SlideShare a Scribd company logo
Let's Paint a Picasso:
A look at Generative Adversarial Networks (GAN)
and its applications.
Sreya Ghosh (Ph.D.)
Data Scientist II, Merchandising
Wayfair
Portrait of Edmond Belamy
Artist: Obvious
Year: 2018
Auction House: Christie’s
Price: $432,500
Generative Adversarial Networks (GANS)
Generative: Generate new data based on some learned features.
Adversarial: A game-theory derived cost function
Network: Deep Neural Networks
Yann LeCun : “Adversarial training is the coolest thing since sliced bread.”
Generative Adversarial Nets.
Ian J. Goodfellow , Jean Pouget-Abadie , Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair , Aaron
Courville, Yoshua Bengio
University of Montreal, NeuralIPS, 2014
Deep Neural Networks
AutoEncoders
Encoder: This is the part of the network that compresses the input into a latent-
space representation. It can be represented by an encoding function h=f(x).
Decoder: This part aims to reconstruct the input from the latent space
representation. It can be represented by a decoding function r=g(h).
Generative Model
● Noise from a simple distribution like a Gaussian/Uniform Distribution is used to
represent Latent Features.
● The semantic meaning of the latent features is learnt via a neural network.
Discriminative Model
● Generator alone will just create
random noise. Conceptually, the
discriminator in GAN provides
guidance to the generator on what
to create.
● Discriminator predicts the label of
images.
○ Fake images generated from the
Generator are 0
○ Images from the distribution is 1
● The idea is to bring the accuracy
of the Discriminator to 50%
GAN Architecture
The Cost Function
Discriminator: Cross-Entropy
Generator:
GAN:
Performance
Types of GANs
Deep Convolutional GANs (DCGANs): The first improvement over GAN. This
network studied and found optimal hyper-parameters.
Conditional GANs (cGANs): These are GANs that use extra label information.
This results in better quality images and being able to control to an extent how
generated images will look.
Wasserstein GANs : Change the loss function to include the Wasserstein
distance. As a result, WassGANs have loss functions that correlate with image
quality. Also, training stability improves and is not as dependent on the
architecture.
Super Resolution GAN (SRGAN)
● Super-resolution GAN applies a deep
network in combination with an
adversary network to produce higher
resolution images.
● During the training, a high-resolution
image (HR) is downsampled to a low-
resolution image (LR).
● A GAN generator upsamples LR
images to super-resolution images
(SR).
● A discriminator to distinguish the HR
images and backpropagate the GAN
loss to train the discriminator and the
generator.
StackGAN: Generative Adversarial Text to Image
Synthesis
● Generate photo-realistic images
conditioned on text descriptions.
● The Stage-I GAN sketches the
primitive shape and colors of the
object based on the given text
description.
● The Stage-II GAN takes Stage-I
results and text descriptions as
inputs, and generates high-
resolution images with photo-
realistic details.
● Conditioning Augmentation
technique encourages
smoothness in the latent
conditioning manifold.
Generative Visual Manipulation on the Natural Image
Manifold
● We then define a class of image
editing operations, and constrain
their output to lie on that learned
manifold at all times.
● The model automatically adjusts
the output keeping all edits as
realistic as possible.
● The presented method can further
be used for changing one image
to look like the other, as well as
generating novel imagery from
scratch based on user's scribbles.
Attribute2Image: Conditional Image Generation from
Visual Attributes
● The image as a composite of
foreground and background
● A layered generative model
with disentangled latent
variables that can be learned
end-to-end using a
variational auto-encoder.
● Generating realistic and
diverse samples with
disentangled latent
representations.
Pose Guided Person Image Generation
Trying to paint Modern Art
● Scraped 1500 images from Google
images using search terms paintings
of faces.
● Augmented the data-set using flipped
images.
● All images were resized to
112x112x3.
● DC-GAN was used to generate the
images
● 20,000 epochs.
Challenges
● The networks try to take successive steps
to minimize a non-convex objective and
end up in an oscillating process rather
than decreasing the underlying true
objective.
● The generator can accidentally start to
produce several copies of exactly the
same image.
● GANs can sometimes be far-sighted and
fail to differentiate the number of particular
objects that should occur at a location.
● GANs sometime are not capable of
differentiating between front and back
view.
Future Work with GAN
● Find effective solutions to challenges, different cost functions that ensure
Nash equilibrium.
● Drug discovery and potential medical applications.
● Application in NLP, especially language modelling.
● Speech generation.
● Cataloging and Image based search.
Citations:
1.Generative Adversarial Nets. Ian J. Goodfellow , Jean Pouget-Abadie , Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil
Ozair , Aaron Courville, Yoshua Bengio, University of Montreal, NeuralIPS, 2014.
2. GAN — What is Generative Adversary Networks GAN? Jonathan Hui. 06-2018
3. GAN — Some cool applications of GANs. Jonathan Hui. 06-2018
4.Generative Adversarial Networks (GANs) — A Beginner’s Guide. Owen Carey. 2018
5. DCGAN: Generate the images with Deep Convolutional GAN. Keisuke Umezawa. 2018
6. https://github.com/eriklindernoren/Keras-GAN

