Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks

19 Nov 2016Emily DentonSam GrossRob Fergus

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... (read more)

PDF Abstract

Evaluation results from the paper

Task Dataset Model Metric name Metric value Global rank Compare
Image Classification STL-10 CC-GAN² Percentage correct 77.79 # 3