Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Denton, Remi, Gross, Sam, Fergus, Rob
Format: Preprint
Publié: 2016
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914711795138560
author Denton, Remi
Gross, Sam
Fergus, Rob
author_facet Denton, Remi
Gross, Sam
Fergus, Rob
contents We introduce a simple semi-supervised learning approach for images based on in-painting using an adversarial loss. Images with random patches removed are presented to a generator whose task is to fill in the hole, based on the surrounding pixels. The in-painted images are then presented to a discriminator network that judges if they are real (unaltered training images) or not. This task acts as a regularizer for standard supervised training of the discriminator. Using our approach we are able to directly train large VGG-style networks in a semi-supervised fashion. We evaluate on STL-10 and PASCAL datasets, where our approach obtains performance comparable or superior to existing methods.
format Preprint
id arxiv_https___arxiv_org_abs_1611_06430
institution arXiv
publishDate 2016
record_format arxiv
spellingShingle Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks
Denton, Remi
Gross, Sam
Fergus, Rob
Computer Vision and Pattern Recognition
We introduce a simple semi-supervised learning approach for images based on in-painting using an adversarial loss. Images with random patches removed are presented to a generator whose task is to fill in the hole, based on the surrounding pixels. The in-painted images are then presented to a discriminator network that judges if they are real (unaltered training images) or not. This task acts as a regularizer for standard supervised training of the discriminator. Using our approach we are able to directly train large VGG-style networks in a semi-supervised fashion. We evaluate on STL-10 and PASCAL datasets, where our approach obtains performance comparable or superior to existing methods.
title Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/1611.06430