More Related Content

Similar to Let's paint a Picasso - A Look at Generative Adversarial Networks (GAN) and its Applications - Sreya Ghosh

Image colorization
Image colorizationImage colorization
Image colorization
Yash Saraf
 
Deep Generative Modelling
Deep Generative ModellingDeep Generative Modelling
Deep Generative Modelling
Petko Nikolov
 
Face-GAN project report.pptx
Face-GAN project report.pptxFace-GAN project report.pptx
Face-GAN project report.pptx
AndleebFatima16
 
Face-GAN project report
Face-GAN project reportFace-GAN project report
Face-GAN project report
AndleebFatima16
 
Decomposing image generation into layout priction and conditional synthesis
Decomposing image generation into layout priction and conditional synthesisDecomposing image generation into layout priction and conditional synthesis
Decomposing image generation into layout priction and conditional synthesis
Naeem Shehzad
 
Generation of Deepfake images using GAN and Least squares GAN.ppt
Generation of Deepfake images using GAN and Least squares GAN.pptGeneration of Deepfake images using GAN and Least squares GAN.ppt
Generation of Deepfake images using GAN and Least squares GAN.ppt
DivyaGugulothu
 
GAN Deep Learning Approaches to Image Processing Applications (1).pptx
GAN Deep Learning Approaches to Image Processing Applications (1).pptxGAN Deep Learning Approaches to Image Processing Applications (1).pptx
GAN Deep Learning Approaches to Image Processing Applications (1).pptx
RMDAcademicCoordinat
 
Project_Final_Review.pdf
Project_Final_Review.pdfProject_Final_Review.pdf
Project_Final_Review.pdf
DivyaGugulothu
 
Image Generation from Caption
Image Generation from Caption Image Generation from Caption
Image Generation from Caption
IJSCAI Journal
 
IMAGE GENERATION FROM CAPTION
IMAGE GENERATION FROM CAPTIONIMAGE GENERATION FROM CAPTION
IMAGE GENERATION FROM CAPTION
ijscai
 
Introduction to Generative Adversarial Networks (GANs)
Introduction to Generative Adversarial Networks (GANs)Introduction to Generative Adversarial Networks (GANs)
Introduction to Generative Adversarial Networks (GANs)
Appsilon Data Science
 
Alberto Massidda - Scenes from a memory - Codemotion Rome 2019
Alberto Massidda - Scenes from a memory - Codemotion Rome 2019Alberto Massidda - Scenes from a memory - Codemotion Rome 2019
Alberto Massidda - Scenes from a memory - Codemotion Rome 2019
Codemotion
 
Reading group gan - 20170417
Reading group   gan - 20170417Reading group   gan - 20170417
Reading group gan - 20170417
Shuai Zhang
 
