Autoencoding Beyond Pixels Using a Learned Similarity Metric

Size: px
Start display at page:

Download "Autoencoding Beyond Pixels Using a Learned Similarity Metric"

Transcription

1 Autoencoding Beyond Pixels Using a Learned Similarity Metric International Conference on Machine Learning, 2016 Anders Boesen Lindbo Larsen, Hugo Larochelle, Søren Kaae Sønderby, Ole Winther Technical University of Denmark, University of Copenhagen, Twitter 16 December 2016 Presented by: Kevin Liang

2 Introduction Deep models have scored impressive successes for discriminative models on large and diverse datasets. However, generative models still present some problems. Variational Autoencoder (VAE) generated faces

3 Current Practice: Pixel-wise Similarity Metrics Many unsupervised learning methods (eg Variational Autoencoders) evaluate performance by comparing reconstruction with the original input. Common Metric: Pixel-wise squared error Problem: Humans do not perceive images element-wise

4 Proposed: Feature-wise Similarity Metric Use higher-level and sufficiently invariant representations of images for comparison, and then learn a function for similarity measure Propose jointly training a Variational Autoencoder (VAE) and a Generative Adversarial Network (GAN) VAE Decoder and GAN Generator shared GAN discriminator is the feature-similarity metric

5 Variational Autoencoder (VAE) Two networks: Encoder and Decoder z Enc(x) = q(z x), x Dec(z) = p(x z) (1) Regularize with a prior over latent distribution p(z) Typically: z N (0, I) Loss to minimize: with L VAE = E q(z x) [ log p(x z)p(z) ] q(z x) = L pixel llike + L prior (2) L pixel llike = E q(z x)[log p(x z)] (3) L prior = D KL (q(z x) p(z)) (4)

6 Generative Adversarial Network (GAN) Two networks: Generator and Discriminator x Gen(z), y = Dis(x) [0, 1] (5) Loss to maximize/minimize wrt Dis/Gen: L GAN = log(dis(x)) + log(1 Dis(Gen(z))) (6) with x being a training sample and z p(z)

7 VAE/GAN In order to properly distinguish generated images from real ones, GAN discriminators must implicitly learn a rich similarity metric. Let Dis l (x) be the hidden representation of lth layer of the discriminator: where x Dec(z) p(dis l (x) z) = N (Dis l (x) Dis l ( x), I) (7) Replace the pixel-wise error with a feature-based one from the discriminator: L Dis l llike = E q(z x)[log p(dis l (x) z)] (8)

8 VAE/GAN Loss VAE/GAN Loss: L = L prior + L Dis l llike + L GAN (9) L Dis l llike : Content Error L GAN : Style error Decoder and Generator share parameters

9 Practical Considerations Limiting error signals to relevant networks Dis should not try to minimize L Dis l llike Do not backpropagate the error signal from L GAN to Enc. Weighting VAE vs GAN Balance reconstruction with fooling the discriminator when training Dec θ Dec + θdec (γl Dis l llike L GAN) (10) Discriminating based on samples from p(z) and q(z x) In addition to exposing the discriminator to the usual fake and real data, encode the real data and add reconstructions L GAN = log(dis(x)) + log(1 Dis(Dec(z))) + log(1 Dis(Dec(Enc(x)))) (11)

10 Summary/Algorithm

11 Models Being Compared 4 Models, all with the same architectures for the sake of parity VAE: Vanilla VAE (pixel-wise Gaussian observation model) VAE Disl : VAE with learned feature-wise similarity metric from a GAN VAE/GAN: Similar to VAE Disl, but Dec also optimized wrt L GAN GAN: Vanilla GAN

12 Introduction Samples VAEs and GANs VAE/GAN Experiments

13 Reconstructions Note: GAN is not included, as it is incapable of performing reconstruction

14 Introduction VAEs and GANs VAE/GAN Visual Attribute Vectors - VAE/GAN Experiments

15 Introduction VAEs and GANs Attribute Query - VAE/GAN VAE/GAN Experiments

16 Shortcomings As a method of training a VAE: Train VAE/GAN model, throw away the GAN, and evaluate the remaining VAE using pixel-wise log likelihood Far from competitive with plain VAE models (on the CIFAR-10 datatset) Semi-supervised: Unsupervised pre-training with the VAE/GAN followed by fine-tuning on a small number of labeled examples Does not reach state-of-the-art (Ladder Networks, Stacked What-Where Autoencoders)

GAN and Feature Representation. Hung-yi Lee

GAN and Feature Representation. Hung-yi Lee GAN and Feature Representation Hung-yi Lee Outline Generator (Decoder) Discrimi nator + Encoder GAN+Autoencoder x InfoGAN Encoder z Generator Discrimi (Decoder) x nator scalar Discrimi z Generator x scalar

More information

arxiv: v1 [cs.lg] 31 Dec 2015

arxiv: v1 [cs.lg] 31 Dec 2015 arxiv:1512.09300v1 [cs.lg] 31 Dec 2015 Anders Boesen Lindbo Larsen 1 ABLL@DTU.DK Søren Kaae Sønderby 2 SKAAESONDERBY@GMAIL.DK Ole Winther 1,2 OLWI@DTU.DK 1 Department for Applied Mathematics and Computer

More information

GAN Frontiers/Related Methods

GAN Frontiers/Related Methods GAN Frontiers/Related Methods Improving GAN Training Improved Techniques for Training GANs (Salimans, et. al 2016) CSC 2541 (07/10/2016) Robin Swanson (robin@cs.toronto.edu) Training GANs is Difficult

