A Self-Training Method for Semi-Supervised GANs
This work addresses semi-supervised learning tasks for machine learning practitioners, but it is incremental as it combines existing ideas of self-training and GANs.
The paper tackles the problem of semi-supervised learning by making GANs self-trainable to leverage their infinite data generation potential, resulting in improvements with even simple self-training and a more complex scheme that performs at least as well with less data augmentation.
Since the creation of Generative Adversarial Networks (GANs), much work has been done to improve their training stability, their generated image quality, their range of application but nearly none of them explored their self-training potential. Self-training has been used before the advent of deep learning in order to allow training on limited labelled training data and has shown impressive results in semi-supervised learning. In this work, we combine these two ideas and make GANs self-trainable for semi-supervised learning tasks by exploiting their infinite data generation potential. Results show that using even the simplest form of self-training yields an improvement. We also show results for a more complex self-training scheme that performs at least as well as the basic self-training scheme but with significantly less data augmentation.