Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks
It addresses semi-supervised learning for image classification, offering a simple approach that is incremental over existing methods.
The paper tackles semi-supervised learning for images by using in-painting with adversarial loss as a regularizer, achieving performance comparable or superior to existing methods on STL-10 and PASCAL datasets.
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.