SlideShare a Scribd company logo
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.

More Related Content

What's hot

Literature Review on Single Image Super Resolution
Literature Review on Single Image Super ResolutionLiterature Review on Single Image Super Resolution
Literature Review on Single Image Super Resolution
ijtsrd
 
CIFAR-10
CIFAR-10CIFAR-10
CIFAR-10
satyam_madala
 
InfoGAN: Interpretable Representation Learning by Information Maximizing Gene...
InfoGAN: Interpretable Representation Learning by Information Maximizing Gene...InfoGAN: Interpretable Representation Learning by Information Maximizing Gene...
InfoGAN: Interpretable Representation Learning by Information Maximizing Gene...
홍배 김
 
Paper Summary of Beta-VAE: Learning Basic Visual Concepts with a Constrained ...
Paper Summary of Beta-VAE: Learning Basic Visual Concepts with a Constrained ...Paper Summary of Beta-VAE: Learning Basic Visual Concepts with a Constrained ...
Paper Summary of Beta-VAE: Learning Basic Visual Concepts with a Constrained ...
준식 최
 
Introduction to Convolutional Neural Networks
Introduction to Convolutional Neural NetworksIntroduction to Convolutional Neural Networks
Introduction to Convolutional Neural Networks
Hannes Hapke
 
What Is A Neural Network? | How Deep Neural Networks Work | Neural Network Tu...
What Is A Neural Network? | How Deep Neural Networks Work | Neural Network Tu...What Is A Neural Network? | How Deep Neural Networks Work | Neural Network Tu...
What Is A Neural Network? | How Deep Neural Networks Work | Neural Network Tu...
Simplilearn
 
[Paper Review] GAIN: Missing Data Imputation using Generative Adversarial Net...
[Paper Review] GAIN: Missing Data Imputation using Generative Adversarial Net...[Paper Review] GAIN: Missing Data Imputation using Generative Adversarial Net...
[Paper Review] GAIN: Missing Data Imputation using Generative Adversarial Net...
Jihoo Kim
 
Single Image Super Resolution Overview
Single Image Super Resolution OverviewSingle Image Super Resolution Overview
Single Image Super Resolution Overview
LEE HOSEONG
 
Pixel RNN to Pixel CNN++
Pixel RNN to Pixel CNN++Pixel RNN to Pixel CNN++
Pixel RNN to Pixel CNN++
Dongheon Lee
 
CNN Machine learning DeepLearning
CNN Machine learning DeepLearningCNN Machine learning DeepLearning
CNN Machine learning DeepLearning
Abhishek Sharma
 
Variational Autoencoder Tutorial
Variational Autoencoder Tutorial Variational Autoencoder Tutorial
Variational Autoencoder Tutorial
Hojin Yang
 
Variational Autoencoder
Variational AutoencoderVariational Autoencoder
Variational Autoencoder
Mark Chang
 
Backpropagation in Convolutional Neural Network
Backpropagation in Convolutional Neural NetworkBackpropagation in Convolutional Neural Network
Backpropagation in Convolutional Neural Network
Hiroshi Kuwajima
 
Distilling the knowledge in a neural network
Distilling the knowledge in a neural networkDistilling the knowledge in a neural network
Distilling the knowledge in a neural network
KyeongUkJang
 
LDM_ImageSythesis.pptx
LDM_ImageSythesis.pptxLDM_ImageSythesis.pptx
LDM_ImageSythesis.pptx
AkankshaRawat53
 
PR 127: FaceNet
PR 127: FaceNetPR 127: FaceNet
PR 127: FaceNet
Taeoh Kim
 
Finding connections among images using CycleGAN
Finding connections among images using CycleGANFinding connections among images using CycleGAN
Finding connections among images using CycleGAN
NAVER Engineering
 
Computer Vision.pptx
Computer Vision.pptxComputer Vision.pptx
Computer Vision.pptx
GDSCIIITDHARWAD
 
Chapter 14 AutoEncoder
Chapter 14 AutoEncoderChapter 14 AutoEncoder
Chapter 14 AutoEncoder
KyeongUkJang
 
Deep learning crash course
Deep learning crash courseDeep learning crash course
Deep learning crash course
Vishwas N
 

What's hot (20)

Literature Review on Single Image Super Resolution
Literature Review on Single Image Super ResolutionLiterature Review on Single Image Super Resolution
Literature Review on Single Image Super Resolution
 
CIFAR-10
CIFAR-10CIFAR-10
CIFAR-10
 
InfoGAN: Interpretable Representation Learning by Information Maximizing Gene...
InfoGAN: Interpretable Representation Learning by Information Maximizing Gene...InfoGAN: Interpretable Representation Learning by Information Maximizing Gene...
InfoGAN: Interpretable Representation Learning by Information Maximizing Gene...
 
Paper Summary of Beta-VAE: Learning Basic Visual Concepts with a Constrained ...
Paper Summary of Beta-VAE: Learning Basic Visual Concepts with a Constrained ...Paper Summary of Beta-VAE: Learning Basic Visual Concepts with a Constrained ...
Paper Summary of Beta-VAE: Learning Basic Visual Concepts with a Constrained ...
 
Introduction to Convolutional Neural Networks
Introduction to Convolutional Neural NetworksIntroduction to Convolutional Neural Networks
Introduction to Convolutional Neural Networks
 
What Is A Neural Network? | How Deep Neural Networks Work | Neural Network Tu...
What Is A Neural Network? | How Deep Neural Networks Work | Neural Network Tu...What Is A Neural Network? | How Deep Neural Networks Work | Neural Network Tu...
What Is A Neural Network? | How Deep Neural Networks Work | Neural Network Tu...
 
[Paper Review] GAIN: Missing Data Imputation using Generative Adversarial Net...
[Paper Review] GAIN: Missing Data Imputation using Generative Adversarial Net...[Paper Review] GAIN: Missing Data Imputation using Generative Adversarial Net...
[Paper Review] GAIN: Missing Data Imputation using Generative Adversarial Net...
 
Single Image Super Resolution Overview
Single Image Super Resolution OverviewSingle Image Super Resolution Overview
Single Image Super Resolution Overview
 
Pixel RNN to Pixel CNN++
Pixel RNN to Pixel CNN++Pixel RNN to Pixel CNN++
Pixel RNN to Pixel CNN++
 
CNN Machine learning DeepLearning
CNN Machine learning DeepLearningCNN Machine learning DeepLearning
CNN Machine learning DeepLearning
 
Variational Autoencoder Tutorial
Variational Autoencoder Tutorial Variational Autoencoder Tutorial
Variational Autoencoder Tutorial
 
Variational Autoencoder
Variational AutoencoderVariational Autoencoder
Variational Autoencoder
 
Backpropagation in Convolutional Neural Network
Backpropagation in Convolutional Neural NetworkBackpropagation in Convolutional Neural Network
Backpropagation in Convolutional Neural Network
 
Distilling the knowledge in a neural network
Distilling the knowledge in a neural networkDistilling the knowledge in a neural network
Distilling the knowledge in a neural network
 
LDM_ImageSythesis.pptx
LDM_ImageSythesis.pptxLDM_ImageSythesis.pptx
LDM_ImageSythesis.pptx
 
PR 127: FaceNet
PR 127: FaceNetPR 127: FaceNet
PR 127: FaceNet
 
Finding connections among images using CycleGAN
Finding connections among images using CycleGANFinding connections among images using CycleGAN
Finding connections among images using CycleGAN
 
Computer Vision.pptx
Computer Vision.pptxComputer Vision.pptx
Computer Vision.pptx
 
Chapter 14 AutoEncoder
Chapter 14 AutoEncoderChapter 14 AutoEncoder
Chapter 14 AutoEncoder
 
Deep learning crash course
Deep learning crash courseDeep learning crash course
Deep learning crash course
 

Similar to Introduction to ambient GAN

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
Balázs Kégl
 
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
Sanghoon Hong
 
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
Greg Landrum
 
Variants of GANs - Jaejun Yoo
Variants of GANs - Jaejun YooVariants of GANs - Jaejun Yoo
Variants of GANs - Jaejun Yoo
JaeJun Yoo
 
Icml2017 overview
Icml2017 overviewIcml2017 overview
Icml2017 overview
Tatsuya Shirakawa
 
Domain Transfer and Adaptation Survey
Domain Transfer and Adaptation SurveyDomain Transfer and Adaptation Survey
Domain Transfer and Adaptation Survey
Sangwoo Mo
 
Generative Adversarial Networks 2
Generative Adversarial Networks 2Generative Adversarial Networks 2
Generative Adversarial Networks 2
Alireza Shafaei
 
lec1.ppt
lec1.pptlec1.ppt
lec1.ppt
SVasuKrishna1
 
Lecture 1
Lecture 1Lecture 1
Lecture 1
Aun Akbar
 
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
 
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
MLReview
 
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
Alex Henderson
 
Reading group gan - 20170417
Reading group   gan - 20170417Reading group   gan - 20170417
Reading group gan - 20170417
Shuai Zhang
 