Generative adversarial network_Ayadi_Alaeddine
Generative adversarial network_Ayadi_AlaeddineGenerative adversarial network_Ayadi_Alaeddine
Generative adversarial network_Ayadi_Alaeddine
Deep Learning Italia
 
Variational Autoencoders For Image Generation
Variational Autoencoders For Image GenerationVariational Autoencoders For Image Generation
Variational Autoencoders For Image Generation
Jason Anderson
 
Deep Generative Models - Kevin McGuinness - UPC Barcelona 2018
Deep Generative Models - Kevin McGuinness - UPC Barcelona 2018Deep Generative Models - Kevin McGuinness - UPC Barcelona 2018
Deep Generative Models - Kevin McGuinness - UPC Barcelona 2018
Universitat Politècnica de Catalunya
 
GAN.pptx
GAN.pptxGAN.pptx
Generational Adversarial Neural Networks - Essential Reference
Generational Adversarial Neural Networks - Essential ReferenceGenerational Adversarial Neural Networks - Essential Reference
Generational Adversarial Neural Networks - Essential Reference
Gokul Alex
 
物件偵測與辨識技術
物件偵測與辨識技術物件偵測與辨識技術
物件偵測與辨識技術
CHENHuiMei
 
brief Introduction to Different Kinds of GANs
brief Introduction to Different Kinds of GANsbrief Introduction to Different Kinds of GANs
brief Introduction to Different Kinds of GANs
Parham Zilouchian
 

Similar to Let's paint a Picasso - A Look at Generative Adversarial Networks (GAN) and its Applications - Sreya Ghosh (20)

Image colorization
Image colorizationImage colorization
Image colorization
 
Deep Generative Modelling
Deep Generative ModellingDeep Generative Modelling
Deep Generative Modelling
 
Face-GAN project report.pptx
Face-GAN project report.pptxFace-GAN project report.pptx
Face-GAN project report.pptx
 
Face-GAN project report
Face-GAN project reportFace-GAN project report
Face-GAN project report
 
Decomposing image generation into layout priction and conditional synthesis
Decomposing image generation into layout priction and conditional synthesisDecomposing image generation into layout priction and conditional synthesis
Decomposing image generation into layout priction and conditional synthesis
 
Generation of Deepfake images using GAN and Least squares GAN.ppt
Generation of Deepfake images using GAN and Least squares GAN.pptGeneration of Deepfake images using GAN and Least squares GAN.ppt
Generation of Deepfake images using GAN and Least squares GAN.ppt
 
GAN Deep Learning Approaches to Image Processing Applications (1).pptx
GAN Deep Learning Approaches to Image Processing Applications (1).pptxGAN Deep Learning Approaches to Image Processing Applications (1).pptx
GAN Deep Learning Approaches to Image Processing Applications (1).pptx
 
Project_Final_Review.pdf
Project_Final_Review.pdfProject_Final_Review.pdf
Project_Final_Review.pdf
 
Image Generation from Caption
Image Generation from Caption Image Generation from Caption
Image Generation from Caption
 
IMAGE GENERATION FROM CAPTION
IMAGE GENERATION FROM CAPTIONIMAGE GENERATION FROM CAPTION
IMAGE GENERATION FROM CAPTION
 
Introduction to Generative Adversarial Networks (GANs)
Introduction to Generative Adversarial Networks (GANs)Introduction to Generative Adversarial Networks (GANs)
Introduction to Generative Adversarial Networks (GANs)
 
Alberto Massidda - Scenes from a memory - Codemotion Rome 2019
Alberto Massidda - Scenes from a memory - Codemotion Rome 2019Alberto Massidda - Scenes from a memory - Codemotion Rome 2019
Alberto Massidda - Scenes from a memory - Codemotion Rome 2019
 
Reading group gan - 20170417
Reading group   gan - 20170417Reading group   gan - 20170417
Reading group gan - 20170417
 
