Overcoming challenges in leveraging GANs for few-shot data augmentation
This addresses challenges in few-shot learning for AI applications, but it is incremental as it builds on existing GAN methods.
The paper tackles the problem of using GANs for few-shot data augmentation to improve classification, finding issues with training and evaluation, and proposes a semi-supervised fine-tuning approach as a solution.
In this paper, we explore the use of GAN-based few-shot data augmentation as a method to improve few-shot classification performance. We perform an exploration into how a GAN can be fine-tuned for such a task (one of which is in a class-incremental manner), as well as a rigorous empirical investigation into how well these models can perform to improve few-shot classification. We identify issues related to the difficulty of training such generative models under a purely supervised regime with very few examples, as well as issues regarding the evaluation protocols of existing works. We also find that in this regime, classification accuracy is highly sensitive to how the classes of the dataset are randomly split. Therefore, we propose a semi-supervised fine-tuning approach as a more pragmatic way forward to address these problems.