Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks (2015-11-19T00:00:00.000000Z)

TL;DR

This work introduces a class of CNNs called deep convolutional generative adversarial networks (DCGANs), that have certain architectural constraints, and demonstrates that they are a strong candidate for unsupervised learning.

Abstract

In recent years, supervised learning with convolutional networks (CNNs) has seen huge adoption in computer vision applications. Comparatively, unsupervised learning with CNNs has received less attention. In this work we hope to help bridge the gap between the success of CNNs for supervised learning and unsupervised learning. We introduce a class of CNNs called deep convolutional generative adversarial networks (DCGANs), that have certain architectural constraints, and demonstrate that they are a strong candidate for unsupervised learning. Training on various image datasets, we show convincing evidence that our deep convolutional adversarial pair learns a hierarchy of representations from object parts to scenes in both the generator and discriminator. Additionally, we use the learned features for novel tasks - demonstrating their applicability as general image representations.

Authors

Soumith Chintala

5 papers

Alec Radford

12 papers

Luke Metz

2 papers

TL;DR

Abstract

Authors

References45 items

Unrolled Generative Adversarial Networks

Improved Techniques for Training GANs

A note on the evaluation of generative models

Dreaming More Data: Class-dependent Distributions over Diffeomorphisms for Learned Data Augmentation

Train faster, generalize better: Stability of stochastic gradient descent

Semi-supervised Learning with Ladder Networks

Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks

LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop

Stacked What-Where Auto-encoders

Empirical Evaluation of Rectified Activations in Convolutional Network

Deep Unsupervised Learning using Nonequilibrium Thermodynamics

DRAW: A Recurrent Neural Network For Image Generation

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Adam: A Method for Stochastic Optimization

Striving for Simplicity: The All Convolutional Net

Learning to Generate Chairs, Tables and Cars with Convolutional Networks

Learning to generate chairs with convolutional neural networks

Understanding Locally Competitive Networks

Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks

Generative Adversarial Nets

Auto-Encoding Variational Bayes

Visualizing and Understanding Convolutional Networks

Distributed Representations of Words and Phrases and their Compositionality

Maxout Networks

Random Search for Hyper-Parameter Optimization

Selecting Receptive Fields in Deep Networks

Rectified Linear Units Improve Restricted Boltzmann Machines

Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion

ImageNet: A large-scale hierarchical image database

Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations

Scene Completion Using Millions of Photographs

Example-Based Super-Resolution

A Parametric Texture Model Based on Joint Statistics of Complex Wavelet Coefficients

Texture synthesis by non-parametric sampling

GENERATIVE ADVERSARIAL NETS

Inceptionism: Going Deeper into Neural Networks

Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434

Under review as a conference paper at ICLR 2016

Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop

Under Review as a Conference Paper at Iclr 2016 Predicting Distributions with Linearizing Belief Networks

Rectifier Nonlinearities Improve Neural Network Acoustic Models

Learning Feature Representations with K-Means

Reading Digits in Natural Images with Unsupervised Feature Learning

Training Invariant Support Vector Machines using Selective Sampling

Ieee Transactions on Pattern Analysis and Machine Intelligence 1 Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names