EC-GAN: Low-Sample Classification using Semi-Supervised Algorithms and GANs

This paper was accepted to 35th AAAI Conference on Artificial Intelligence (AAAI 2021) which was held in February of 2021. The paper was also selected as a finalist paper for the student abstract track and chosen for a 3-minute thesis presentation competition. The paper is available on ArXiv, and the blog is available on Towards Data Science on Medium. Here are some photos of me (virtually) attending the conference.

Semi-supervised learning has been gaining attention as it allows for performing image analysis tasks such as classification with limited labeled data. Some popular algorithms using Generative Adversarial Networks (GANs) for semi-supervised classification share a single architecture for classification and discrimination. However, this may require a model to converge to a separate data distribution for each task, which may reduce overall performance. While progress in semi-supervised learning has been made, less addressed are small-scale, fully-supervised tasks where even unlabeled data is unavailable and unattainable. We therefore, propose a novel GAN model namely External Classifier GAN (EC-GAN), that utilizes GANs and semi-supervised algorithms to improve classification in fully-supervised regimes. Our method leverages a GAN to generate artificial data used to supplement supervised classification. More specifically, we attach an external classifier, hence the name EC-GAN, to the GAN's generator, as opposed to sharing an architecture with the discriminator. Our experiments demonstrate that EC-GAN's performance is comparable to the shared architecture method, far superior to the standard data augmentation and regularization-based approach, and effective on a small, realistic dataset.