Cyathodium bryophyte: morphology, anatomy, reproduction etc.
Cyathodium bryophyte: morphology, anatomy, reproduction etc.
Silpa
 
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
?#DUbAI#??##{{(☎️+971_581248768%)**%*]'#abortion pills for sale in dubai@
 
Module for Grade 9 for Asynchronous/Distance learning
Module for Grade 9 for Asynchronous/Distance learningModule for Grade 9 for Asynchronous/Distance learning
Module for Grade 9 for Asynchronous/Distance learning
levieagacer
 

Kürzlich hochgeladen (20)

Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 bAsymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
 
CYTOGENETIC MAP................ ppt.pptx
CYTOGENETIC MAP................ ppt.pptxCYTOGENETIC MAP................ ppt.pptx
CYTOGENETIC MAP................ ppt.pptx
 
LUNULARIA -features, morphology, anatomy ,reproduction etc.
LUNULARIA -features, morphology, anatomy ,reproduction etc.LUNULARIA -features, morphology, anatomy ,reproduction etc.
LUNULARIA -features, morphology, anatomy ,reproduction etc.
 
TransientOffsetin14CAftertheCarringtonEventRecordedbyPolarTreeRings
TransientOffsetin14CAftertheCarringtonEventRecordedbyPolarTreeRingsTransientOffsetin14CAftertheCarringtonEventRecordedbyPolarTreeRings
TransientOffsetin14CAftertheCarringtonEventRecordedbyPolarTreeRings
 
Thyroid Physiology_Dr.E. Muralinath_ Associate Professor
Thyroid Physiology_Dr.E. Muralinath_ Associate ProfessorThyroid Physiology_Dr.E. Muralinath_ Associate Professor
Thyroid Physiology_Dr.E. Muralinath_ Associate Professor
 
Human genetics..........................pptx
Human genetics..........................pptxHuman genetics..........................pptx
Human genetics..........................pptx
 
Reboulia: features, anatomy, morphology etc.
Reboulia: features, anatomy, morphology etc.Reboulia: features, anatomy, morphology etc.
Reboulia: features, anatomy, morphology etc.
 
Phenolics: types, biosynthesis and functions.
Phenolics: types, biosynthesis and functions.Phenolics: types, biosynthesis and functions.
Phenolics: types, biosynthesis and functions.
 
FAIRSpectra - Enabling the FAIRification of Analytical Science
FAIRSpectra - Enabling the FAIRification of Analytical ScienceFAIRSpectra - Enabling the FAIRification of Analytical Science
FAIRSpectra - Enabling the FAIRification of Analytical Science
 
Cyathodium bryophyte: morphology, anatomy, reproduction etc.
Cyathodium bryophyte: morphology, anatomy, reproduction etc.Cyathodium bryophyte: morphology, anatomy, reproduction etc.
Cyathodium bryophyte: morphology, anatomy, reproduction etc.
 
GBSN - Microbiology (Unit 3)Defense Mechanism of the body
GBSN - Microbiology (Unit 3)Defense Mechanism of the body GBSN - Microbiology (Unit 3)Defense Mechanism of the body
GBSN - Microbiology (Unit 3)Defense Mechanism of the body
 
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
 
Molecular markers- RFLP, RAPD, AFLP, SNP etc.
Molecular markers- RFLP, RAPD, AFLP, SNP etc.Molecular markers- RFLP, RAPD, AFLP, SNP etc.
Molecular markers- RFLP, RAPD, AFLP, SNP etc.
 
Atp synthase , Atp synthase complex 1 to 4.
Atp synthase , Atp synthase complex 1 to 4.Atp synthase , Atp synthase complex 1 to 4.
Atp synthase , Atp synthase complex 1 to 4.
 
CURRENT SCENARIO OF POULTRY PRODUCTION IN INDIA
CURRENT SCENARIO OF POULTRY PRODUCTION IN INDIACURRENT SCENARIO OF POULTRY PRODUCTION IN INDIA
CURRENT SCENARIO OF POULTRY PRODUCTION IN INDIA
 
Use of mutants in understanding seedling development.pptx
Use of mutants in understanding seedling development.pptxUse of mutants in understanding seedling development.pptx
Use of mutants in understanding seedling development.pptx
 
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
 
Selaginella: features, morphology ,anatomy and reproduction.
Selaginella: features, morphology ,anatomy and reproduction.Selaginella: features, morphology ,anatomy and reproduction.
Selaginella: features, morphology ,anatomy and reproduction.
 
Gwalior ❤CALL GIRL 84099*07087 ❤CALL GIRLS IN Gwalior ESCORT SERVICE❤CALL GIRL
Gwalior ❤CALL GIRL 84099*07087 ❤CALL GIRLS IN Gwalior ESCORT SERVICE❤CALL GIRLGwalior ❤CALL GIRL 84099*07087 ❤CALL GIRLS IN Gwalior ESCORT SERVICE❤CALL GIRL
Gwalior ❤CALL GIRL 84099*07087 ❤CALL GIRLS IN Gwalior ESCORT SERVICE❤CALL GIRL
 
Module for Grade 9 for Asynchronous/Distance learning
Module for Grade 9 for Asynchronous/Distance learningModule for Grade 9 for Asynchronous/Distance learning
Module for Grade 9 for Asynchronous/Distance learning
 

Introduction to ambient GAN

  • 1. AmbientGAN: Generative Models From Lossy Measurements ICLR 2018 Reading Group Jaejun Yoo Clova ML / NAVER 12th Mar, 2018 by A. Bora, E. Price, A.G. Dimakis
  • 2. Motivation “How can we train our generative models with partial, noisy observations” In many settings, it is expensive or even impossible to obtain fully-observed samples, but economical to obtain partial, noisy samples. Why do we care?
  • 3. This paper proposes • AmbientGAN: train the discriminator not on the raw data domain but on the measurement domain. • Propose the way to train the generative model with a noisy, corrupted, or missing data. • Prove that it is theoretically possible to recover the original true data distribution even though the measurement process is not invertible.
  • 7. Generative Adversarial Networsks Diagram of Standard GAN Gaussian noise as an input for G z G D x Real or Fake? 지폐위조범 경찰
  • 8. Limitation of GAN • Training Stability • Forgetting problem • Requires Good (or fully observed) Training Samples!! • To train the generator, we need a lot of good images • In many settings, it is expensive or even impossible to obtain fully-observed samples, but economical to obtain partial, noisy samples.
  • 9. Limitation of GAN • Training Stability • Forgetting problem • Requires Good (or fully observed) Training Samples!! • To train the generator, we need a lot of good images • In many settings, it is expensive or even impossible to obtain fully-observed samples, but economical to obtain partial, noisy samples. Compressed sensing attempts to address this problem by exploiting the models of the data structure; sparsity. Bora et al. ICML 2017, “Compressed Sensing using Generative Models”
  • 10. https://www.cs.utexas.edu/~ashishb/assets/csgm/slides_google_ashish.pdf Bora et al. 2017, “Compressed Sensing using Generative Models” Compressed Sensing Paper in “a” Slide
  • 11. Chicken and Egg problem • Okay, they showed it is possible to solve the problem with a small number of (good) measurements by using Generative Models! • But, what if it is even not possible to gather the good data in the first place? • How can we collect enough data to train a generative model to start with?
  • 15. Measurements? (in this paper) • Block-Pixels: with 𝑝, make image pixel 0 • Conv + Noise: Gaussian kernel blur + add random Gaussian noise • Block-Patch: make 𝑘 × 𝑘 patch 0 • Keep-Patch: make 0 except 𝑘 × 𝑘 patch • Extract-Patch: use 𝑘 × 𝑘 patch as input • Pad-Rotate-Project: zero padding + rotate + vertical 1D projection • Pad-Rotate-Project-𝛉: Pad-Rotate-Project and include θ as an additional information for the measurement • Gaussian-Projection: Sample a random Gaussian vector and project
  • 16. Dataset and Model Architectures
  • 25. In Conclusion • Using AmbientGAN, it is possible to train the generator without the fully-observed data • In theory, it is possible to find the true distribution by training the generator when the measurement process is invertible and differentiable • Empirically, it is possible to recover the good data distribution even though the measurement process is not clearly known.
  • 26. Possible Applications? • OCR • Gayoung’s Webtoon data • Adding Reconstruction loss and Cyclic loss • Learnable 𝒇 𝜽 −𝟏 ⋅ by FC • etc.