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
Authors
Bibliographic Details
- 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
Item Description
- Language:
- English
- Keywords:
- Pubs id:
-
1130212
- Local pid:
- pubs:1130212
- Deposit date:
- 2020-09-04
Terms of use
- Copyright holder:
- Springer Nature
- Copyright date:
- 2020
- Rights statement:
- © Springer Nature Switzerland AG 2020.
- Notes:
- This paper was presented at the 16th European Conference on Computer Vision (ECCV 2020), August 2020. This is the accepted manuscript version of the article. The final version is available online from Springer at: https://doi.org/10.1007/978-3-030-58542-6_16
Metrics
If you are the owner of this record, you can report an update to it here: Report update to this record