2014 pycon-talk
2014 pycon-talk2014 pycon-talk
2014 pycon-talk
c.titus.brown
 
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
Sri Ambati
 
Technical computing in Julia
Technical computing in JuliaTechnical computing in Julia
Technical computing in Julia
Jiahao Chen
 
in5490-classification (1).pptx
in5490-classification (1).pptxin5490-classification (1).pptx
in5490-classification (1).pptx
MonicaTimber
 
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
knowdiff
 
Hacking Predictive Modeling - RoadSec 2018
Hacking Predictive Modeling - RoadSec 2018Hacking Predictive Modeling - RoadSec 2018
Hacking Predictive Modeling - RoadSec 2018
HJ van Veen
 

Similar to 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
 
lec1.ppt
lec1.pptlec1.ppt
lec1.ppt
 
Lecture 1
Lecture 1Lecture 1
Lecture 1
 
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
 

More from JaeJun Yoo

[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
JaeJun Yoo
 
[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
JaeJun Yoo
 
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...
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
 
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
JaeJun Yoo
 
[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
JaeJun Yoo
 
[PR12] categorical reparameterization with gumbel softmax
[PR12] categorical reparameterization with gumbel softmax[PR12] categorical reparameterization with gumbel softmax
[PR12] categorical reparameterization with gumbel softmax
JaeJun Yoo
 
[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
JaeJun Yoo
 
[PR12] Capsule Networks - Jaejun Yoo
[PR12] Capsule Networks - Jaejun Yoo[PR12] Capsule Networks - Jaejun Yoo
[PR12] Capsule Networks - Jaejun Yoo
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
JaeJun Yoo
 
[PR12] PixelRNN- Jaejun Yoo
[PR12] PixelRNN- Jaejun Yoo[PR12] PixelRNN- Jaejun Yoo
[PR12] PixelRNN- Jaejun Yoo
JaeJun Yoo
 
[Pr12] dann jaejun yoo
[Pr12] dann   jaejun yoo[Pr12] dann   jaejun yoo
[Pr12] dann jaejun yoo
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
JaeJun Yoo
 

More from 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
 

Recently uploaded

Authoring a personal GPT for your research and practice: How we created the Q...
Authoring a personal GPT for your research and practice: How we created the Q...Authoring a personal GPT for your research and practice: How we created the Q...
Authoring a personal GPT for your research and practice: How we created the Q...
Leonel Morgado
 
aziz sancar nobel prize winner: from mardin to nobel
aziz sancar nobel prize winner: from mardin to nobelaziz sancar nobel prize winner: from mardin to nobel
aziz sancar nobel prize winner: from mardin to nobel
İsa Badur
 
ESA/ACT Science Coffee: Diego Blas - Gravitational wave detection with orbita...
ESA/ACT Science Coffee: Diego Blas - Gravitational wave detection with orbita...ESA/ACT Science Coffee: Diego Blas - Gravitational wave detection with orbita...
ESA/ACT Science Coffee: Diego Blas - Gravitational wave detection with orbita...
Advanced-Concepts-Team
 
Sharlene Leurig - Enabling Onsite Water Use with Net Zero Water
Sharlene Leurig - Enabling Onsite Water Use with Net Zero WaterSharlene Leurig - Enabling Onsite Water Use with Net Zero Water
Sharlene Leurig - Enabling Onsite Water Use with Net Zero Water
Texas Alliance of Groundwater Districts
 
Topic: SICKLE CELL DISEASE IN CHILDREN-3.pdf
Topic: SICKLE CELL DISEASE IN CHILDREN-3.pdfTopic: SICKLE CELL DISEASE IN CHILDREN-3.pdf
Topic: SICKLE CELL DISEASE IN CHILDREN-3.pdf
TinyAnderson
 
快速办理(UAM毕业证书)马德里自治大学毕业证学位证一模一样
快速办理(UAM毕业证书)马德里自治大学毕业证学位证一模一样快速办理(UAM毕业证书)马德里自治大学毕业证学位证一模一样
快速办理(UAM毕业证书)马德里自治大学毕业证学位证一模一样
hozt8xgk
 
Eukaryotic Transcription Presentation.pptx
Eukaryotic Transcription Presentation.pptxEukaryotic Transcription Presentation.pptx
Eukaryotic Transcription Presentation.pptx
RitabrataSarkar3
 
Shallowest Oil Discovery of Turkiye.pptx
Shallowest Oil Discovery of Turkiye.pptxShallowest Oil Discovery of Turkiye.pptx
Shallowest Oil Discovery of Turkiye.pptx
Gokturk Mehmet Dilci
 