More information

When Variational Auto-encoders meet Generative Adversarial Networks

When Variational Auto-encoders meet Generative Adversarial Networks When Variational Auto-encoders meet Generative Adversarial Networks Jianbo Chen Billy Fang Cheng Ju 14 December 2016 Abstract Variational auto-encoders are a promising class of generative models. In this

More information

Alternatives to Direct Supervision

Alternatives to Direct Supervision CreativeAI: Deep Learning for Graphics Alternatives to Direct Supervision Niloy Mitra Iasonas Kokkinos Paul Guerrero Nils Thuerey Tobias Ritschel UCL UCL UCL TUM UCL Timetable Theory and Basics State of

More information

Variational Autoencoders. Sargur N. Srihari

Variational Autoencoders. Sargur N. Srihari Variational Autoencoders Sargur N. srihari@cedar.buffalo.edu Topics 1. Generative Model 2. Standard Autoencoder 3. Variational autoencoders (VAE) 2 Generative Model A variational autoencoder (VAE) is a

More information

arxiv: v2 [cs.lg] 17 Dec 2018

arxiv: v2 [cs.lg] 17 Dec 2018 Lu Mi 1 * Macheng Shen 2 * Jingzhao Zhang 2 * 1 MIT CSAIL, 2 MIT LIDS {lumi, macshen, jzhzhang}@mit.edu The authors equally contributed to this work. This report was a part of the class project for 6.867

More information

Deep Generative Models Variational Autoencoders

Deep Generative Models Variational Autoencoders Deep Generative Models Variational Autoencoders Sudeshna Sarkar 5 April 2017 Generative Nets Generative models that represent probability distributions over multiple variables in some way. Directed Generative

More information

GENERATIVE ADVERSARIAL NETWORKS (GAN) Presented by Omer Stein and Moran Rubin

GENERATIVE ADVERSARIAL NETWORKS (GAN) Presented by Omer Stein and Moran Rubin GENERATIVE ADVERSARIAL NETWORKS (GAN) Presented by Omer Stein and Moran Rubin GENERATIVE MODEL Given a training dataset, x, try to estimate the distribution, Pdata(x) Explicitly or Implicitly (GAN) Explicitly

More information

Unsupervised Learning

Unsupervised Learning Deep Learning for Graphics Unsupervised Learning Niloy Mitra Iasonas Kokkinos Paul Guerrero Vladimir Kim Kostas Rematas Tobias Ritschel UCL UCL/Facebook UCL Adobe Research U Washington UCL Timetable Niloy

More information

Adversarially Learned Inference

Adversarially Learned Inference Institut des algorithmes d apprentissage de Montréal Adversarially Learned Inference Aaron Courville CIFAR Fellow Université de Montréal Joint work with: Vincent Dumoulin, Ishmael Belghazi, Olivier Mastropietro,

More information

Extracting and Composing Robust Features with Denoising Autoencoders

Extracting and Composing Robust Features with Denoising Autoencoders Presenter: Alexander Truong March 16, 2017 Extracting and Composing Robust Features with Denoising Autoencoders Pascal Vincent, Hugo Larochelle, Yoshua Bengio, Pierre-Antoine Manzagol 1 Outline Introduction

More information

19: Inference and learning in Deep Learning

19: Inference and learning in Deep Learning 10-708: Probabilistic Graphical Models 10-708, Spring 2017 19: Inference and learning in Deep Learning Lecturer: Zhiting Hu Scribes: Akash Umakantha, Ryan Williamson 1 Classes of Deep Generative Models

More information

Implicit generative models: dual vs. primal approaches

Implicit generative models: dual vs. primal approaches Implicit generative models: dual vs. primal approaches Ilya Tolstikhin MPI for Intelligent Systems ilya@tue.mpg.de Machine Learning Summer School 2017 Tübingen, Germany Contents 1. Unsupervised generative

More information

(University Improving of Montreal) Generative Adversarial Networks with Denoising Feature Matching / 17

(University Improving of Montreal) Generative Adversarial Networks with Denoising Feature Matching / 17 Improving Generative Adversarial Networks with Denoising Feature Matching David Warde-Farley 1 Yoshua Bengio 1 1 University of Montreal, ICLR,2017 Presenter: Bargav Jayaraman Outline 1 Introduction 2 Background

More information

arxiv: v1 [cs.lg] 10 Nov 2016

arxiv: v1 [cs.lg] 10 Nov 2016 Disentangling factors of variation in deep representations using adversarial training arxiv:1611.03383v1 [cs.lg] 10 Nov 2016 Michael Mathieu, Junbo Zhao, Pablo Sprechmann, Aditya Ramesh, Yann LeCun 719

More information

Lecture 19: Generative Adversarial Networks

Lecture 19: Generative Adversarial Networks Lecture 19: Generative Adversarial Networks Roger Grosse 1 Introduction Generative modeling is a type of machine learning where the aim is to model the distribution that a given set of data (e.g. images,

More information

Bidirectional GAN. Adversarially Learned Inference (ICLR 2017) Adversarial Feature Learning (ICLR 2017)

