Self-supervised Segmentation
Self-Supervised Segmentation is a machine learning approach within semantic segmentation that leverages unlabeled data by generating pseudo-supervisory signals through pretext tasks, thereby distinguishing itself from fully supervised methods by eliminating the reliance on manually annotated ground truth labels.
224
Publications
11.4K
Citations
961
Authors
336
Institutions
Publications per year
2017–2026
211
Parents
224
Unsupervised Intra-Domain Adaptation for Semantic Segmentation Through Self-Supervision
Fei Pan, Inkyu Shin, François Rameau et al. · 2020 · 375 citations
Weakly-Supervised Semantic Segmentation via Sub-Category Exploration
Yu-Ting Chang, Qiaosong Wang, Wei-Chih Hung et al. · 2020 · 315 citations
1–5 of 224
961
3
h-index
3
h-index
3
h-index
3
h-index
3
h-index
1–5 of 961
336
University of Science and Technology of China
Hefei, China
7 h-index
22 publications
1.6K citations

Zhejiang University
Hangzhou, China
6 h-index
18 publications
632 citations
Google (United States)
Mountain View, United States
5 h-index
9 publications
1K citations
University of Oxford
Oxford, United Kingdom
5 h-index
15 publications
1.4K citations

Central South University
Changsha, China
5 h-index
23 publications
1.3K citations

Shanghai Jiao Tong University
Shanghai, China
5 h-index
19 publications
875 citations
Technical University of Munich
Munich, Germany
4 h-index
7 publications
425 citations
ETH Zurich
Zurich, Switzerland
4 h-index
14 publications
1.6K citations
1–8 of 336
Repository · 35 publications · 972 citations
18
h-index
Conference · 9 publications · 732 citations
9
h-index
9 publications · 535 citations
9
h-index
Conference · 5 publications · 324 citations
5
h-index
4 publications · 311 citations
4
h-index
1–5