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

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.