Bidirectional GAN. Adversarially Learned Inference (ICLR 2017) Adversarial Feature Learning (ICLR 2017) Bidirectional GAN Adversarially Learned Inference (ICLR 2017) V. Dumoulin 1, I. Belghazi 1, B. Poole 2, O. Mastropietro 1, A. Lamb 1, M. Arjovsky 3 and A. Courville 1 1 Universite de Montreal & 2 Stanford

More information

Deep generative models of natural images

Deep generative models of natural images Spring 2016 1 Motivation 2 3 Variational autoencoders Generative adversarial networks Generative moment matching networks Evaluating generative models 4 Outline 1 Motivation 2 3 Variational autoencoders

More information

Auto-Encoding Variational Bayes

Auto-Encoding Variational Bayes Auto-Encoding Variational Bayes Diederik P (Durk) Kingma, Max Welling University of Amsterdam Ph.D. Candidate, advised by Max Durk Kingma D.P. Kingma Max Welling Problem class Directed graphical model:

More information

Autoencoders. Stephen Scott. Introduction. Basic Idea. Stacked AE. Denoising AE. Sparse AE. Contractive AE. Variational AE GAN.

Autoencoders. Stephen Scott. Introduction. Basic Idea. Stacked AE. Denoising AE. Sparse AE. Contractive AE. Variational AE GAN. Stacked Denoising Sparse Variational (Adapted from Paul Quint and Ian Goodfellow) Stacked Denoising Sparse Variational Autoencoding is training a network to replicate its input to its output Applications:

More information

Autoencoder. Representation learning (related to dictionary learning) Both the input and the output are x

Autoencoder. Representation learning (related to dictionary learning) Both the input and the output are x Deep Learning 4 Autoencoder, Attention (spatial transformer), Multi-modal learning, Neural Turing Machine, Memory Networks, Generative Adversarial Net Jian Li IIIS, Tsinghua Autoencoder Autoencoder Unsupervised

More information

Model Generalization and the Bias-Variance Trade-Off

Model Generalization and the Bias-Variance Trade-Off Charu C. Aggarwal IBM T J Watson Research Center Yorktown Heights, NY Model Generalization and the Bias-Variance Trade-Off Neural Networks and Deep Learning, Springer, 2018 Chapter 4, Section 4.1-4.2 What

More information

Neural Networks for Machine Learning. Lecture 15a From Principal Components Analysis to Autoencoders

Neural Networks for Machine Learning. Lecture 15a From Principal Components Analysis to Autoencoders Neural Networks for Machine Learning Lecture 15a From Principal Components Analysis to Autoencoders Geoffrey Hinton Nitish Srivastava, Kevin Swersky Tijmen Tieleman Abdel-rahman Mohamed Principal Components

More information

Generating Images with Perceptual Similarity Metrics based on Deep Networks

Generating Images with Perceptual Similarity Metrics based on Deep Networks Generating Images with Perceptual Similarity Metrics based on Deep Networks Alexey Dosovitskiy and Thomas Brox University of Freiburg {dosovits, brox}@cs.uni-freiburg.de Abstract We propose a class of

More information

Lecture 21 : A Hybrid: Deep Learning and Graphical Models

Lecture 21 : A Hybrid: Deep Learning and Graphical Models 10-708: Probabilistic Graphical Models, Spring 2018 Lecture 21 : A Hybrid: Deep Learning and Graphical Models Lecturer: Kayhan Batmanghelich Scribes: Paul Liang, Anirudha Rayasam 1 Introduction and Motivation

More information

Autoencoders, denoising autoencoders, and learning deep networks

Autoencoders, denoising autoencoders, and learning deep networks 4 th CiFAR Summer School on Learning and Vision in Biology and Engineering Toronto, August 5-9 2008 Autoencoders, denoising autoencoders, and learning deep networks Part II joint work with Hugo Larochelle,

More information

arxiv: v1 [cs.lg] 28 Feb 2017

arxiv: v1 [cs.lg] 28 Feb 2017 Shengjia Zhao 1 Jiaming Song 1 Stefano Ermon 1 arxiv:1702.08658v1 cs.lg] 28 Feb 2017 Abstract We propose a new family of optimization criteria for variational auto-encoding models, generalizing the standard

More information

Auto-encoder with Adversarially Regularized Latent Variables

Auto-encoder with Adversarially Regularized Latent Variables Information Engineering Express International Institute of Applied Informatics 2017, Vol.3, No.3, P.11 20 Auto-encoder with Adversarially Regularized Latent Variables for Semi-Supervised Learning Ryosuke

More information

Denoising Adversarial Autoencoders

Denoising Adversarial Autoencoders Denoising Adversarial Autoencoders Antonia Creswell BICV Imperial College London Anil Anthony Bharath BICV Imperial College London Email: ac2211@ic.ac.uk arxiv:1703.01220v4 [cs.cv] 4 Jan 2018 Abstract

More information

An Empirical Evaluation of Deep Architectures on Problems with Many Factors of Variation

An Empirical Evaluation of Deep Architectures on Problems with Many Factors of Variation An Empirical Evaluation of Deep Architectures on Problems with Many Factors of Variation Hugo Larochelle, Dumitru Erhan, Aaron Courville, James Bergstra, and Yoshua Bengio Université de Montréal 13/06/2007

More information

Lab meeting (Paper review session) Stacked Generative Adversarial Networks

Lab meeting (Paper review session) Stacked Generative Adversarial Networks Lab meeting (Paper review session) Stacked Generative Adversarial Networks 2017. 02. 01. Saehoon Kim (Ph. D. candidate) Machine Learning Group Papers to be covered Stacked Generative Adversarial Networks

More information

Neural Networks: promises of current research

Neural Networks: promises of current research April 2008 www.apstat.com Current research on deep architectures A few labs are currently researching deep neural network training: Geoffrey Hinton s lab at U.Toronto Yann LeCun s lab at NYU Our LISA lab

More information

Introduction to Generative Adversarial Networks

Introduction to Generative Adversarial Networks Introduction to Generative Adversarial Networks Luke de Oliveira Vai Technologies Lawrence Berkeley National Laboratory @lukede0 @lukedeo lukedeo@vaitech.io https://ldo.io 1 Outline Why Generative Modeling?

More information

Auxiliary Deep Generative Models

Auxiliary Deep Generative Models Downloaded from orbit.dtu.dk on: Dec 12, 2018 Auxiliary Deep Generative Models Maaløe, Lars; Sønderby, Casper Kaae; Sønderby, Søren Kaae; Winther, Ole Published in: Proceedings of the 33rd International

More information

JOINT MULTIMODAL LEARNING WITH DEEP GENERA-

JOINT MULTIMODAL LEARNING WITH DEEP GENERA- JOINT MULTIMODAL LEARNING WITH DEEP GENERA- TIVE MODELS Masahiro Suzuki, Kotaro Nakayama, Yutaka Matsuo The University of Tokyo Bunkyo-ku, Tokyo, Japan {masa,k-nakayama,matsuo}@weblab.t.u-tokyo.ac.jp ABSTRACT

More information

arxiv: v2 [stat.ml] 21 Oct 2017

arxiv: v2 [stat.ml] 21 Oct 2017 Variational Approaches for Auto-Encoding Generative Adversarial Networks arxiv:1706.04987v2 stat.ml] 21 Oct 2017 Mihaela Rosca Balaji Lakshminarayanan David Warde-Farley Shakir Mohamed DeepMind {mihaelacr,balajiln,dwf,shakir}@google.com

More information

Toward better reconstruction of style images with GANs

Toward better reconstruction of style images with GANs Toward better reconstruction of style images with GANs Alexander Lorbert, Nir Ben-Zvi, Arridhana Ciptadi, Eduard Oks, Ambrish Tyagi Amazon Lab126 [lorbert,nirbenz,ciptadia,oksed,ambrisht]@amazon.com ABSTRACT

More information

arxiv: v1 [cs.cv] 4 Apr 2018

arxiv: v1 [cs.cv] 4 Apr 2018 arxiv:1804.01523v1 [cs.cv] 4 Apr 2018 Stochastic Adversarial Video Prediction Alex X. Lee, Richard Zhang, Frederik Ebert, Pieter Abbeel, Chelsea Finn, and Sergey Levine University of California, Berkeley

More information

Stacked Denoising Autoencoders for Face Pose Normalization

Stacked Denoising Autoencoders for Face Pose Normalization Stacked Denoising Autoencoders for Face Pose Normalization Yoonseop Kang 1, Kang-Tae Lee 2,JihyunEun 2, Sung Eun Park 2 and Seungjin Choi 1 1 Department of Computer Science and Engineering Pohang University

More information

Day 3 Lecture 1. Unsupervised Learning

Day 3 Lecture 1. Unsupervised Learning Day 3 Lecture 1 Unsupervised Learning Semi-supervised and transfer learning Myth: you can t do deep learning unless you have a million labelled examples for your problem. Reality You can learn useful representations

More information

Deep Generative Models and a Probabilistic Programming Library

Deep Generative Models and a Probabilistic Programming Library Deep Generative Models and a Probabilistic Programming Library Discriminative (Deep) Learning Learn a (differentiable) function mapping from input to output x f(x; θ) y Gradient back-propagation Generative

More information

Akarsh Pokkunuru EECS Department Contractive Auto-Encoders: Explicit Invariance During Feature Extraction

Akarsh Pokkunuru EECS Department Contractive Auto-Encoders: Explicit Invariance During Feature Extraction Akarsh Pokkunuru EECS Department 03-16-2017 Contractive Auto-Encoders: Explicit Invariance During Feature Extraction 1 AGENDA Introduction to Auto-encoders Types of Auto-encoders Analysis of different

More information

arxiv: v2 [cs.lg] 9 Jun 2017

arxiv: v2 [cs.lg] 9 Jun 2017 Shengjia Zhao 1 Jiaming Song 1 Stefano Ermon 1 arxiv:1702.08396v2 [cs.lg] 9 Jun 2017 Abstract Deep neural networks have been shown to be very successful at learning feature hierarchies in supervised learning

More information

Lab 8 CSC 5930/ Computer Vision

Lab 8 CSC 5930/ Computer Vision Lab 8 CSC 5930/9010 - Computer Vision Description: One way to effectively train a neural network with multiple layers is by training one layer at a time. You can achieve this by training a special type

More information

arxiv: v2 [cs.lg] 25 May 2016

arxiv: v2 [cs.lg] 25 May 2016 Adversarial Autoencoders Alireza Makhzani University of Toronto makhzani@psi.toronto.edu Jonathon Shlens & Navdeep Jaitly Google Brain {shlens,ndjaitly}@google.com arxiv:1511.05644v2 [cs.lg] 25 May 2016

