Conference item icon

Conference item

Uncertainty estimation with a VAE-classifier hybrid model

Abstract:

We propose a hybrid model that combines a generative unit and a discriminative classifier to quantify uncertainty in a classification task. The representation learning capability in the VAE module allows our method to learn more useful and generalizable features and outperform other purely discriminative classifiers when training labels are limited. With proper statistical treatment, the probabilistic encoder in our VAE module offers a convenient mechanism to express uncertainty for out-of-di...

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

Actions


Access Document


Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
ORCID:
0000-0002-9305-9268
Publisher:
IEEE Publisher's website
Host title:
Proceedings of the 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2022)
Pages:
3548-3552
Publication date:
2022-04-27
Event title:
2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2022)
Event location:
Singapore
Event website:
https://2022.ieeeicassp.org/
Event start date:
2022-05-23
Event end date:
2022-05-27
DOI:
EISSN:
1520-6149
ISSN:
2640-3943
EISBN:
9781665405409
ISBN:
9781665405416
Language:
English
Keywords:
Pubs id:
1264330
Local pid:
pubs:1264330
Deposit date:
2023-01-20

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