A comprehensive review on zero-shot-learning techniques

Author:

Lazaros Konstantinos1,Koumadorakis Dimitris E.1,Vrahatis Aristidis G.1,Kotsiantis Sotiris2

Affiliation:

1. Bioinformatics and Human Electrophysiology Laboratory, Department of Informatics, Ionian University, Corfu, Greece

2. Department of Mathematics, University of Patras, Patras, Greece

Abstract

Advancements in computational capabilities have enabled the implementation of advanced deep learning models across various domains of knowledge, yet the increasing complexity and scarcity of data in specialized areas pose significant challenges. Zero-shot learning (ZSL), a subset of transfer learning, has emerged as an innovative solution to these challenges, focusing on classifying unseen categories present in the test set but absent during training. Unlike traditional methods, ZSL utilizes semantic descriptions, like attribute lists or natural language phrases, to map intermediate features from the training data to unseen categories effectively, enhancing the model’s applicability across diverse and complex domains. This review provides a concise synthesis of the advancements, methodologies, and applications in the field of zero-shot learning, highlighting the milestones achieved and possible future directions. We aim to offer insights into the contemporary developments in ZSL, serving as a comprehensive reference for researchers exploring the potentials and challenges of implementing ZSL-based methodologies in real-world scenarios.

Publisher

IOS Press

Reference228 articles.

1. Géron A. Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow. ISBN: 9781098125974: “O’Reilly Media, Inc.”; 2022.

2. Benois-Pineau J, Zemmari A. Multi-faceted deep learning: Models and data. Springer Nature; 2021.

3. towards zero-shot learning: A brief review and an attention-based embedding network;Xie;IEEE Transactions on Circuits and Systems for Video Technology,2023

4. Pourpanah F, Abdar M, Luo Y, Zhou X, Wang R, Lim CP, et al. A review of generalized zero-shot learning methods. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2022.

5. A review on multimodal zero-shot learning;Cao;Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery,2023

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3