Generative adversarial network_Ayadi_Alaeddine
Generative adversarial network_Ayadi_AlaeddineGenerative adversarial network_Ayadi_Alaeddine
Generative adversarial network_Ayadi_Alaeddine
 
Variational Autoencoders For Image Generation
Variational Autoencoders For Image GenerationVariational Autoencoders For Image Generation
Variational Autoencoders For Image Generation
 
Deep Generative Models - Kevin McGuinness - UPC Barcelona 2018
Deep Generative Models - Kevin McGuinness - UPC Barcelona 2018Deep Generative Models - Kevin McGuinness - UPC Barcelona 2018
Deep Generative Models - Kevin McGuinness - UPC Barcelona 2018
 
GAN.pptx
GAN.pptxGAN.pptx
GAN.pptx
 
Generational Adversarial Neural Networks - Essential Reference
Generational Adversarial Neural Networks - Essential ReferenceGenerational Adversarial Neural Networks - Essential Reference
Generational Adversarial Neural Networks - Essential Reference
 
物件偵測與辨識技術
物件偵測與辨識技術物件偵測與辨識技術
物件偵測與辨識技術
 
brief Introduction to Different Kinds of GANs
brief Introduction to Different Kinds of GANsbrief Introduction to Different Kinds of GANs
brief Introduction to Different Kinds of GANs
 

More from Catalina Arango

Intelligent Enterprise: How to Create the Customer Experience of the Future? ...
Intelligent Enterprise: How to Create the Customer Experience of the Future? ...Intelligent Enterprise: How to Create the Customer Experience of the Future? ...
Intelligent Enterprise: How to Create the Customer Experience of the Future? ...
Catalina Arango
 
It's All About the Data - Tia Dubuisson
It's All About the Data - Tia DubuissonIt's All About the Data - Tia Dubuisson
It's All About the Data - Tia Dubuisson
Catalina Arango
 
Transforming an Organization using Data Science - Successes & Challenges - Da...
Transforming an Organization using Data Science - Successes & Challenges - Da...Transforming an Organization using Data Science - Successes & Challenges - Da...
Transforming an Organization using Data Science - Successes & Challenges - Da...
Catalina Arango
 
Natural Language Processing - Principles and Practice - Gracie Diaz
Natural Language Processing - Principles and Practice - Gracie DiazNatural Language Processing - Principles and Practice - Gracie Diaz
Natural Language Processing - Principles and Practice - Gracie Diaz
Catalina Arango
 
Digital Data Transformation
Digital Data TransformationDigital Data Transformation
Digital Data Transformation
Catalina Arango
 
The right JOIN: Merchants + Data
The right JOIN: Merchants + DataThe right JOIN: Merchants + Data
The right JOIN: Merchants + Data
Catalina Arango
 
Biomedical Signal Extraction for Computer-assisted Clinical Decision Making -...
Biomedical Signal Extraction for Computer-assisted Clinical Decision Making -...Biomedical Signal Extraction for Computer-assisted Clinical Decision Making -...
Biomedical Signal Extraction for Computer-assisted Clinical Decision Making -...
Catalina Arango
 
The Power of Topology - Colleen Farrelly - WiDS Miami 2018
The Power of Topology - Colleen Farrelly - WiDS Miami 2018The Power of Topology - Colleen Farrelly - WiDS Miami 2018
The Power of Topology - Colleen Farrelly - WiDS Miami 2018
Catalina Arango
 
How AI is Transforming Industry - Dr. Monica DeZulueta - WiDS Miami 2018
How AI is Transforming Industry - Dr. Monica DeZulueta - WiDS Miami 2018How AI is Transforming Industry - Dr. Monica DeZulueta - WiDS Miami 2018
How AI is Transforming Industry - Dr. Monica DeZulueta - WiDS Miami 2018
Catalina Arango
 

More from Catalina Arango (9)

Intelligent Enterprise: How to Create the Customer Experience of the Future? ...
Intelligent Enterprise: How to Create the Customer Experience of the Future? ...Intelligent Enterprise: How to Create the Customer Experience of the Future? ...
Intelligent Enterprise: How to Create the Customer Experience of the Future? ...
 
It's All About the Data - Tia Dubuisson
It's All About the Data - Tia DubuissonIt's All About the Data - Tia Dubuisson
It's All About the Data - Tia Dubuisson
 
Transforming an Organization using Data Science - Successes & Challenges - Da...
Transforming an Organization using Data Science - Successes & Challenges - Da...Transforming an Organization using Data Science - Successes & Challenges - Da...
Transforming an Organization using Data Science - Successes & Challenges - Da...
 
Natural Language Processing - Principles and Practice - Gracie Diaz
Natural Language Processing - Principles and Practice - Gracie DiazNatural Language Processing - Principles and Practice - Gracie Diaz
Natural Language Processing - Principles and Practice - Gracie Diaz
 
Digital Data Transformation
Digital Data TransformationDigital Data Transformation
Digital Data Transformation
 
The right JOIN: Merchants + Data
The right JOIN: Merchants + DataThe right JOIN: Merchants + Data
The right JOIN: Merchants + Data
 
Biomedical Signal Extraction for Computer-assisted Clinical Decision Making -...
Biomedical Signal Extraction for Computer-assisted Clinical Decision Making -...Biomedical Signal Extraction for Computer-assisted Clinical Decision Making -...
Biomedical Signal Extraction for Computer-assisted Clinical Decision Making -...
 
The Power of Topology - Colleen Farrelly - WiDS Miami 2018
The Power of Topology - Colleen Farrelly - WiDS Miami 2018The Power of Topology - Colleen Farrelly - WiDS Miami 2018
The Power of Topology - Colleen Farrelly - WiDS Miami 2018
 
How AI is Transforming Industry - Dr. Monica DeZulueta - WiDS Miami 2018
How AI is Transforming Industry - Dr. Monica DeZulueta - WiDS Miami 2018How AI is Transforming Industry - Dr. Monica DeZulueta - WiDS Miami 2018
How AI is Transforming Industry - Dr. Monica DeZulueta - WiDS Miami 2018
 

Recently uploaded

Natural Language Processing (NLP), RAG and its applications .pptx
Natural Language Processing (NLP), RAG and its applications .pptxNatural Language Processing (NLP), RAG and its applications .pptx
Natural Language Processing (NLP), RAG and its applications .pptx
fkyes25
 
Enhanced Enterprise Intelligence with your personal AI Data Copilot.pdf
Enhanced Enterprise Intelligence with your personal AI Data Copilot.pdfEnhanced Enterprise Intelligence with your personal AI Data Copilot.pdf
Enhanced Enterprise Intelligence with your personal AI Data Copilot.pdf
GetInData
 
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
Timothy Spann
 
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
nuttdpt
 
Global Situational Awareness of A.I. and where its headed
Global Situational Awareness of A.I. and where its headedGlobal Situational Awareness of A.I. and where its headed
Global Situational Awareness of A.I. and where its headed
vikram sood
 
Population Growth in Bataan: The effects of population growth around rural pl...
Population Growth in Bataan: The effects of population growth around rural pl...Population Growth in Bataan: The effects of population growth around rural pl...
Population Growth in Bataan: The effects of population growth around rural pl...
Bill641377
 
Challenges of Nation Building-1.pptx with more important
Challenges of Nation Building-1.pptx with more importantChallenges of Nation Building-1.pptx with more important
Challenges of Nation Building-1.pptx with more important
Sm321
 
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
bopyb
 
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
nuttdpt
 
一比一原版(CBU毕业证)卡普顿大学毕业证如何办理
一比一原版(CBU毕业证)卡普顿大学毕业证如何办理一比一原版(CBU毕业证)卡普顿大学毕业证如何办理
一比一原版(CBU毕业证)卡普顿大学毕业证如何办理
ahzuo
 
Intelligence supported media monitoring in veterinary medicine
Intelligence supported media monitoring in veterinary medicineIntelligence supported media monitoring in veterinary medicine
Intelligence supported media monitoring in veterinary medicine
AndrzejJarynowski
 
My burning issue is homelessness K.C.M.O.
My burning issue is homelessness K.C.M.O.My burning issue is homelessness K.C.M.O.
My burning issue is homelessness K.C.M.O.
rwarrenll
 
原版制作(Deakin毕业证书)迪肯大学毕业证学位证一模一样
原版制作(Deakin毕业证书)迪肯大学毕业证学位证一模一样原版制作(Deakin毕业证书)迪肯大学毕业证学位证一模一样
原版制作(Deakin毕业证书)迪肯大学毕业证学位证一模一样
u86oixdj
 
一比一原版(Adelaide毕业证书)阿德莱德大学毕业证如何办理
一比一原版(Adelaide毕业证书)阿德莱德大学毕业证如何办理一比一原版(Adelaide毕业证书)阿德莱德大学毕业证如何办理
一比一原版(Adelaide毕业证书)阿德莱德大学毕业证如何办理
slg6lamcq
 
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
Social Samosa
 
Predictably Improve Your B2B Tech Company's Performance by Leveraging Data
Predictably Improve Your B2B Tech Company's Performance by Leveraging DataPredictably Improve Your B2B Tech Company's Performance by Leveraging Data
Predictably Improve Your B2B Tech Company's Performance by Leveraging Data
Kiwi Creative
 
Beyond the Basics of A/B Tests: Highly Innovative Experimentation Tactics You...
Beyond the Basics of A/B Tests: Highly Innovative Experimentation Tactics You...Beyond the Basics of A/B Tests: Highly Innovative Experimentation Tactics You...
Beyond the Basics of A/B Tests: Highly Innovative Experimentation Tactics You...
Aggregage
 
原版制作(swinburne毕业证书)斯威本科技大学毕业证毕业完成信一模一样
原版制作(swinburne毕业证书)斯威本科技大学毕业证毕业完成信一模一样原版制作(swinburne毕业证书)斯威本科技大学毕业证毕业完成信一模一样
原版制作(swinburne毕业证书)斯威本科技大学毕业证毕业完成信一模一样
u86oixdj
 
Analysis insight about a Flyball dog competition team's performance
Analysis insight about a Flyball dog competition team's performanceAnalysis insight about a Flyball dog competition team's performance
Analysis insight about a Flyball dog competition team's performance
roli9797
 
一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
74nqk8xf
 

Recently uploaded (20)

Natural Language Processing (NLP), RAG and its applications .pptx
Natural Language Processing (NLP), RAG and its applications .pptxNatural Language Processing (NLP), RAG and its applications .pptx
Natural Language Processing (NLP), RAG and its applications .pptx
 
Enhanced Enterprise Intelligence with your personal AI Data Copilot.pdf
Enhanced Enterprise Intelligence with your personal AI Data Copilot.pdfEnhanced Enterprise Intelligence with your personal AI Data Copilot.pdf
Enhanced Enterprise Intelligence with your personal AI Data Copilot.pdf
 
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
 
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
 
Global Situational Awareness of A.I. and where its headed
Global Situational Awareness of A.I. and where its headedGlobal Situational Awareness of A.I. and where its headed
Global Situational Awareness of A.I. and where its headed
 
Population Growth in Bataan: The effects of population growth around rural pl...
Population Growth in Bataan: The effects of population growth around rural pl...Population Growth in Bataan: The effects of population growth around rural pl...
Population Growth in Bataan: The effects of population growth around rural pl...
 
