GAN Applications.

Slides:



Advertisements
Similar presentations
Lecture 14 – Neural Networks
Advertisements

Overview of Back Propagation Algorithm
Deep Learning Overview Sources: workshop-tutorial-final.pdf
Generative Adversarial Nets ML Reading Group Xiao Lin Jul
Conditional Generative Adversarial Networks
Convolutional Sequence to Sequence Learning
Generative Adversarial Nets
Generative Adversarial Network (GAN)
Group presentation WANG Yue 13/2/2017.
Convolutional Neural Network
Environment Generation with GANs
Summary of “Efficient Deep Learning for Stereo Matching”
Deep Neural Net Scenery Generation
Automatic Lung Cancer Diagnosis from CT Scans (Week 2)
Classification: Logistic Regression
Adversarial Learning for Neural Dialogue Generation
Photorealistic Image Colourization with Generative Adversarial Nets
Generative Adversarial Networks
CSCI 5922 Neural Networks and Deep Learning Generative Adversarial Networks Mike Mozer Department of Computer Science and Institute of Cognitive Science.
Ying Kin Yu, Kin Hong Wong and Siu Hang Or
Generative adversarial networks (GANs) for edge detection
Shunyuan Zhang Nikhil Malik
Unsupervised Conditional Generation
CS6890 Deep Learning Weizhen Cai
Authors: Jun-Yan Zhu*, Taesun Park*, Phillip Isola, Alexei A. Efros
Presenter: Hajar Emami
Adversarially Tuned Scene Generation
Low Dose CT Image Denoising Using WGAN and Perceptual Loss
Computer Vision James Hays
Convolutional Neural Networks
Wei Liu, Chaofeng Chen and Kwan-Yee K. Wong
CSC 578 Neural Networks and Deep Learning
CellNetQL Image Segmentation without Feature Definition
Object Classification through Deconvolutional Neural Networks
Smart Robots, Drones, IoT
Image recognition: Defense adversarial attacks
Non-Stationary Texture Synthesis by Adversarial Expansion
David Healey BYU Capstone Course 15 Nov 2018
Image to Image Translation using GANs
Neural Networks Geoff Hulten.
Papers 15/08.
Lip movement Synthesis from Text
Coding neural networks: A gentle Introduction to keras
Do GANs actually learn the distribution? Some theory and empirics.
Hein H. Aung Matt Anderson, Advisor Introduction
Recent Advances in Generative Adversarial Networks (GAN)
实习生汇报 ——北邮 张安迪.
CS 2770: Computer Vision Generative Adversarial Networks
Martin Schrimpf & Jon Gauthier MIT BCS Peer Lectures
Video Imagination from a Single Image with Transformation Generation
Course Recap and What’s Next?
TPGAN overview.
Abnormally Detection
Attention for translation
Ch 14. Generative adversarial networks (GANs) for edge detection
U-Net: Convolutional Network for Segmentation
Applications of Capsules
Mandikal Vikram1 and Steffen Wolf2
Hsiao-Yu Chiang Xiaoya Li Ganyu “Bruce” Xu Pinshuo Ye Zhanyuan Zhang
Neural Machine Translation using CNN
Angel A. Cantu, Nami Akazawa Department of Computer Science
Deep screen image crop and enhance
End-to-End Facial Alignment and Recognition
Fig. 2. Examples showing the ability of deep learning to generate realistic fake images. (a) Representative test images from the trained network for generating.
Text-to-speech (TTS) Traditional approaches (before 2016) Neural TTS
CSC 578 Neural Networks and Deep Learning
CRCV REU 2019 Aaron Honculada.
Directional Occlusion with Neural Network
Generative adversarial networks (GANs)
ONNX Training Discussion
Presentation transcript:

GAN Applications

Recap

G D D Two player game 𝓓𝓪𝓽𝓪 z x y = D(G(z)) x y = D(x) G tries to make D(G(z)) near 1 -- “I am not fake” D tries to make D(G(z)) near 0 -- “You are fake” D x y = D(x) 𝓓𝓪𝓽𝓪 D tries to output 1 -- “You are real”

G D G D Update generator z y = D(G(z)) Cost Calculate gradients (backprop) and update parameters Calculate gradients (backprop) and do not update parameters

Calculate gradients (backprop) and update parameters Update discriminator G D z y = D(G(z)) Cost 1 D 𝓓𝓪𝓽𝓪 x y = D(x) Cost 2 D Add Calculate gradients (backprop) and update parameters

G D Conditional GAN z x = G(z | y) y x y = D(x | y) y random vector auxiliary input y input x D y = D(x | y) auxiliary input y

Image to image translation (transformation) Input Output GOAL 𝓓𝓪𝓽𝓪 Aerial map Aerial image From Google Maps Image-to-Image Translation with Conditional Adversarial Networks, Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, and Alexei A. Efros, Berkeley AI Research (BAIR) Laboratory, CVPR 2017

Auxiliary / conditional input Training Generator Auxiliary / conditional input y x G D Noise z

Auxiliary / conditional input Training Generator Auxiliary / conditional input y x G D

Auxiliary / conditional input Training Generator Auxiliary / conditional input y x G D Real or fake?

Training Generator Auxiliary / conditional input x i.e. G(y) G D Backprop D and update G considering this pair to be real. min Auxiliary / conditional input y

Auxiliary / conditional input y Discriminator update x from G i.e. G(y) D Consider this pair to be fake. max Auxiliary / conditional input y

Discriminator update x from G i.e. G(y) x from data D D Consider this pair to be fake. Consider this pair to be real. max max Auxiliary / conditional input y Auxiliary / conditional input y

Auxiliary / conditional input Training Generator Auxiliary / conditional input y x i.e. G(y) G D Backprop D and update G considering this pair to be real. min y

Auxiliary / conditional input Training Generator Auxiliary / conditional input y x i.e. G(y) G D Backprop D and update G considering this pair to be real. G(y) x from data L1( , ) min λ y The generator is tasked to not only fool the discriminator, but also to be near the ground truth Traditional image loss

Generator Architecture y x G D Aerial map Aerial image

Generator Architecture encode decode Essential features Aerial map Aerial image Encoder-decoder architecture

Generator Architecture Essential features Skip connections Aerial map Aerial image U-net Encoder-decoder architecture with skip connections Encoder-decoder architecture O. Ronneberger, P. Fischer, and T. Brox. U-net: Convolutional networks for biomedical image segmentation, 2015.

Input Output Input Output Image-to-Image Translation with Conditional Adversarial Networks, Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, and Alexei A. Efros, CVPR 2017

Image-to-Image Translation with Conditional Adversarial Networks, Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, and Alexei A. Efros, CVPR 2017

Image-to-Image Translation with Conditional Adversarial Networks, Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, and Alexei A. Efros, CVPR 2017