首页|Visual Semantic Segmentation Based on Few/Zero-Shot Learning:An Overview

Visual Semantic Segmentation Based on Few/Zero-Shot Learning:An Overview

扫码查看
原文链接
  • 国家科技期刊平台
  • NETL
  • NSTL
  • 万方数据
  • 维普
Visual semantic segmentation aims at separating a visual sample into diverse blocks with specific semantic attributes and identifying the category for each block,and it plays a crucial role in environmental perception.Conventional learning-based visual semantic segmentation approaches count heavily on large-scale training data with dense annotations and consistently fail to estimate accurate semantic labels for unseen categories.This obstruction spurs a craze for studying visual semantic segmenta-tion with the assistance of few/zero-shot learning.The emergence and rapid progress of few/zero-shot visual semantic segmentation make it possible to learn unseen categories from a few labeled or even zero-labeled samples,which advances the extension to prac-tical applications.Therefore,this paper focuses on the recently published few/zero-shot visual semantic segmentation methods varying from 2D to 3D space and explores the commonalities and discrepancies of technical settlements under different segmenta-tion circumstances.Specifically,the preliminaries on few/zero-shot visual semantic segmentation,including the problem defini-tions,typical datasets,and technical remedies,are briefly reviewed and discussed.Moreover,three typical instantiations are involved to uncover the interactions of few/zero-shot learning with visual semantic segmentation,including image semantic segmen-tation,video object segmentation,and 3D segmentation.Finally,the future challenges of few/zero-shot visual semantic segmenta-tion are discussed.

Computer visiondeep learningfew-shot learninglow-shot learningsemantic segmentationzero-shot learning

Wenqi Ren、Yang Tang、Qiyu Sun、Chaoqiang Zhao、Qing-Long Han

展开 >

Key Laboratory of Smart Manufa-cturing in Energy Chemical Process,Ministry of Education,East China Uni-versity of Science and Technology,Shanghai 200237,China

National Key Laboratory of Air-Based Information Perception and Fusion,Aviation Industry Corporation of China,Luoyang 471000,China

School of Science,Computing and Engineering Technologies,Swinburne University of Technology,Melbourne VIC 3122,Australia

国家重点研发计划国家自然科学基金CNPC Innovation FundFundamental Research Funds for the Central Universities and Shanghai AI LabShanghai Gaofeng and Gaoyuan Project for University Academic Program Development

2021YFB1714300622330052021D002-0902

2024

10.1109/JAS.2023.123207

自动化学报(英文版)
中国自动化学会,中国科学院自动化研究所,中国科技出版传媒股份有限公司

自动化学报(英文版)

CSTPCDEI
ISSN：2329-9266
年,卷(期)：2024.11(5)
  • 163