A Review of Generalized Zero-Shot Learning Methods

Farhad Pourpanah; Moloud Abdar; Yuxuan Luo; Xinlei Zhou; Ran Wang; Chee Peng Lim; Xi-Zhao Wang; Q. M. Jonathan Wu

doi:10.1109/TPAMI.2022.3191696

A Review of Generalized Zero-Shot Learning Methods

Farhad Pourpanah, Moloud Abdar, Yuxuan Luo, Xinlei Zhou, Ran Wang^*, Chee Peng Lim, Xi-Zhao Wang, Q. M. Jonathan Wu

^*Corresponding author for this work

Department of Computer Science

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

373 Citations (Scopus)

159 Downloads (CityUHK Scholars)

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.

Original language	English
Pages (from-to)	4051-4070
Journal	IEEE Transactions on Pattern Analysis and Machine Intelligence
Volume	45
Issue number	4
Online published	18 Jul 2022
DOIs	https://doi.org/10.1109/TPAMI.2022.3191696
Publication status	Published - Apr 2023

Research Keywords

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

Publisher's Copyright Statement

This full text is made available under CC-BY-NC-ND 4.0. https://creativecommons.org/licenses/by-nc-nd/4.0/

Access Output

10.1109/TPAMI.2022.3191696

112837184.pdfFinal Published version, 1.62 MBLicence: CC BY-NC-ND

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{885bea44227f441ea54732d34b136a56,

title = "A Review of Generalized Zero-Shot Learning Methods",

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.",

keywords = "Computational modeling, Data models, deep learning, Feature extraction, Generalized zero shot learning, generative adversarial networks, semantic embedding, Semantics, Training, variational auto-encoders, Visualization",

author = "Farhad Pourpanah and Moloud Abdar and Yuxuan Luo and Xinlei Zhou and Ran Wang and Lim, {Chee Peng} and Xi-Zhao Wang and Wu, {Q. M. Jonathan}",

year = "2023",

month = apr,

doi = "10.1109/TPAMI.2022.3191696",

language = "English",

volume = "45",

pages = "4051--4070",

journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",

issn = "0162-8828",

publisher = "IEEE Computer Society",

number = "4",

}

TY - JOUR

T1 - A Review of Generalized Zero-Shot Learning Methods

AU - Pourpanah, Farhad

AU - Abdar, Moloud

AU - Luo, Yuxuan

AU - Zhou, Xinlei

AU - Wang, Ran

AU - Lim, Chee Peng

AU - Wang, Xi-Zhao

AU - Wu, Q. M. Jonathan

PY - 2023/4

Y1 - 2023/4

N2 - 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.

AB - 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.

KW - Computational modeling

KW - Data models

KW - deep learning

KW - Feature extraction

KW - Generalized zero shot learning

KW - generative adversarial networks

KW - semantic embedding

KW - Semantics

KW - Training

KW - variational auto-encoders

KW - Visualization

UR - http://www.scopus.com/inward/record.url?scp=85135235120&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85135235120&origin=recordpage

UR - https://app-overton-io.ezproxy.cityu.edu.hk/articles.php?query=10.1109/TPAMI.2022.3191696

U2 - 10.1109/TPAMI.2022.3191696

DO - 10.1109/TPAMI.2022.3191696

M3 - RGC 21 - Publication in refereed journal

SN - 0162-8828

VL - 45

SP - 4051

EP - 4070

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

IS - 4

ER -

A Review of Generalized Zero-Shot Learning Methods

Abstract

Research Keywords

Publisher's Copyright Statement

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this