Gaurav Bhatt, Shivam Chandok, Vineeth N Balasubramanian
TL;DR本文提出了基于产品专家公式和 A UD 模块的零样本和少量样本归纳学习框架,利用来自非数据类的未标记采样来提高任意数量学习的泛化能力,并证明了该模型适用于有限监督场景下的广义零样本模型。
Abstract
A common problem with most zero and few-shot learning approaches is they suffer from bias towards seen classes resulting in sub-optimal performance. Existing efforts aim to utilize unlabeled images from unseen classes (i.e transductive zero-shot) during training to enable