generative adversarial networks - deep learning

GENERATIVE ADVERSARIAL NETWORKS 11785- Introduction to Deep Learning AKSHAT GUPTA KUSHAL SAHARAN

Upload: others

Post on 31-Oct-2021

10 views

Category:

Documents

1 download

Report

Download

Embed Size (px):

TRANSCRIPT

GENERATIVE ADVERSARIAL NETWORKS

11785- Introduction to Deep Learning

AKSHAT GUPTAKUSHAL SAHARAN

Page 2: GENERATIVE ADVERSARIAL NETWORKS - Deep Learning

–Yann LeCun

“This (GANS), and the variations that are now being proposed is the most interesting idea in the last 10

years in ML, in my opinion”

Page 3: GENERATIVE ADVERSARIAL NETWORKS - Deep Learning

Video: https://www.youtube.com/watch?v=QiiSAvKJIHo

https://www.youtube.com/watch?v=QiiSAvKJIHo

WHAT ARE GANS?

Generative Adversarial Networks

WHAT ARE GANS?

Generative Adversarial Networks

Generative ModelsWe try to learn the underlying the distribution

from which our dataset comes from.Eg: Variational AutoEncoders (VAE)

WHAT ARE GANS?

Generative Adversarial Networks

Generative ModelsWe try to learn the underlying the distribution

from which our dataset comes from.Eg: Variational AutoEncoders (VAE)

Encoderx ~ (training set) P(z) Decoder

WHAT ARE GANS?

Generative Adversarial Networks

Generative ModelsWe try to learn the underlying the distribution

from which our dataset comes from.Eg: Variational AutoEncoders (VAE)

Adversarial TrainingGANS are made up of two competing networks (adversaries)

that are trying beat each other.

WHAT ARE GANS?

Generative Adversarial Networks

Generative ModelsWe try to learn the underlying the distribution

from which our dataset comes from.Eg: Variational AutoEncoders (VAE)

Adversarial TrainingGANS are made up of two competing networks (adversaries)

that are trying beat each other.

Neural Networks

Page 9: GENERATIVE ADVERSARIAL NETWORKS - Deep Learning

WHAT ARE GANS?

P(z) Generator Generated Data

Page 10: GENERATIVE ADVERSARIAL NETWORKS - Deep Learning

WHAT ARE GANS?

P(z) Generator Generated Data

Discriminator Real/Fake?

Page 11: GENERATIVE ADVERSARIAL NETWORKS - Deep Learning

WHAT ARE GANS?

P(z) Generator Generated Data

Discriminator Real/Fake?

RealData

Page 12: GENERATIVE ADVERSARIAL NETWORKS - Deep Learning

HOW TO TRAIN A GAN?

Page 13: GENERATIVE ADVERSARIAL NETWORKS - Deep Learning

HOW TO TRAIN A GAN?At t = 0,

GeneratorLatent Vector

GeneratedImage (fake image)

Generated Data

Discriminator Real/Fake?

GivenTraining

Data

(fake data)

(Real data)

Page 14: GENERATIVE ADVERSARIAL NETWORKS - Deep Learning

HOW TO TRAIN A GAN?At t = 0,

GeneratorLatent Vector

GeneratedImage (fake image)

Generated Data

Discriminator Real/Fake?

GivenTraining

Data

(fake data)

(Real data)

BinaryClassifier

Page 15: GENERATIVE ADVERSARIAL NETWORKS - Deep Learning

HOW TO TRAIN A GAN?Which network should I train first?

Page 16: GENERATIVE ADVERSARIAL NETWORKS - Deep Learning

HOW TO TRAIN A GAN?Which network should I train first?

Discriminator!

Page 17: GENERATIVE ADVERSARIAL NETWORKS - Deep Learning

HOW TO TRAIN A GAN?

Which network should I train first?Discriminator!

But with what training data?

Page 18: GENERATIVE ADVERSARIAL NETWORKS - Deep Learning

HOW TO TRAIN A GAN?

Which network should I train first?Discriminator!

But with what training data?The Discriminator is a Binary classifier.The Discriminator has two class - Real and Fake.The data for Real class if already given: THE TRAINING DATAThe data for Fake class? -> generate from the Generator

Page 19: GENERATIVE ADVERSARIAL NETWORKS - Deep Learning

HOW TO TRAIN A GAN?What’s next? -> Train the Generator

But how? What’s our training objective?

Page 20: GENERATIVE ADVERSARIAL NETWORKS - Deep Learning

HOW TO TRAIN A GAN?What’s next? -> Train the Generator

But how? What’s our training objective?Generate images from the Generator

such that they are classified incorrectly by the Discriminator!

Page 21: GENERATIVE ADVERSARIAL NETWORKS - Deep Learning

HOW TO TRAIN A GAN?

Discriminator

Step 1:Train the Discriminator using the current ability

of the Generator.

Page 22: GENERATIVE ADVERSARIAL NETWORKS - Deep Learning

HOW TO TRAIN A GAN?

GeneratorDiscriminator

Step 1:Train the Discriminator using the current ability

of the Generator.

Step 2:Train the Generator

to beatthe Discriminator.

Page 23: GENERATIVE ADVERSARIAL NETWORKS - Deep Learning

HOW TO TRAIN A GAN?

GeneratorDiscriminator

Step 1:Train the Discriminator using the current ability

of the Generator.

Step 2:Train the Generator

to beatthe Discriminator.

Generate images from the Generator such that they are classified incorrectly by the Discriminator!

Page 24: GENERATIVE ADVERSARIAL NETWORKS - Deep Learning

HOW TO TRAIN A GAN?

GeneratorDiscriminator

Step 1:Train the Discriminator using the current ability

of the Generator.

Step 2:Train the Generator

to beatthe Discriminator.

Page 25: GENERATIVE ADVERSARIAL NETWORKS - Deep Learning

MNIST AND FASHION-MNIST

Generative Adversarial Networks (GANs) - Emanuele Sansone · List of recent papers on Generative Adversarial Networks: PAPERs about GANs 20142016 Generative Adversarial Networks ICLR

Computer Vision Perspective Year in Review 2016: Deep ... · Using a Generative Adversarial Network (15 Sep 2016) superresolution generative adversarial network (SRGAN) with a perceptual

Deep Learning for Computer Vision: Generative models and adversarial training (UPC 2016)

GANs in Action: Deep learning with generative adversarial ......welcome Welcome to MEAP for GANs in Action: Deep Learning with Generative Adversarial Networks. GANs are an exciting

A Deep Convolutional Generative Adversarial Networks … · In this paper, we present a semi-supervised learning method that is based on the standard deep convolutional generative

Capsule Architecture as a Discriminator in Generative Adversarial …€¦ · Variational Autoencoder VAE Deep Learning DL Convolutional Neural Network CCN Generative Adversarial

Generative Adversarial Networks (part 2)deeplearning.cs.cmu.edu/document/slides/bstriner_gans_part_2.pdf · Unrolled Generative Adversarial Networks Unrolled Generative Adversarial

Semi-Supervised Generative Adversarial Hashing for Image Retrievalopenaccess.thecvf.com › ...Wang_Semi-Supervised_Generative_Adver… · Semi-Supervised Generative Adversarial Hashing

Hammad A. Ayyubi - cseweb.ucsd.educseweb.ucsd.edu/~dasgupta/254-deep-ul/hammad.pdf · Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Network Alec

EmotiGAN: Emoji Art using Generative Adversarial Networkscs229.stanford.edu/proj2017/final-reports/5244346.pdfA. Generative Adversarial Networks A Generative Adversarial Network[4]

Geometry-Consistent Generative Adversarial Networks for ...openaccess.thecvf.com/content_CVPR_2019/papers/Fu_Geometry-Consistent... · Geometry-Consistent Generative Adversarial Networks

Generative Adversarial Nets: Applications and Extensionsice.dlut.edu.cn/valse2018/ppt/Generative... · Generative Adversarial Nets: Applications and Extensions Wangmeng Zuo Vision

Deep Generative Image Models using a Laplacian …papers.nips.cc/paper/5773-deep-generative-image-models...Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks

Lecture 7: Generative Adversarial Networks · UVA DEEP LEARNING COURSE –EFSTRATIOS GAVVES GENERATIVE ADVERSARIAL NETWORKS - 25 o𝐽(𝐷)=−1 2 𝔼𝑥~ 𝑑 𝑡 log𝐷 −1

Generative Adversarial Networks for Simulation · Generative Adversarial Networks for Simulation! @wondermicky " [email protected] # mickypaganini.github.io Michela Paganini

DAGAN: Deep De-Aliasing Generative Adversarial Networks ... · conditional Generative Adversarial Networks-based model (DAGAN)-based model is proposed to reconstruct CS-MRI. In our

Deep Generative Image Models using a Laplacian Pyramid ...sudeshna/courses/DL18/gan-applications-slides.pdfGenerative Adversarial Network Deep Generative Image Models using a Laplacian

Generative adversarial networks - University Of Illinoisslazebni.cs.illinois.edu/fall18/lec13_gan.pdfconvolutional generative adversarial networks, ICLR 2016 Four transposed convolution

Deep Semantic Hashing with Generative Adversarial … generative adversarial networks (GANs), which leverages largely unlabeled and limited labeled training data ... state-of-the-art

10. Generative Adversarial Networks EE-559 { Deep learningAdvances in generative models that can sample but not estimate ... { Deep learning / 10. Generative Adversarial Networks 18

Generative Adversarial Networks (GANs) - Ian Goodfellotions. Meanwhile, deep convolutional generative adversarial networks (GANs) have begun to gen-erate highly compelling images of

ESRGAN: Enhanced Super-Resolution Generative Adversarial ...openaccess.thecvf.com/content_ECCVW_2018/papers/11133/Wang_ESRGAN... · ESRGAN: EnhancedSuper-Resolution Generative Adversarial

Lecture 9: Unsupervised, Generative & Adversarial Networks · PDF fileuva deep learning course –efstratios gavves unsupervised, generative & adversarial

Evolutionary Generative Adversarial Networks · Generative adversarial networks (GAN) provides an excel-lent framework for learning deep generative models, which aim to capture probability

Generative adversarial networks

Deep generative models of natural imagesVariational autoencoders Generative adversarial networks Generative moment matching networks Evaluating generative models Outline 1 Motivation

Deep Generative Models: GANs and VAE · Deep convolutional generative adversarial networks Auxiliary classifier GANs Odena, A., Olah, C., & Shlens, J. (2016). Conditional image synthesis

Generative adversarial networks...Generative adversarial nets. NeurIPS. Longer version Goodfellow, (2016). NIPS 2016 Tutorial: Generative Adversarial Networks. Extra Radford et al,

AnomiGAN: Generative Adversarial Networks forpsb.stanford.edu/psb-online/proceedings/psb20/Bae.pdf2.4. Generative Adversarial Networks GANs25 are designed to complement other generative

Recurrent Generative Adversarial Networks for Compressive ...on-demand.gputechconf.com/.../s8197-recurrent-generative-adversarial-neural-networks...Xing, and John Pauly, ``Deep generative

Lecture 19: Generative Adversarial Networksrgrosse/courses/csc321_2018/readings/L19 GANs.pdfLecture 19: Generative Adversarial Networks Roger Grosse 1 Introduction Generative modeling

1 CAGFuzz: Coverage-Guided Adversarial Generative Fuzzing Testing of Deep Learning Systems · 2019-11-20 · 1 CAGFuzz: Coverage-Guided Adversarial Generative Fuzzing Testing of Deep

Triple Generative Adversarial Netspapers.nips.cc/paper/6997-triple-generative-adversarial-nets.pdf · the labels. To address the problems, we present triple generative adversarial

Generative Adversarial Networkstat.snu.ac.kr/mcp/Lecture10_GAN.pdf · 2019-11-11 · Generative Adversarial Network Generative adversarial network: Setup Let y = 1 if the data is

Generative Adversarial Networks (GANs) - Sciencesconf.org · Generative Adversarial Networks (GANs) Anirban Mukhopadhyay TU Darmstadt, Germany. Introduction Generative vs. Discriminative