Detector Adaptation by Maximising Agreement Between Independent Data Sources
Abstract
Traditional methods for creating classifiers have two main disadvantages. Firstly, it is time consuming to acquire, or manually annotate, the training collection. Secondly, the data on which the classifier is trained may be over-generalised or too specific. This paper presents our investigations into overcoming both of these drawbacks simultaneously, by providing example applications where two data sources train each other. This removes both the need for supervised annotation or feedback, and allows rapid adaptation of the classifier to different data. Two applications are presented: one using thermal infrared and visual imagery to robustly learn changing skin models, and another using changes in saturation and luminance to learn shadow appearance parameters.
Cite
Text
Conaire et al. "Detector Adaptation by Maximising Agreement Between Independent Data Sources." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2007. doi:10.1109/CVPR.2007.383448Markdown
[Conaire et al. "Detector Adaptation by Maximising Agreement Between Independent Data Sources." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2007.](https://mlanthology.org/cvpr/2007/conaire2007cvpr-detector/) doi:10.1109/CVPR.2007.383448BibTeX
@inproceedings{conaire2007cvpr-detector,
title = {{Detector Adaptation by Maximising Agreement Between Independent Data Sources}},
author = {Conaire, Ciarán Ó and O'Connor, Noel E. and Smeaton, Alan F.},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2007},
doi = {10.1109/CVPR.2007.383448},
url = {https://mlanthology.org/cvpr/2007/conaire2007cvpr-detector/}
}