BriefGPT.xyz
Jan, 2021
基于熵的不确定性校准用于广义零样本学习
Entropy-Based Uncertainty Calibration for Generalized Zero-Shot Learning
HTML
PDF
Zhi Chen, Zi Huang, Jingjing Li, Zheng Zhang
TL;DR
提出一种新的框架,利用双重变分自编码器和三元组损失学习区分性潜在特征,并应用基于熵的校准来最小化见和未见类之间重叠区域的不确定性,在六个基准数据集上进行的实验表明,该方法胜过现有的最先进方法。
Abstract
Compared to conventional
zero-shot learning
(ZSL) where recognising unseen classes is the primary or only aim, the goal of generalized
zero-shot learning
(GZSL) is to recognise both seen and unseen classes. Most
→