Thornton ESPP slides UK WW Network 4_6_24.pdf
Thornton ESPP slides UK WW Network 4_6_24.pdfThornton ESPP slides UK WW Network 4_6_24.pdf
Thornton ESPP slides UK WW Network 4_6_24.pdf
European Sustainable Phosphorus Platform
 
EWOCS-I: The catalog of X-ray sources in Westerlund 1 from the Extended Weste...
EWOCS-I: The catalog of X-ray sources in Westerlund 1 from the Extended Weste...EWOCS-I: The catalog of X-ray sources in Westerlund 1 from the Extended Weste...
EWOCS-I: The catalog of X-ray sources in Westerlund 1 from the Extended Weste...
Sérgio Sacani
 
Equivariant neural networks and representation theory
Equivariant neural networks and representation theoryEquivariant neural networks and representation theory
Equivariant neural networks and representation theory
Daniel Tubbenhauer
 
mô tả các thí nghiệm về đánh giá tác động dòng khí hóa sau đốt
mô tả các thí nghiệm về đánh giá tác động dòng khí hóa sau đốtmô tả các thí nghiệm về đánh giá tác động dòng khí hóa sau đốt
mô tả các thí nghiệm về đánh giá tác động dòng khí hóa sau đốt
HongcNguyn6
 
Medical Orthopedic PowerPoint Templates.pptx
Medical Orthopedic PowerPoint Templates.pptxMedical Orthopedic PowerPoint Templates.pptx
Medical Orthopedic PowerPoint Templates.pptx
terusbelajar5
 
在线办理(salfor毕业证书)索尔福德大学毕业证毕业完成信一模一样
在线办理(salfor毕业证书)索尔福德大学毕业证毕业完成信一模一样在线办理(salfor毕业证书)索尔福德大学毕业证毕业完成信一模一样
在线办理(salfor毕业证书)索尔福德大学毕业证毕业完成信一模一样
vluwdy49
 
GBSN - Biochemistry (Unit 6) Chemistry of Proteins
GBSN - Biochemistry (Unit 6) Chemistry of ProteinsGBSN - Biochemistry (Unit 6) Chemistry of Proteins
GBSN - Biochemistry (Unit 6) Chemistry of Proteins
Areesha Ahmad
 
Applied Science: Thermodynamics, Laws & Methodology.pdf
Applied Science: Thermodynamics, Laws & Methodology.pdfApplied Science: Thermodynamics, Laws & Methodology.pdf
Applied Science: Thermodynamics, Laws & Methodology.pdf
University of Hertfordshire
 
Basics of crystallography, crystal systems, classes and different forms
Basics of crystallography, crystal systems, classes and different formsBasics of crystallography, crystal systems, classes and different forms
Basics of crystallography, crystal systems, classes and different forms
MaheshaNanjegowda
 
Immersive Learning That Works: Research Grounding and Paths Forward
Immersive Learning That Works: Research Grounding and Paths ForwardImmersive Learning That Works: Research Grounding and Paths Forward
Immersive Learning That Works: Research Grounding and Paths Forward
Leonel Morgado
 
SAR of Medicinal Chemistry 1st by dk.pdf
SAR of Medicinal Chemistry 1st by dk.pdfSAR of Medicinal Chemistry 1st by dk.pdf
SAR of Medicinal Chemistry 1st by dk.pdf
KrushnaDarade1
 
ESR spectroscopy in liquid food and beverages.pptx
ESR spectroscopy in liquid food and beverages.pptxESR spectroscopy in liquid food and beverages.pptx
ESR spectroscopy in liquid food and beverages.pptx
PRIYANKA PATEL
 

Recently uploaded (20)

Authoring a personal GPT for your research and practice: How we created the Q...
Authoring a personal GPT for your research and practice: How we created the Q...Authoring a personal GPT for your research and practice: How we created the Q...
Authoring a personal GPT for your research and practice: How we created the Q...
 
aziz sancar nobel prize winner: from mardin to nobel
aziz sancar nobel prize winner: from mardin to nobelaziz sancar nobel prize winner: from mardin to nobel
aziz sancar nobel prize winner: from mardin to nobel
 
ESA/ACT Science Coffee: Diego Blas - Gravitational wave detection with orbita...
ESA/ACT Science Coffee: Diego Blas - Gravitational wave detection with orbita...ESA/ACT Science Coffee: Diego Blas - Gravitational wave detection with orbita...
ESA/ACT Science Coffee: Diego Blas - Gravitational wave detection with orbita...
 
