Loading...
Loading...

Go to the content (press return)

Picking groups instead of samples: a close look at Static Pool-based Meta-Active Learning

Author
Mas, I.; Morros, J.R.; Vilaplana, V.
Type of activity
Presentation of work at congresses
Name of edition
IEEE International Conference on Computer Vision Workshops 2019
Date of publication
2019
Presentation's date
2019-11
Book of congress proceedings
2019 International Conference on Computer Vision ICCV 2019: proceedings: 27 October - 2 November 2019 Seoul, Korea
First page
1
Last page
9
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
DOI
10.1109/ICCVW.2019.00171
Repository
http://hdl.handle.net/2117/179428 Open in new window
https://imatge.upc.edu/web/publications/picking-groups-instead-samples-close-look-static-pool-based-meta-active-learning Open in new window
URL
https://ieeexplore.ieee.org/document/9022361 Open in new window
Abstract
Active Learning techniques are used to tackle learning problems where obtaining training labels is costly. In this work we use Meta-Active Learning to learn to select a subset of samples from a pool of unsupervised input for further annotation. This scenario is called Static Pool-based Meta-Active Learning. We propose to extend existing approaches by performing the selection in a manner that, unlike previous works, can handle the selection of each sample based on the whole selected subset. ©201...
Citation
Mas, I.; Morros, J.R.; Vilaplana, V. Picking groups instead of samples: a close look at Static Pool-based Meta-Active Learning. A: IEEE International Conference on Computer Vision Workshops. "2019 International Conference on Computer Vision ICCV 2019: proceedings: 27 October- 2 November 2019 Seoul, Korea". Institute of Electrical and Electronics Engineers (IEEE), 2019, p. 1-9.
Keywords
Active learning, Few shot learning, Learning under constraints, Meta active learning, Meta learning, RNN, Reinforcement learning, Static pool based active learning
Group of research
GPI - Image and Video Processing Group
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center

Participants

Attachments