A Biologically Inspired Feature Enhancement Framework for Zero-Shot Learning

no code implementations • 13 May 2020 • Zhongwu Xie, Weipeng Cao, Xi-Zhao Wang, Zhong Ming, Jingjing Zhang, Jiyong Zhang

Most of the Zero-Shot Learning (ZSL) algorithms currently use pre-trained models as their feature extractors, which are usually trained on the ImageNet data set by using deep neural networks.

Zero-Shot Learning