arrow
返回

Non-target feature filtering for weakly supervised semantic segmentation

delete2024-12-02
delete0
delete
OA
AI
X
Xuesheng Zhou
Y
Yan Li
G
Guitao Cao *
W
Wenming Cao
DOI:10.1007/s40747-024-01678-8delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Weakly supervised semantic segmentation (WSSS) utilizes weak labels to learn semantic segmentation models, significantly reducing reliance on pixel-level annotations. WSSS typically employs a multi-label classification network to extract image features for constructing localization maps. The quality of the localization map critically influences the performance of WSSS. However, non-target semantic noise within the features impedes the improvement of localization map quality. To address this issue, we propose a non-target feature filtering class activation mapping (NFF-CAM) for WSSS, which can reduce non-target semantic signals and generate higher-quality localization maps. Specifically, the class-constrained dual cosine clustering (CDCC) and channel identification (CI) modules are introduced in NFF-CAM. CDCC effectively addresses the issue of unsuitability in the clustering group relationships of the original features under specified class conditions. CI can efficiently identify channel features containing non-target semantic information. We conduct extensive evaluations of NFF-CAM on popular datasets, including PASCAL VOC 2012 and MS COCO 2014. Experimental results show that NFF-CAM can effectively improve the segmentation performance of off-the-shelf methods.
Keyword:
Semantic segmentation
Weak supervision
Localization map
Class activation mapping
Classification

期刊

Complex and Intelligent Systems 封面图
Complex and Intelligent Systems
IF:
4.6
论文数:
2.1K
被引数:
6.6K

机构

E
east china normal university
学者数:
3.1W
论文数: 2.1W
被引数: 25
S
Shanghai Normal University
学者数:
7.4K
论文数: 5.0K
被引数: 8.0K
S
shenzhen university
学者数:
4.6W
论文数: 3.4W
被引数: 72
学者 查看更多机构
引用论文

引用论文

Measurement of Lubrication Condition in Rolling Element Bearings
err2008-03-25
err0
PREAI
errR. S. Heemskerk; K. N. Vermeiren; H. Dolfsma
err分享
err收藏
err分享
err收藏
LayerCAM: Exploring Hierarchical Class Activation Maps for Localization
err2021-01-01
err369
PREAI
errJiang, Peng-Tao; Zhang, Chang-Bin; Hou, Qibin; Cheng, Ming-Ming; Wei, Yunchao
err分享
err收藏
err分享
err收藏
学者 查看更多内容