Loading...
Loading...

Go to the content (press return)

Refinement network for unsupervised on the scene foreground segmentation

Author
Pardas, M.; Canet, G.
Type of activity
Presentation of work at congresses
Name of edition
28th European Signal Processing Conference
Date of publication
2020
Presentation's date
2020-08
Book of congress proceedings
28th European Signal Processing Conference (EUSIPCO 2020): 24-28 August 2020: Amsterdam, the Netherlands
First page
705
Last page
709
Publisher
European Association for Signal Processing (EURASIP)
Project funding
Multimodal Signal Processing and Machine Learning on Graphs
Repository
http://hdl.handle.net/2117/332324 Open in new window
URL
https://www.eurasip.org/Proceedings/Eusipco/Eusipco2020/pdfs/0000705.pdf Open in new window
Abstract
Unsupervised learning represents one of the most interesting challenges in computer vision today. The task has an immense practical value with many applications in artificial intelligence and emerging technologies, as large quantities of unlabeled images and videos can be collected at low cost. In this paper, we address the unsupervised learning problem in the context of segmenting the main foreground objects in single images. We propose an unsupervised learning system, which has two pathways, t...
Citation
Pardàs, M.; Canet, G. Refinement network for unsupervised on the scene foreground segmentation. A: European Signal Processing Conference. "28th European Signal Processing Conference (EUSIPCO 2020): 24-28 August 2020: Amsterdam, the Netherlands". European Association for Signal Processing (EURASIP), 2020, p. 705-709. ISBN 978-9-0827-9705-3.
Keywords
Foreground object segmentation, Object discovery in video, Transfer learning, Unsupervised learning
Group of research
GPI - Image and Video Processing Group
Universitat Politècnica de Catalunya

Participants

Attachments