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.
|Task||Dataset||Model||Metric name||Metric value||Global rank||Compare|
|Image Classification||STL-10||CC-GAN²||Percentage correct||77.79||# 1|