Active self-training for weakly supervised 3D scene semantic segmentation  

作　　者：Gengxin Liu Oliver van Kaick Hui Huang Ruizhen Hu 

机构地区：[1]College of Computer Science&Software Engineering,Shenzhen University,Shenzhen 518060,China [2]School of Computer Science,Carleton University,Ottawa K1S 5B6,Canada

出　　处：《Computational Visual Media》2024年第3期425-438,共14页计算可视媒体（英文版）

基　　金：supported by Guangdong Natural Science Foundation(2021B1515020085);Shenzhen Science and Technology Program(RCYX20210609103121030);National Natural Science Foundation of China(62322207,61872250,U2001206,U21B2023);Department of Education of Guangdong Province Innovation Team(2022KCXTD025);Shenzhen Science and Technology Innovation Program(JCYJ20210324120213036);the Natural Sciences and Engineering Research Council of Canada(NSERC);Guangdong Laboratory of Artificial Intelligence and Digital Economy(ShenZhen).

摘　　要：Since the preparation of labeled datafor training semantic segmentation networks of pointclouds is a time-consuming process, weakly supervisedapproaches have been introduced to learn fromonly a small fraction of data. These methods aretypically based on learning with contrastive losses whileautomatically deriving per-point pseudo-labels from asparse set of user-annotated labels. In this paper, ourkey observation is that the selection of which samplesto annotate is as important as how these samplesare used for training. Thus, we introduce a methodfor weakly supervised segmentation of 3D scenes thatcombines self-training with active learning. Activelearning selects points for annotation that are likelyto result in improvements to the trained model, whileself-training makes efficient use of the user-providedlabels for learning the model. We demonstrate thatour approach leads to an effective method that providesimprovements in scene segmentation over previouswork and baselines, while requiring only a few userannotations.

关 键 词：semantic segmentation weakly supervised SELF-TRAINING active learning 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]