Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks

• DOI: 10.48550/arxiv.1611.06430
• Publication Date: 2016-01-01
• Authors: Emily Denton; Sam Gross; Rob Fergus
• Keywords: Discriminator; Pascal (unit); Supervised Learning

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 generator whose task is fill in the hole, surrounding pixels. The in-painted then discriminator network that judges if they real (unaltered training images) or not. This acts as regularizer standard supervised of discriminator. Using our we able directly train large VGG-style networks fashion. evaluate STL-10 and PASCAL datasets, where obtains performance comparable superior existing methods.