To access this element change to forms mode OFF
Grant Award View - GA142292-V3
Automatic Training Data Search and Model Evaluation by Measuring Domain...
GA ID:
GA142292-V3
Agency:
Australian Research Council
Approval Date:
11-Dec-2020
Variation Publish Date:
18-May-2022
Variation Date:
18-May-2022
Category:
Science, Technology, Engineering and Mathematics (STEM) Research
Grant Term:
11-Dec-2021 to 10-Dec-2024
Value (AUD):
$506,671.00
(GST inclusive where applicable)
Varies:
GA142292
- Automatic Training Data Search and Model Evaluation by Measuring Domain Gap
One-off/Ad hoc:
No
Aggregate Grant Award:
No
PBS Program Name:
ARC 20/21 Discovery
Grant Program:
Discovery Projects
Grant Activity:
Automatic Training Data Search and Model Evaluation by Measuring Domain Gap
Purpose:
We aim to investigate computer vision training data and test data, using automatically generated data sets for facial expression recognition and object re-identification. This project expects to quantify and understand the domain gap, the distribution difference between training and test data sets. Expected outcomes of this project are insights on measuring the domain gap, the ability to estimate model performance without accessing expensive test labels and improvements to system generalisation. This should provide significant benefits for computer vision applications that currently require expensive labelling, and commercial and economic benefits across sectors such as transportation, security and manufacturing.
GO ID:
GO Title:
Discovery Projects for funding commencing in 2021
Internal Reference ID:
DP21 Round 1
Selection Process:
Targeted or Restricted Competitive
Confidentiality - Contract:
No
Confidentiality - Outputs:
No
Grant Recipient Details
Recipient Name:
The Australian National University
Recipient ABN:
52 234 063 906
Grant Recipient Location
Suburb:
ACTON
Town/City:
ACTON
Postcode:
2601
State/Territory:
ACT
Country:
AUSTRALIA
Grant Delivery Location
State/Territory:
ACT
Postcode:
2601
Country:
AUSTRALIA