An Zhao, Mingyu Ding, Zhiwu Lu, Tao Xiang, Yulei Niu...
TL;DR本文提出一种新的面向领域自适应少样本学习(DA-FSL)的解决方案,即基于领域对抗性原型网络(DAPN),该模型通过显式增强源/目标每类别的区分性在域自适应特征嵌入学习之前,以实现全局领域分布对齐,同时保持源/目标每类别的差异性从而提高 FSL 的性能。实验表明,DAPN 模型优于现有的 FSL 和 DA 模型及其简单组合。
Abstract
Existing few-shot learning (FSL) methods make the implicit assumption that the few target class samples are from the same domain as the source class samples. However, in practice this assumption is often invalid -- the target classes could come from a different domain. This poses an ad