.png){kind=icon}
返回
Guided Filter Network for Semantic Image Segmentation
.png){kind=icon}
PRE
AI
DOI：10.1109/TIP.2022.3160399.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The existing publicly available datasets with pixel-level labels contain limited categories, and it is difficult to generalize to the real world containing thousands of categories. In this paper, we propose an approach to generate object masks with detailed pixel-level structures/boundaries automatically to enable semantic image segmentation of thousands of targets in the real world without manually labelling. A Guided Filter Network (GFN) is first developed to learn the segmentation knowledge from an existed dataset, and such GFN then transfers the learned segmentation knowledge to generate initial coarse object masks for the target images. These coarse object masks are treated as pseudo labels to self-optimize the GFN iteratively in the target images. Our experiments on six image sets have demonstrated that our proposed approach can generate object masks with detailed pixel-level structures/boundaries, whose quality is comparable to the manually-labelled ones. Our proposed approach also achieves better performance on semantic image segmentation than most existing weakly-supervised, semi-supervised, and domain adaptation approaches under the same experimental conditions.
Keyword:
Image segmentation
Semantics
Training
Feature extraction
Labeling
Manuals
Knowledge engineering
Semantic image segmentation
pixel-level labels
guided filter
deep networks
期刊
IF:
13.7
论文数:
1.0W
被引数:
8.4W
机构
引用论文
The spectrophotometric determination of the alkaline-earth metals with murexide, eriochrome black T and with o-cresolphthalein complexone.png)
The Analyst
The AnalystIF0
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Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation通过不确定性估计纠正伪标签学习，用于领域自适应语义分割
PREAI
分享收藏
查看更多内容