Active rare class discovery and classification using Dirichlet processes
- Submitting institution
-
The University of Bath
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 159975408
- Type
- D - Journal article
- DOI
-
10.1007/s11263-013-0630-3
- Title of journal
- International Journal of Computer Vision
- Article number
- -
- First page
- 315
- Volume
- 106
- Issue
- 3
- ISSN
- 0920-5691
- Open access status
- Out of scope for open access requirements
- Month of publication
- May
- Year of publication
- 2014
- 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
-
1
- Research group(s)
-
-
- Citation count
- 11
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Majority of active learning papers combine a known approach with a known ML algorithm. Much rarer is the kind presented here, one that introduces a fundamentally new approach. This is only the second approach to the specific problem, with many of the later approaches building on the technique presented here.
ECCV 2012 "A unifying theory of active discovery and learning", Loy et al, CVPR 2012 "Stream-based joint exploration-exploitation active learning").
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -