Conference item icon

Conference item

Revisiting vicinal risk minimization for partially supervised multi-label classification under data scarcity

Abstract:

Due to the high human cost of annotation, it is nontrivial to curate a large-scale medical dataset that is fully labeled for all classes of interest. Instead, it would be convenient to collect multiple small partially labeled datasets from different matching sources, where the medical images may have only been annotated for a subset of classes of interest. This paper offers an empirical understanding of an under-explored problem, namely partially supervised multi-label classification (PSMLC),...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.1109/CVPRW56347.2022.00466

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Role:
Author
Publisher:
IEEE
Host title:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Pages:
4211-4219
Publication date:
2022-08-23
Acceptance date:
2022-04-12
Event title:
Workshop on Learning with Limited Labelled Data for Image and Video Understanding, CVPR 2022
Event location:
New Orleans, Louisiana
Event website:
https://sites.google.com/view/l3d-ivu
Event start date:
2022-06-20
Event end date:
2022-06-20
DOI:
EISSN:
2160-7516
ISSN:
2160-7508
EISBN:
9781665487399
ISBN:
978-665487405
Language:
English
Keywords:
Pubs id:
1272347
Local pid:
pubs:1272347
Deposit date:
2022-08-03

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP