Loading...
Loading...

Go to the content (press return)

Mask-guided sample selection for semi-supervised instance segmentation

Author
Bellver, M.; Salvador, A.; Torres, J.; Giro, X.
Type of activity
Journal article
Journal
Multimedia tools and applications
Date of publication
2020-07-05
Volume
79
First page
25551
Last page
25569
DOI
10.1007/s11042-020-09235-4
Project funding
Computación de Altas Prestaciones VI
MALEGRA, TEC2016-75976-R
Repository
http://hdl.handle.net/2117/328619 Open in new window
https://imatge.upc.edu/web/publications/mask-guided-sample-selection-semi-supervised-instance-segmentation Open in new window
URL
https://link.springer.com/article/10.1007/s11042-020-09235-4 Open in new window
Abstract
Image segmentation methods are usually trained with pixel-level annotations, which require significant human effort to collect. Weakly-supervised pipelines are the most common solution to address this constraint because they are trained with lower forms of supervision, such as bounding boxes or scribbles. Semi-supervised methods are another option, that leverage a large amount of unlabeled data and a limited number of strongly-labeled samples. In this second setup, samples to be strongly-annotat...
Citation
Bellver, M. [et al.]. Mask-guided sample selection for semi-supervised instance segmentation. "Multimedia tools and applications", 5 Juliol 2020, vol. 79, p. 25551-25569.
Keywords
Active learning, Image 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