Conference item icon

Conference item

AutoSimulate: (Quickly) learning synthetic data generation

Abstract:

Simulation is increasingly being used for generating large labelled datasets in many machine learning problems. Recent methods have focused on adjusting simulator parameters with the goal of maximising accuracy on a validation task, usually relying on REINFORCE-like gradient estimators. However these approaches are very expensive as they treat the entire data generation, model training, and validation pipeline as a black-box and require multiple costly objective evaluations at each iteration....

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

Actions


Access Document


Files:
Publisher copy:
10.1007/978-3-030-58542-6_16

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
ORCID:
0000-0001-9854-8100
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
Publisher:
Springer Publisher's website
Publication date:
2020-11-17
Acceptance date:
2020-07-03
Event title:
16th European Conference on Computer Vision (ECCV 2020)
Event website:
https://eccv2020.eu/
Event start date:
2020-08-23
Event end date:
2020-08-28
DOI:
EISBN:
9783030585426
ISBN:
9783030585419
Language:
English
Keywords:
Pubs id:
1130212
Local pid:
pubs:1130212
Deposit date:
2020-09-04

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