Sharlene Leurig - Enabling Onsite Water Use with Net Zero Water
Sharlene Leurig - Enabling Onsite Water Use with Net Zero WaterSharlene Leurig - Enabling Onsite Water Use with Net Zero Water
Sharlene Leurig - Enabling Onsite Water Use with Net Zero Water
 
Topic: SICKLE CELL DISEASE IN CHILDREN-3.pdf
Topic: SICKLE CELL DISEASE IN CHILDREN-3.pdfTopic: SICKLE CELL DISEASE IN CHILDREN-3.pdf
Topic: SICKLE CELL DISEASE IN CHILDREN-3.pdf
 
快速办理(UAM毕业证书)马德里自治大学毕业证学位证一模一样
快速办理(UAM毕业证书)马德里自治大学毕业证学位证一模一样快速办理(UAM毕业证书)马德里自治大学毕业证学位证一模一样
快速办理(UAM毕业证书)马德里自治大学毕业证学位证一模一样
 
Eukaryotic Transcription Presentation.pptx
Eukaryotic Transcription Presentation.pptxEukaryotic Transcription Presentation.pptx
Eukaryotic Transcription Presentation.pptx
 
Shallowest Oil Discovery of Turkiye.pptx
Shallowest Oil Discovery of Turkiye.pptxShallowest Oil Discovery of Turkiye.pptx
Shallowest Oil Discovery of Turkiye.pptx
 
Thornton ESPP slides UK WW Network 4_6_24.pdf
Thornton ESPP slides UK WW Network 4_6_24.pdfThornton ESPP slides UK WW Network 4_6_24.pdf
Thornton ESPP slides UK WW Network 4_6_24.pdf
 
EWOCS-I: The catalog of X-ray sources in Westerlund 1 from the Extended Weste...
EWOCS-I: The catalog of X-ray sources in Westerlund 1 from the Extended Weste...EWOCS-I: The catalog of X-ray sources in Westerlund 1 from the Extended Weste...
EWOCS-I: The catalog of X-ray sources in Westerlund 1 from the Extended Weste...
 
Equivariant neural networks and representation theory
Equivariant neural networks and representation theoryEquivariant neural networks and representation theory
Equivariant neural networks and representation theory
 
mô tả các thí nghiệm về đánh giá tác động dòng khí hóa sau đốt
mô tả các thí nghiệm về đánh giá tác động dòng khí hóa sau đốtmô tả các thí nghiệm về đánh giá tác động dòng khí hóa sau đốt
mô tả các thí nghiệm về đánh giá tác động dòng khí hóa sau đốt
 
Medical Orthopedic PowerPoint Templates.pptx
Medical Orthopedic PowerPoint Templates.pptxMedical Orthopedic PowerPoint Templates.pptx
Medical Orthopedic PowerPoint Templates.pptx
 
在线办理(salfor毕业证书)索尔福德大学毕业证毕业完成信一模一样
在线办理(salfor毕业证书)索尔福德大学毕业证毕业完成信一模一样在线办理(salfor毕业证书)索尔福德大学毕业证毕业完成信一模一样
在线办理(salfor毕业证书)索尔福德大学毕业证毕业完成信一模一样
 
GBSN - Biochemistry (Unit 6) Chemistry of Proteins
GBSN - Biochemistry (Unit 6) Chemistry of ProteinsGBSN - Biochemistry (Unit 6) Chemistry of Proteins
GBSN - Biochemistry (Unit 6) Chemistry of Proteins
 
Applied Science: Thermodynamics, Laws & Methodology.pdf
Applied Science: Thermodynamics, Laws & Methodology.pdfApplied Science: Thermodynamics, Laws & Methodology.pdf
Applied Science: Thermodynamics, Laws & Methodology.pdf
 
Basics of crystallography, crystal systems, classes and different forms
Basics of crystallography, crystal systems, classes and different formsBasics of crystallography, crystal systems, classes and different forms
Basics of crystallography, crystal systems, classes and different forms
 
Immersive Learning That Works: Research Grounding and Paths Forward
Immersive Learning That Works: Research Grounding and Paths ForwardImmersive Learning That Works: Research Grounding and Paths Forward
Immersive Learning That Works: Research Grounding and Paths Forward
 
SAR of Medicinal Chemistry 1st by dk.pdf
SAR of Medicinal Chemistry 1st by dk.pdfSAR of Medicinal Chemistry 1st by dk.pdf
SAR of Medicinal Chemistry 1st by dk.pdf
 
ESR spectroscopy in liquid food and beverages.pptx
ESR spectroscopy in liquid food and beverages.pptxESR spectroscopy in liquid food and beverages.pptx
ESR spectroscopy in liquid food and beverages.pptx
 

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.