Challenges of Nation Building-1.pptx with more important
Challenges of Nation Building-1.pptx with more importantChallenges of Nation Building-1.pptx with more important
Challenges of Nation Building-1.pptx with more important
 
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
 
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
 
一比一原版(CBU毕业证)卡普顿大学毕业证如何办理
一比一原版(CBU毕业证)卡普顿大学毕业证如何办理一比一原版(CBU毕业证)卡普顿大学毕业证如何办理
一比一原版(CBU毕业证)卡普顿大学毕业证如何办理
 
Intelligence supported media monitoring in veterinary medicine
Intelligence supported media monitoring in veterinary medicineIntelligence supported media monitoring in veterinary medicine
Intelligence supported media monitoring in veterinary medicine
 
My burning issue is homelessness K.C.M.O.
My burning issue is homelessness K.C.M.O.My burning issue is homelessness K.C.M.O.
My burning issue is homelessness K.C.M.O.
 
原版制作(Deakin毕业证书)迪肯大学毕业证学位证一模一样
原版制作(Deakin毕业证书)迪肯大学毕业证学位证一模一样原版制作(Deakin毕业证书)迪肯大学毕业证学位证一模一样
原版制作(Deakin毕业证书)迪肯大学毕业证学位证一模一样
 
一比一原版(Adelaide毕业证书)阿德莱德大学毕业证如何办理
一比一原版(Adelaide毕业证书)阿德莱德大学毕业证如何办理一比一原版(Adelaide毕业证书)阿德莱德大学毕业证如何办理
一比一原版(Adelaide毕业证书)阿德莱德大学毕业证如何办理
 
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
 
Predictably Improve Your B2B Tech Company's Performance by Leveraging Data
Predictably Improve Your B2B Tech Company's Performance by Leveraging DataPredictably Improve Your B2B Tech Company's Performance by Leveraging Data
Predictably Improve Your B2B Tech Company's Performance by Leveraging Data
 
Beyond the Basics of A/B Tests: Highly Innovative Experimentation Tactics You...
Beyond the Basics of A/B Tests: Highly Innovative Experimentation Tactics You...Beyond the Basics of A/B Tests: Highly Innovative Experimentation Tactics You...
Beyond the Basics of A/B Tests: Highly Innovative Experimentation Tactics You...
 
原版制作(swinburne毕业证书)斯威本科技大学毕业证毕业完成信一模一样
原版制作(swinburne毕业证书)斯威本科技大学毕业证毕业完成信一模一样原版制作(swinburne毕业证书)斯威本科技大学毕业证毕业完成信一模一样
原版制作(swinburne毕业证书)斯威本科技大学毕业证毕业完成信一模一样
 
Analysis insight about a Flyball dog competition team's performance
Analysis insight about a Flyball dog competition team's performanceAnalysis insight about a Flyball dog competition team's performance
Analysis insight about a Flyball dog competition team's performance
 
一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
 

Let's paint a Picasso - A Look at Generative Adversarial Networks (GAN) and its Applications - Sreya Ghosh

