Conference item icon

Conference item

Improving few-shot learning by spatially-aware matching and crosstransformer

Abstract:

Current few-shot learning models capture visual object relations in the so-called meta-learning setting under a fixed-resolution input. However, such models have a limited generalization ability under the scale and location mismatch between objects, as only few samples from target classes are provided. Therefore, the lack of a mechanism to match the scale and location between pairs of compared images leads to the performance degradation. The importance of image contents varies across coarse-t...

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

Actions


Access Document


Files:
Publisher copy:
10.1007/978-3-031-26348-4_1

Authors


More by this author
Role:
Author
ORCID:
0000-0003-0734-0078
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
More by this author
Role:
Author
ORCID:
0000-0002-6340-5289
Publisher:
Springer
Series:
Lecture Notes in Computer Science
Series number:
13845
Pages:
3-20
Place of publication:
Cham, Switzerland
Publication date:
2023-01-09
Event title:
16th Asian Conference on Computer Vision (ACCV 2022)
Event location:
Macau SAR, China
Event website:
https://www.accv2022.org/en/default.asp
Event start date:
2022-12-04
Event end date:
2022-12-08
DOI:
EISSN:
1611-3349
ISSN:
0302-9743
EISBN:
9783031263484
ISBN:
9783031263477
Language:
English
Keywords:
Pubs id:
1335905
Local pid:
pubs:1335905
Deposit date:
2023-05-12

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