Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks

Remi Denton, Sam Gross, Rob Fergus

11/19/2016

cs.CV

Official code: edenton/cc-gan (13 stars, last commit 2017-04-10).

Abstract

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.

View on arXiv View PDF

Code Implementations(1)

edenton/cc-ganOfficial100%

135LuaNov 4, 20169 years ago

Similar Papers

Improved Techniques for Training GANs

85% match1 repo2.3k2016

Generative Image Inpainting with Segmentation Confusion Adversarial Training and Contrastive Learning

84% match1 repo222023

Inpainting Normal Maps for Lightstage data

83% match2024

Masked Auto-Encoders Meet Generative Adversarial Networks and Beyond

83% match2023

Learning to Impute: A General Framework for Semi-supervised Learning

83% match1 repo62019

Image Fine-grained Inpainting

83% match1 repo2542020

Cite this paper

@article{denton2016semisupervised,
  title  = {Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks},
  author = {Remi Denton and Sam Gross and Rob Fergus},
  year   = {2016},
  eprint = {1611.06430},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1611.06430}
}

Add a badge to your README

Shows whether official code is linked for this paper.

[![Code of Paper](https://codeofpaper.com/badge/1611.06430.svg)](https://codeofpaper.com/paper/1611.06430)