Self-ensembling for visual domain adaptation
- Submitting institution
-
The University of East Anglia
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 182621615
- Type
- E - Conference contribution
- DOI
-
-
- Title of conference / published proceedings
- International Conference on Learning Representations
- First page
- 1
- Volume
- -
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- February
- Year of publication
- 2018
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
2
- Research group(s)
-
-
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- In this work, we have shown that visual domain adaptation can be achieved across very different domains such as highly sketchy, lacking detail synthetic images; and cluttered, full of detail real images. The work presented in this paper has won the ICCV Visual Domain Adaptation challenge 2017. The paper has been highly influential and attracted a large number of citations. It underwent the Open Review process which is available on-line (https://openreview.net/forum?id=rkpoTaxA-) and has been ranked well within the top 10% of submissions. It influenced further research and outputs from Mackiewicz’s REF 2021 ICS “Computer vision for monitoring animal populations".
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -