EC-GAN: Low-Sample Classification using Semi-Supervised Algorithms and GANs
This work addresses the challenge of improving classification accuracy for small-scale, fully-supervised tasks where even unlabeled data is unavailable, which is a practical problem for researchers and practitioners dealing with limited datasets.
The paper proposes External Classifier GAN (EC-GAN) to improve classification performance in fully-supervised, low-sample regimes by generating artificial data to supplement training. EC-GAN achieves performance comparable to shared-architecture methods and significantly outperforms standard data augmentation and regularization-based approaches.
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.