.png){kind=icon}
返回
Bias-Correction Feature Learner for Semi-Supervised Instance Segmentation
.png){kind=icon}
PRE
AI
DOI：10.1109/TMM.2022.3199922.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Instance segmentation is heavily reliant on large-scale annotated datasets to yield an ideal accuracy. However, annotated data are difficult to collect. To expand the annotated data, a straightforward idea is to introduce semi-supervised learning, which uses a trained model to obtain initial proposals on unlabeled images and then use initial proposals to generate pseudo labels. However, existing methods inevitably introduce the bias for the model learning, i.e., the foreground in initial low-confident proposals (low-confident foreground) is arbitrarily assigned as background. This bias makes the foreground and background closer in the feature space, which degenerates the model accuracy. To address this issue, this paper discards incorrect supervision and designs a bias-correction feature learner. Specifically, on the one hand, low-confident foreground does not participate in supervised learning. On the other hand, we extract possible foreground regions from all initial proposals to construct high-quality positive pairs which depict objects of the same category in contrastive learning. Then, positive pairs are pulled closer in the feature space. This helps models extract closely clustered foreground features. Experimental results demonstrate the effectiveness of our method on the public datasets (i.e., COCO, Cityscapes and Pascal VOC).
Keyword:
Semi-supervised learning
instance segmentation
contrastive learning
low-confident proposals
期刊
IF:
9.7
论文数:
4.6K
被引数:
2.4W
机构
暂无机构信息
引用论文
.png){kind=icon}
Inflexibility of mental planning: A characteristic disorder with prefrontal lobe lesions?心理计划的僵化: 前额叶病变的特征性障碍？
PREAI
分享收藏
CONSTRUCTION OF FOOD POUCH FROM SEGMENT OF JEJUNUM AS SUBSTITUTE FOR STOMACH IN TOTAL GASTRECTOMY
PREAI
分享收藏分享收藏
查看更多内容