Weakly Supervised Segmentation
Weakly Supervised Segmentation is an image segmentation paradigm that belongs to the broader class of supervised learning methods but is distinguished by its reliance on limited or inexact forms of annotation—such as image-level labels, bounding boxes, or scribbles—rather than requiring dense pixel-level ground truth masks for training.
610
Publications
52.7K
Citations
2.2K
Authors
608
Institutions
Publications per year
2017–2026
553
Parents
610
1–5 of 610
2.2K
14
h-index
11
h-index
10
h-index
10
h-index
10
h-index
1–5 of 2.2K
608
University of Chinese Academy of Sciences
Beijing, China
22 h-index
78 publications
9.6K citations

Chinese Academy of Sciences
Beijing, China
19 h-index
89 publications
8.5K citations
Tsinghua University
Beijing, China
19 h-index
66 publications
5.4K citations
Tencent (China)
Shenzhen, China
16 h-index
36 publications
2.2K citations

Zhejiang University
Hangzhou, China
16 h-index
52 publications
4K citations
Nanyang Technological University
Singapore, Singapore
15 h-index
40 publications
2.5K citations

University of Electronic Science and Technology of China
Chengdu, China
14 h-index
42 publications
1.8K citations
ETH Zurich
Zurich, Switzerland
14 h-index
25 publications
2.4K citations
1–8 of 608
Repository · 96 publications · 8.9K citations
30
h-index
Conference · 23 publications · 2.8K citations
20
h-index
TPAMI · 23 publications · 1.9K citations
19
h-index
20 publications · 2.1K citations
18
h-index
18 publications · 1.5K citations
17
h-index
1–5