A Review of Generalized Zero-Shot Learning Methods

TL;DR

This paper provides a comprehensive review of generalized zero-shot learning (GZSL), covering its challenges, methods, benchmarks, applications, and future research directions in the field.

Contribution

It offers a hierarchical categorization of GZSL methods and discusses key datasets, applications, and research gaps, serving as a valuable resource for future work.

Findings

Overview of GZSL challenges and problems

Categorization of GZSL methods and representative models

Discussion of benchmarks, applications, and future research directions

Abstract

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. Firstly, 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.