More information

Variational Autoencoders

Variational Autoencoders red red red red red red red red red red red red red red red red red red red red Tutorial 03/10/2016 Generative modelling Assume that the original dataset is drawn from a distribution P(X ). Attempt to

More information

DOMAIN-ADAPTIVE GENERATIVE ADVERSARIAL NETWORKS FOR SKETCH-TO-PHOTO INVERSION

DOMAIN-ADAPTIVE GENERATIVE ADVERSARIAL NETWORKS FOR SKETCH-TO-PHOTO INVERSION DOMAIN-ADAPTIVE GENERATIVE ADVERSARIAL NETWORKS FOR SKETCH-TO-PHOTO INVERSION Yen-Cheng Liu 1, Wei-Chen Chiu 2, Sheng-De Wang 1, and Yu-Chiang Frank Wang 1 1 Graduate Institute of Electrical Engineering,

More information

DOMAIN-ADAPTIVE GENERATIVE ADVERSARIAL NETWORKS FOR SKETCH-TO-PHOTO INVERSION

DOMAIN-ADAPTIVE GENERATIVE ADVERSARIAL NETWORKS FOR SKETCH-TO-PHOTO INVERSION 2017 IEEE INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING, SEPT. 25 28, 2017, TOKYO, JAPAN DOMAIN-ADAPTIVE GENERATIVE ADVERSARIAL NETWORKS FOR SKETCH-TO-PHOTO INVERSION Yen-Cheng Liu 1,

More information

Semi-Amortized Variational Autoencoders

Semi-Amortized Variational Autoencoders Semi-Amortized Variational Autoencoders Yoon Kim Sam Wiseman Andrew Miller David Sontag Alexander Rush Code: https://github.com/harvardnlp/sa-vae Background: Variational Autoencoders (VAE) (Kingma et al.

More information

Generative Models in Deep Learning. Sargur N. Srihari

Generative Models in Deep Learning. Sargur N. Srihari Generative Models in Deep Learning Sargur N. Srihari srihari@cedar.buffalo.edu 1 Topics 1. Need for Probabilities in Machine Learning 2. Representations 1. Generative and Discriminative Models 2. Directed/Undirected

More information

arxiv: v1 [cs.lg] 22 Sep 2016

arxiv: v1 [cs.lg] 22 Sep 2016 NEURAL PHOTO EDITING WITH INTROSPECTIVE AD- VERSARIAL NETWORKS Andrew Brock, Theodore Lim,& J.M. Ritchie School of Engineering and Physical Sciences Heriot-Watt University Edinburgh, UK {ajb5, t.lim, j.m.ritchie}@hw.ac.uk

More information

Tutorial on Keras CAP ADVANCED COMPUTER VISION SPRING 2018 KISHAN S ATHREY

Tutorial on Keras CAP ADVANCED COMPUTER VISION SPRING 2018 KISHAN S ATHREY Tutorial on Keras CAP 6412 - ADVANCED COMPUTER VISION SPRING 2018 KISHAN S ATHREY Deep learning packages TensorFlow Google PyTorch Facebook AI research Keras Francois Chollet (now at Google) Chainer Company

More information

arxiv: v1 [cs.cv] 24 Apr 2018

arxiv: v1 [cs.cv] 24 Apr 2018 Mask-aware Photorealistic Face Attribute Manipulation Ruoqi Sun 1, Chen Huang 2, Jianping Shi 3, Lizhuang Ma 1 1 Shanghai Jiao Tong University 2 Carnegie Mellon University 3 Beijing Sensetime Tech. Dev.

More information

Generative Adversarial Networks (GANs)

Generative Adversarial Networks (GANs) Generative Adversarial Networks (GANs) Hossein Azizpour Most of the slides are courtesy of Dr. Ian Goodfellow (Research Scientist at OpenAI) and from his presentation at NIPS 2016 tutorial Note. I am generally

More information

CSC321: Neural Networks. Lecture 13: Learning without a teacher: Autoencoders and Principal Components Analysis. Geoffrey Hinton

CSC321: Neural Networks. Lecture 13: Learning without a teacher: Autoencoders and Principal Components Analysis. Geoffrey Hinton CSC321: Neural Networks Lecture 13: Learning without a teacher: Autoencoders and Principal Components Analysis Geoffrey Hinton Three problems with backpropagation Where does the supervision come from?

More information

ADVERSARIAL EXAMPLES FOR GENERATIVE MODELS

ADVERSARIAL EXAMPLES FOR GENERATIVE MODELS Under review as a conference paper at ICLR ADVERSARIAL EXAMPLES FOR GENERATIVE MODELS Jernej Kos National University of Singapore Ian Fischer Google Research Dawn Song University of California, Berkeley

More information

GAN Related Works. CVPR 2018 & Selective Works in ICML and NIPS. Zhifei Zhang

GAN Related Works. CVPR 2018 & Selective Works in ICML and NIPS. Zhifei Zhang GAN Related Works CVPR 2018 & Selective Works in ICML and NIPS Zhifei Zhang Generative Adversarial Networks (GANs) 9/12/2018 2 Generative Adversarial Networks (GANs) Feedforward Backpropagation Real? z

More information

Unsupervised Learning of Spatiotemporally Coherent Metrics

Unsupervised Learning of Spatiotemporally Coherent Metrics Unsupervised Learning of Spatiotemporally Coherent Metrics Ross Goroshin, Joan Bruna, Jonathan Tompson, David Eigen, Yann LeCun arxiv 2015. Presented by Jackie Chu Contributions Insight between slow feature

More information

arxiv: v1 [cs.cv] 21 Jan 2018

arxiv: v1 [cs.cv] 21 Jan 2018 ecoupled Learning for Conditional Networks Zhifei Zhang, Yang Song, and Hairong Qi University of Tennessee {zzhang61, ysong18, hqi}@utk.edu arxiv:1801.06790v1 [cs.cv] 21 Jan 2018 Abstract Incorporating

More information

The Multi-Entity Variational Autoencoder

The Multi-Entity Variational Autoencoder The Multi-Entity Variational Autoencoder Charlie Nash 1,2, S. M. Ali Eslami 2, Chris Burgess 2, Irina Higgins 2, Daniel Zoran 2, Theophane Weber 2, Peter Battaglia 2 1 Edinburgh University 2 DeepMind Abstract

More information

Deep Manga Colorization with Color Style Extraction by Conditional Adversarially Learned Inference

Deep Manga Colorization with Color Style Extraction by Conditional Adversarially Learned Inference Information Engineering Express International Institute of Applied Informatics 2017, Vol.3, No.4, P.55-66 Deep Manga Colorization with Color Style Extraction by Conditional Adversarially Learned Inference

More information

Generative Modeling with Convolutional Neural Networks. Denis Dus Data Scientist at InData Labs

Generative Modeling with Convolutional Neural Networks. Denis Dus Data Scientist at InData Labs Generative Modeling with Convolutional Neural Networks Denis Dus Data Scientist at InData Labs What we will discuss 1. 2. 3. 4. Discriminative vs Generative modeling Convolutional Neural Networks How to

More information

X-GAN: Improving Generative Adversarial Networks with ConveX Combinations

X-GAN: Improving Generative Adversarial Networks with ConveX Combinations X-GAN: Improving Generative Adversarial Networks with ConveX Combinations Oliver Blum, Biagio Brattoli, and Björn Ommer Heidelberg University, HCI / IWR, Germany o.blum90@gmail.com biagio.brattoli@iwr.uni-heidelberg.de

More information

Learning to generate with adversarial networks

Learning to generate with adversarial networks Learning to generate with adversarial networks Gilles Louppe June 27, 2016 Problem statement Assume training samples D = {x x p data, x X } ; We want a generative model p model that can draw new samples

More information

Deep-Q: Traffic-driven QoS Inference using Deep Generative Network

Deep-Q: Traffic-driven QoS Inference using Deep Generative Network Deep-Q: Traffic-driven QoS Inference using Deep Generative Network Shihan Xiao, Dongdong He, Zhibo Gong Network Technology Lab, Huawei Technologies Co., Ltd., Beijing, China 1 Background What is a QoS

More information

Deep Tracking: Biologically Inspired Tracking with Deep Convolutional Networks

Deep Tracking: Biologically Inspired Tracking with Deep Convolutional Networks Deep Tracking: Biologically Inspired Tracking with Deep Convolutional Networks Si Chen The George Washington University sichen@gwmail.gwu.edu Meera Hahn Emory University mhahn7@emory.edu Mentor: Afshin

More information

Deep Hybrid Discriminative-Generative Models for Semi-Supervised Learning

Deep Hybrid Discriminative-Generative Models for Semi-Supervised Learning Volodymyr Kuleshov 1 Stefano Ermon 1 Abstract We propose a framework for training deep probabilistic models that interpolate between discriminative and generative approaches. Unlike previously proposed

More information

COMP 551 Applied Machine Learning Lecture 16: Deep Learning

COMP 551 Applied Machine Learning Lecture 16: Deep Learning COMP 551 Applied Machine Learning Lecture 16: Deep Learning Instructor: Ryan Lowe (ryan.lowe@cs.mcgill.ca) Slides mostly by: Class web page: www.cs.mcgill.ca/~hvanho2/comp551 Unless otherwise noted, all

More information

Image Restoration Using DNN

Image Restoration Using DNN Image Restoration Using DNN Hila Levi & Eran Amar Images were taken from: http://people.tuebingen.mpg.de/burger/neural_denoising/ Agenda Domain Expertise vs. End-to-End optimization Image Denoising and

More information

Unsupervised Image-to-Image Translation Networks

Unsupervised Image-to-Image Translation Networks Unsupervised Image-to-Image Translation Networks Ming-Yu Liu, Thomas Breuel, Jan Kautz NVIDIA {mingyul,tbreuel,jkautz}@nvidia.com Abstract Unsupervised image-to-image translation aims at learning a joint

More information

Iterative Inference Models

Iterative Inference Models Iterative Inference Models Joseph Marino, Yisong Yue California Institute of Technology {jmarino, yyue}@caltech.edu Stephan Mt Disney Research stephan.mt@disneyresearch.com Abstract Inference models, which

More information

arxiv: v3 [cs.ne] 6 Dec 2016

arxiv: v3 [cs.ne] 6 Dec 2016 Sampling Generative Networks arxiv:1609.04468v3 [cs.ne] 6 Dec 2016 Tom White School of Design Victoria University of Wellington Wellington, New Zealand tom.white@vuw.ac.nz Abstract We introduce several

More information

Introduction to GAN. Generative Adversarial Networks. Junheng(Jeff) Hao

Introduction to GAN. Generative Adversarial Networks. Junheng(Jeff) Hao Introduction to GAN Generative Adversarial Networks Junheng(Jeff) Hao Adversarial Training is the coolest thing since sliced bread. -- Yann LeCun Roadmap 1. Generative Modeling 2. GAN 101: What is GAN?

