论文标题
克服利用GAN的挑战，以进行几次数据扩展
Overcoming challenges in leveraging GANs for few-shot data augmentation
论文作者
论文摘要
在本文中，我们探讨了基于GAN的少量数据增强用作改善少量分类性能的方法。我们对如何对这种任务进行微调（其中一项是以课堂开采方式）进行微调的探索，以及对这些模型如何表现如何改善少数拍摄分类的严格经验研究。我们确定了与纯粹有监督的制度训练此类生成模型的困难有关的问题，几乎没有例子，以及有关现有作品的评估协议的问题。我们还发现，在这种制度中，分类精度对数据集的类别随机分配方式高度敏感。因此，我们提出了一种半监督的微调方法，作为解决这些问题的更务实的方向。
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.