  • 1. Let's Paint a Picasso: A look at Generative Adversarial Networks (GAN) and its applications. Sreya Ghosh (Ph.D.) Data Scientist II, Merchandising Wayfair
  • 2. Portrait of Edmond Belamy Artist: Obvious Year: 2018 Auction House: Christie’s Price: $432,500
  • 3. Generative Adversarial Networks (GANS) Generative: Generate new data based on some learned features. Adversarial: A game-theory derived cost function Network: Deep Neural Networks Yann LeCun : “Adversarial training is the coolest thing since sliced bread.” Generative Adversarial Nets. Ian J. Goodfellow , Jean Pouget-Abadie , Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair , Aaron Courville, Yoshua Bengio University of Montreal, NeuralIPS, 2014
  • 4.
  • 6. AutoEncoders Encoder: This is the part of the network that compresses the input into a latent- space representation. It can be represented by an encoding function h=f(x). Decoder: This part aims to reconstruct the input from the latent space representation. It can be represented by a decoding function r=g(h).
  • 7. Generative Model ● Noise from a simple distribution like a Gaussian/Uniform Distribution is used to represent Latent Features. ● The semantic meaning of the latent features is learnt via a neural network.
  • 8. Discriminative Model ● Generator alone will just create random noise. Conceptually, the discriminator in GAN provides guidance to the generator on what to create. ● Discriminator predicts the label of images. ○ Fake images generated from the Generator are 0 ○ Images from the distribution is 1 ● The idea is to bring the accuracy of the Discriminator to 50%
  • 10. The Cost Function Discriminator: Cross-Entropy Generator: GAN:
  • 12. Types of GANs Deep Convolutional GANs (DCGANs): The first improvement over GAN. This network studied and found optimal hyper-parameters. Conditional GANs (cGANs): These are GANs that use extra label information. This results in better quality images and being able to control to an extent how generated images will look. Wasserstein GANs : Change the loss function to include the Wasserstein distance. As a result, WassGANs have loss functions that correlate with image quality. Also, training stability improves and is not as dependent on the architecture.
  • 13. Super Resolution GAN (SRGAN) ● Super-resolution GAN applies a deep network in combination with an adversary network to produce higher resolution images. ● During the training, a high-resolution image (HR) is downsampled to a low- resolution image (LR). ● A GAN generator upsamples LR images to super-resolution images (SR). ● A discriminator to distinguish the HR images and backpropagate the GAN loss to train the discriminator and the generator.
  • 14. StackGAN: Generative Adversarial Text to Image Synthesis ● Generate photo-realistic images conditioned on text descriptions. ● The Stage-I GAN sketches the primitive shape and colors of the object based on the given text description. ● The Stage-II GAN takes Stage-I results and text descriptions as inputs, and generates high- resolution images with photo- realistic details. ● Conditioning Augmentation technique encourages smoothness in the latent conditioning manifold.
  • 15. Generative Visual Manipulation on the Natural Image Manifold ● We then define a class of image editing operations, and constrain their output to lie on that learned manifold at all times. ● The model automatically adjusts the output keeping all edits as realistic as possible. ● The presented method can further be used for changing one image to look like the other, as well as generating novel imagery from scratch based on user's scribbles.
  • 16. Attribute2Image: Conditional Image Generation from Visual Attributes ● The image as a composite of foreground and background ● A layered generative model with disentangled latent variables that can be learned end-to-end using a variational auto-encoder. ● Generating realistic and diverse samples with disentangled latent representations.
  • 17. Pose Guided Person Image Generation
  • 18. Trying to paint Modern Art ● Scraped 1500 images from Google images using search terms paintings of faces. ● Augmented the data-set using flipped images. ● All images were resized to 112x112x3. ● DC-GAN was used to generate the images ● 20,000 epochs.
  • 19. Challenges ● The networks try to take successive steps to minimize a non-convex objective and end up in an oscillating process rather than decreasing the underlying true objective. ● The generator can accidentally start to produce several copies of exactly the same image. ● GANs can sometimes be far-sighted and fail to differentiate the number of particular objects that should occur at a location. ● GANs sometime are not capable of differentiating between front and back view.
  • 20. Future Work with GAN ● Find effective solutions to challenges, different cost functions that ensure Nash equilibrium. ● Drug discovery and potential medical applications. ● Application in NLP, especially language modelling. ● Speech generation. ● Cataloging and Image based search.
  • 21. Citations: 1.Generative Adversarial Nets. Ian J. Goodfellow , Jean Pouget-Abadie , Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair , Aaron Courville, Yoshua Bengio, University of Montreal, NeuralIPS, 2014. 2. GAN — What is Generative Adversary Networks GAN? Jonathan Hui. 06-2018 3. GAN — Some cool applications of GANs. Jonathan Hui. 06-2018 4.Generative Adversarial Networks (GANs) — A Beginner’s Guide. Owen Carey. 2018 5. DCGAN: Generate the images with Deep Convolutional GAN. Keisuke Umezawa. 2018 6. https://github.com/eriklindernoren/Keras-GAN