.png){kind=icon}
返回
Hybrid supervised instance segmentation by learning label noise suppression
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2022.05.026.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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.
Keyword:
Instance segmentation
Semantic segmentation
Weak supervision
Semi-supervision
Hybrid supervision
Pseudo label
Labeling cost
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
Distant regulatory elements in a Sox10‐βGEO BAC transgene are required for expression of Sox10 in the enteric nervous system and other neural crest‐derived tissuesSox10-βgeo BAC转基因中的远距离调控元件是肠神经系统和其他神经源性组织中 Sox10 表达所必需的
OAAI
OAAI分享收藏Dark induced increase in pineal serotonin N-acetyltransferase activity: A refractory period.png)
Experientia
ExperientiaIF0
PREAI
分享收藏
分享收藏
查看更多内容