More information

Deep Feature Interpolation for Image Content Changes

Deep Feature Interpolation for Image Content Changes Deep Feature Interpolation for Image Content Changes by P. Upchurch, J. Gardner, G. Pleiss, R. Pleiss, N. Snavely, K. Bala, K. Weinberger Presenter: Aliya Amirzhanova Master Scientific Computing, Heidelberg

More information

Deep Learning for Visual Manipulation and Synthesis

Deep Learning for Visual Manipulation and Synthesis Deep Learning for Visual Manipulation and Synthesis Jun-Yan Zhu 朱俊彦 UC Berkeley 2017/01/11 @ VALSE What is visual manipulation? Image Editing Program input photo User Input result Desired output: stay

More information

IMPROVING SAMPLING FROM GENERATIVE AUTOENCODERS WITH MARKOV CHAINS

IMPROVING SAMPLING FROM GENERATIVE AUTOENCODERS WITH MARKOV CHAINS IMPROVING SAMPLING FROM GENERATIVE AUTOENCODERS WITH MARKOV CHAINS Antonia Creswell, Kai Arulkumaran & Anil A. Bharath Department of Bioengineering Imperial College London London SW7 2BP, UK {ac2211,ka709,aab01}@ic.ac.uk

More information

arxiv: v2 [cs.cv] 24 Dec 2018

arxiv: v2 [cs.cv] 24 Dec 2018 arxiv:1811.07999v2 [cs.cv] 24 Dec 2018 Computer Science Technical Report Synthetic Lung Nodule 3D Image Generation Using Autoencoders Steve Kommrusch a and Louis-Noël Pouchet a a Dept. of Computer Science,

More information

Generative Adversarial Text to Image Synthesis

Generative Adversarial Text to Image Synthesis Generative Adversarial Text to Image Synthesis Scott Reed, Zeynep Akata, Xinchen Yan, Lajanugen Logeswaran, Bernt Schiele, Honglak Lee Presented by: Jingyao Zhan Contents Introduction Related Work Method

More information

ECE 599/692 Deep Learning. Lecture 12 GAN - Introduction

ECE 599/692 Deep Learning. Lecture 12 GAN - Introduction ECE 599/692 Deep Learning Lecture 12 AN - Introduction Hairong Qi, onzalez Family Professor Electrical Engineering and Computer Science University of Tennessee, Knoxville http://www.eecs.utk.edu/faculty/qi

More information

arxiv: v1 [stat.ml] 3 Apr 2017

arxiv: v1 [stat.ml] 3 Apr 2017 Lars Maaløe 1 Marco Fraccaro 1 Ole Winther 1 arxiv:1704.00637v1 stat.ml] 3 Apr 2017 Abstract Deep generative models trained with large amounts of unlabelled data have proven to be powerful within the domain

More information

Deep Meditations: Controlled navigation of latent space

Deep Meditations: Controlled navigation of latent space Deep Meditations: Controlled navigation of latent space Memo Akten (m.akten@gold.ac.uk) 1, Rebecca Fiebrink (r.fiebrink@gold.ac.uk) 1, and Mick Grierson (m.grierson@arts.ac.uk) 2 1 Department of Computing,

More information

DEEP LEARNING OF COMPRESSED SENSING OPERATORS WITH STRUCTURAL SIMILARITY (SSIM) LOSS

DEEP LEARNING OF COMPRESSED SENSING OPERATORS WITH STRUCTURAL SIMILARITY (SSIM) LOSS DEEP LEARNING OF COMPRESSED SENSING OPERATORS WITH STRUCTURAL SIMILARITY (SSIM) LOSS ABSTRACT Compressed sensing (CS) is a signal processing framework for efficiently reconstructing a signal from a small

More information

Visual Recommender System with Adversarial Generator-Encoder Networks

Visual Recommender System with Adversarial Generator-Encoder Networks Visual Recommender System with Adversarial Generator-Encoder Networks Bowen Yao Stanford University 450 Serra Mall, Stanford, CA 94305 boweny@stanford.edu Yilin Chen Stanford University 450 Serra Mall

More information

arxiv: v1 [stat.ml] 7 Nov 2016

arxiv: v1 [stat.ml] 7 Nov 2016 JOINT MULTIMODAL LEARNING WITH DEEP GENERA- TIVE MODELS Masahiro Suzuki, Kotaro Nakayama, Yutaka Matsuo The University of Tokyo Bunkyo-ku, Tokyo, Japan {masa,k-nakayama,matsuo}@weblab.t.u-tokyo.ac.jp arxiv:1611.01891v1

More information

Flow-GAN: Bridging implicit and prescribed learning in generative models

Flow-GAN: Bridging implicit and prescribed learning in generative models Aditya Grover 1 Manik Dhar 1 Stefano Ermon 1 Abstract Evaluating the performance of generative models for unsupervised learning is inherently challenging due to the lack of welldefined and tractable objectives.

