4.8 Article

A Review of Generalized Zero-Shot Learning Methods

出版社

IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2022.3191696

关键词

Semantics; Visualization; Training; Deep learning; Feature extraction; Data models; Computational modeling; Generalized zero shot learning; deep learning; semantic embedding; generative adversarial networks; variational auto-encoders

向作者/读者索取更多资源

Generalized zero-shot learning (GZSL) trains a model to classify data samples when some output classes are unknown. Semantic information of seen and unseen classes is used to bridge the gap between them. This review paper provides an overview, discusses categorization and representative methods, benchmark datasets, applications, and research gaps of GZSL.
Generalized zero-shot learning (GZSL) aims to train a model for classifying data samples under the condition that some output classes are unknown during supervised learning. To address this challenging task, GZSL leverages semantic information of the seen (source) and unseen (target) classes to bridge the gap between both seen and unseen classes. Since its introduction, many GZSL models have been formulated. In this review paper, we present a comprehensive review on GZSL. First, we provide an overview of GZSL including the problems and challenges. Then, we introduce a hierarchical categorization for the GZSL methods and discuss the representative methods in each category. In addition, we discuss the available benchmark data sets and applications of GZSL, along with a discussion on the research gaps and directions for future investigations.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.8
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据