Visual Semantic Segmentation Based on Few/Zero-Shot Learning:An Overview
作者机构:Key Laboratory of Smart Manufacturing in Energy Chemical ProcessMinistry of EducationEast China University of Science and TechnologyShanghai 200237China National Key Laboratory of Air-Based Information Perception and FusionAviation Industry Corporation of ChinaLuoyang 471000China School of ScienceComputing and Engineering TechnologiesSwinburne University of TechnologyMelbourne VIC 3122Australia
出 版 物:《IEEE/CAA Journal of Automatica Sinica》 (自动化学报(英文版))
年 卷 期:2024年第11卷第5期
页 面:1106-1126页
核心收录:
学科分类:08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 0811[工学-控制科学与工程]
基 金:supported by National Key Research and Development Program of China(2021YFB1714300) the National Natural Science Foundation of China(62233005) in part by the CNPC Innovation Fund(2021D002-0902) Fundamental Research Funds for the Central Universities and Shanghai AI Lab sponsored by Shanghai Gaofeng and Gaoyuan Project for University Academic Program Development
主 题:Visual segmentation separating
摘 要: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 *** learning-based visual semantic segmentation approaches count heavily on largescale training data with dense annotations and consistently fail to estimate accurate semantic labels for unseen *** obstruction spurs a craze for studying visual semantic segmentation with the assistance of few/zero-shot *** 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 practical ***,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 segmentation ***,the preliminaries on few/zeroshot visual semantic segmentation,including the problem definitions,typical datasets,and technical remedies,are briefly reviewed and ***,three typical instantiations are involved to uncover the interactions of few/zero-shot learning with visual semantic segmentation,including image semantic segmentation,video object segmentation,and 3D ***,the future challenges of few/zero-shot visual semantic segmentation are discussed.