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.
翻译:在本文中,我们探索使用基于GAN的微光数据扩增作为改进微光分类性能的方法。我们探索如何微调GAN,以完成这一任务(其中之一是以等级递增的方式),以及对这些模型在改进微光分类方面能发挥多大作用进行严格的实证调查。我们找出了与在纯粹监督的制度下培训这种基因化模型的困难有关的问题,并举了很少的例子,以及现有工程的评价程序问题。我们还发现,在这个制度下,分类准确性对于数据集的类别如何随机划分非常敏感。因此,我们建议采用半监督的微调方法,作为解决这些问题的更务实的方法。