文献类型：期刊文献

英文题名：Hybrid supervised instance segmentation by learning label noise suppression

作者：Chen, Linwei[1];Fu, Ying[1];You, Shaodi[2];Liu, Hongzhe[3]

第一作者：Chen, Linwei

通讯作者：Fu, Y[1]

机构：[1]Beijing Inst Technol, Sch Comp Sci & Technol, Beijing 100081, Peoples R China;[2]Univ Amsterdam, Inst Informat, Comp Vis Res Grp, NL-1098 XH Amsterdam, Netherlands;[3]Beijing Union Univ, Beijing Key Lab Informat Serv Engn, Beijing 100101, Peoples R China

第一机构：Beijing Inst Technol, Sch Comp Sci & Technol, Beijing 100081, Peoples R China

通讯机构：[1]corresponding author), Beijing Inst Technol, Sch Comp Sci & Technol, Beijing 100081, Peoples R China.

年份：2022

卷号：496

起止页码：131-146

外文期刊名：NEUROCOMPUTING

收录：;EI(收录号：20222112140605);Scopus(收录号：2-s2.0-85130319874);WOS:【SCI-EXPANDED(收录号:WOS:000830186600008)】；

基金：This work was supported by the National Natural Science Foundation of China under Grants No. 62171038, No. 61827901, No. 61936011, and No. 62088101.

语种：英文

外文关键词：Instance segmentation; Semantic segmentation; Weak supervision; Semi-supervision; Hybrid supervision; Pseudo label; Labeling cost

摘要：To reach top accuracy, current fully supervised instance segmentation methods severely rely on large-scale pixel-wise labeled datasets. They are usually expensive and time-consuming to obtain. Though weakly or semi-supervised methods utilize cheap bounding box labeled, image-level labeled or unlabeled samples to save the labeling cost, their performance is largely sacrificed. To save labeling cost without losing much performance, in this paper, we present a pipeline that can utilize economical bounding box labels and accurate pixel-wise labels in a hybrid way. Specifically, we design two ancillary models to learn label noise suppression and obtain accurate pseudo pixel-wise labels from bounding box labels for training. One is designed to suppress mislabeling between foreground and background, and the other is designed to suppress noise from mislabeling of instances. Moreover, we exploit category-aware spatial attention module, category constraint module, instance constraint module, and self-learning training approach to improve the accuracy of pseudo labels. Experiments on the PASCAL VOC 2012 and the Cityscapes datasets show that our method can achieve competitive performance with much less labeling cost. (C) 2022 Published by Elsevier B.V.