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

作　　者：Wenqi Ren Yang Tang Qiyu Sun Chaoqiang Zhao Qing-Long Han 

机构地区：[1]Key Laboratory of Smart Manufacturing in Energy Chemical Process,Ministry of Education,East China University of Science and Technology,Shanghai 200237,China [2]National Key Laboratory of Air-Based Information Perception and Fusion,Aviation Industry Corporation of China,Luoyang 471000,China [3]School of Science,Computing and Engineering Technologies,Swinburne University of Technology,Melbourne VIC 3122,Australia

出　　处：《IEEE/CAA Journal of Automatica Sinica》2024年第5期1106-1126,共21页自动化学报（英文版）

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。

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 perception.Conventional 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 categories.This obstruction spurs a craze for studying visual semantic segmentation 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 practical 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 segmentation circumstances.Specifically,the preliminaries on few/zeroshot visual semantic segmentation,including the problem definitions,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 segmentation,video object segmentation,and 3D segmentation.Finally,the future challenges of few/zero-shot visual semantic segmentation are discussed.

关 键 词：VISUAL SEGMENTATION SEPARATING 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]