Loading...
Loading...

Go to the content (press return)

Budget-aware semi-supervised semantic and instance segmentation

Author
Bellver, M.; Salvador, A.; Torres, J.; Giro, X.
Type of activity
Presentation of work at congresses
Name of edition
2019 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Date of publication
2019
Presentation's date
2019-06-16
Book of congress proceedings
The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2019
First page
93
Last page
102
Project funding
Computación de Altas Prestaciones VII
Models de programació i entorns d'execució paral·lels
Multimodal Signal Processing and Machine Learning on Graphs
Repository
http://hdl.handle.net/2117/184978 Open in new window
https://arxiv.org/abs/1905.05880 Open in new window
URL
http://openaccess.thecvf.com/content_CVPRW_2019/html/Deep_Vision_Workshop/Bellver_Budget-aware_Semi-Supervised_Semantic_and_Instance_Segmentation_CVPRW_2019_paper.html Open in new window
Abstract
Methods that move towards less supervised scenarios are key for image segmentation, as dense labels demand significant human intervention. Generally, the annotation burden is mitigated by labeling datasets with weaker forms of supervision, e.g. image-level labels or bounding boxes. Another option are semi-supervised settings, that commonly leverage a few strong annotations and a huge number of unlabeled/weakly-labeled data. In this paper, we revisit semi-supervised segmentation schemes and narro...
Citation
Bellver, M. [et al.]. Budget-aware semi-supervised semantic and instance segmentation. A: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. "The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2019". 2019, p. 93-102.
Keywords
Annotation, Budget, Computer vision, Cost, Image segmentation, Instance segmentation, Semi-supervised learning
Group of research
CAP - High Performace Computing Group
GPI - Image and Video Processing Group
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center

Participants

Attachments