More information

Virtual Adversarial Ladder Networks for Semi-Supervised Learning

Virtual Adversarial Ladder Networks for Semi-Supervised Learning Virtual Adversarial Ladder Networks for Semi-Supervised Learning Saki Shinoda 1, Daniel E. Worrall 2 & Gabriel J. Brostow 2 Computer Science Department University College London United Kingdom 1 saki.shinoda.16@ucl.ac.uk

More information

Deep Learning. Deep Learning. Practical Application Automatically Adding Sounds To Silent Movies

Deep Learning. Deep Learning. Practical Application Automatically Adding Sounds To Silent Movies http://blog.csdn.net/zouxy09/article/details/8775360 Automatic Colorization of Black and White Images Automatically Adding Sounds To Silent Movies Traditionally this was done by hand with human effort

More information

arxiv: v1 [cs.gr] 27 Dec 2018

arxiv: v1 [cs.gr] 27 Dec 2018 Sampling using Neural Networks for colorizing the grayscale images arxiv:1812.10650v1 [cs.gr] 27 Dec 2018 Wonbong Jang Department of Statistics London School of Economics London, WC2A 2AE w.jang@lse.ac.uk

More information

arxiv: v2 [cs.cv] 6 Dec 2017

arxiv: v2 [cs.cv] 6 Dec 2017 Arbitrary Facial Attribute Editing: Only Change What You Want arxiv:1711.10678v2 [cs.cv] 6 Dec 2017 Zhenliang He 1,2 Wangmeng Zuo 4 Meina Kan 1 Shiguang Shan 1,3 Xilin Chen 1 1 Key Lab of Intelligent Information

More information

An Empirical Study of Generative Adversarial Networks for Computer Vision Tasks

An Empirical Study of Generative Adversarial Networks for Computer Vision Tasks An Empirical Study of Generative Adversarial Networks for Computer Vision Tasks Report for Undergraduate Project - CS396A Vinayak Tantia (Roll No: 14805) Guide: Prof Gaurav Sharma CSE, IIT Kanpur, India

More information

ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matching

ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matching ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matching Chunyuan Li 1, Hao Liu 2, Changyou Chen 3, Yunchen Pu 1, Liqun Chen 1, Ricardo Henao 1 and Lawrence Carin 1 1 Duke University

More information

Tutorial Deep Learning : Unsupervised Feature Learning

Tutorial Deep Learning : Unsupervised Feature Learning Tutorial Deep Learning : Unsupervised Feature Learning Joana Frontera-Pons 4th September 2017 - Workshop Dictionary Learning on Manifolds OUTLINE Introduction Representation Learning TensorFlow Examples

More information

COMPARATIVE DEEP LEARNING FOR CONTENT- BASED MEDICAL IMAGE RETRIEVAL

COMPARATIVE DEEP LEARNING FOR CONTENT- BASED MEDICAL IMAGE RETRIEVAL 1 COMPARATIVE DEEP LEARNING FOR CONTENT- BASED MEDICAL IMAGE RETRIEVAL ADITYA SRIRAM DECEMBER 1 st, 2016 Aditya Sriram CS846 Software Engineering for Big Data December 1, 2016 TOPICS 2 Paper Synopsis Content-Based

More information

LEARNING TO INFER ABSTRACT 1 INTRODUCTION. Under review as a conference paper at ICLR Anonymous authors Paper under double-blind review

LEARNING TO INFER ABSTRACT 1 INTRODUCTION. Under review as a conference paper at ICLR Anonymous authors Paper under double-blind review LEARNING TO INFER Anonymous authors Paper under double-blind review ABSTRACT Inference models, which replace an optimization-based inference procedure with a learned model, have been fundamental in advancing

More information

Neural Networks for unsupervised learning From Principal Components Analysis to Autoencoders to semantic hashing

Neural Networks for unsupervised learning From Principal Components Analysis to Autoencoders to semantic hashing Neural Networks for unsupervised learning From Principal Components Analysis to Autoencoders to semantic hashing feature 3 PC 3 Beate Sick Many slides are taken form Hinton s great lecture on NN: https://www.coursera.org/course/neuralnets

More information

Energy Based Models, Restricted Boltzmann Machines and Deep Networks. Jesse Eickholt

Energy Based Models, Restricted Boltzmann Machines and Deep Networks. Jesse Eickholt Energy Based Models, Restricted Boltzmann Machines and Deep Networks Jesse Eickholt ???? Who s heard of Energy Based Models (EBMs) Restricted Boltzmann Machines (RBMs) Deep Belief Networks Auto-encoders

More information

Tackling Over-pruning in Variational Autoencoders

Tackling Over-pruning in Variational Autoencoders Serena Yeung 1 Anitha Kannan 2 Yann Dauphin 2 Li Fei-Fei 1 Abstract Variational autoencoders (VAE) are directed generative models that learn factorial latent variables. As noted by Burda et al. (2015),

More information

Gradient of the lower bound

Gradient of the lower bound Weakly Supervised with Latent PhD advisor: Dr. Ambedkar Dukkipati Department of Computer Science and Automation gaurav.pandey@csa.iisc.ernet.in Objective Given a training set that comprises image and image-level

More information

Machine Learning. Deep Learning. Eric Xing (and Pengtao Xie) , Fall Lecture 8, October 6, Eric CMU,

Machine Learning. Deep Learning. Eric Xing (and Pengtao Xie) , Fall Lecture 8, October 6, Eric CMU, Machine Learning 10-701, Fall 2015 Deep Learning Eric Xing (and Pengtao Xie) Lecture 8, October 6, 2015 Eric Xing @ CMU, 2015 1 A perennial challenge in computer vision: feature engineering SIFT Spin image

More information