An Optimized Interaction Strategy for Bayesian Relevance Feedback
Abstract
A new algorithm and systematic evaluation is presented for searching a database via relevance feedback. It represents a new image display strategy for the PicHunter system. The algorithm takes feedback in the form of relative judgments ("item A is more relevant than item B") as opposed to the stronger assumption of categorical relevance judgments ("item A is relevant but item B is not"). It also exploits a learned probabilistic model of human behavior to make better use of the feedback it obtains. The algorithm can be viewed as an extension of indexing schemes like the k-d tree to a stochastic setting, hence the name "stochastic-comparison search." In simulations, the amount of feedback required for the new algorithm scales like log/sub 2/ |D|, where |D| is the size of the database, while a simple query-by-example approach scales like |D|/sup /spl alpha//, where /spl alpha/<1 depends on the structure of the database. This theoretical advantage is reflected by experiments with real users on a database of 1500 stock photographs.
Cite
Text
Cox et al. "An Optimized Interaction Strategy for Bayesian Relevance Feedback." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1998. doi:10.1109/CVPR.1998.698660Markdown
[Cox et al. "An Optimized Interaction Strategy for Bayesian Relevance Feedback." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1998.](https://mlanthology.org/cvpr/1998/cox1998cvpr-optimized/) doi:10.1109/CVPR.1998.698660BibTeX
@inproceedings{cox1998cvpr-optimized,
title = {{An Optimized Interaction Strategy for Bayesian Relevance Feedback}},
author = {Cox, Ingemar J. and Miller, Matthew L. and Minka, Thomas P. and Yianilos, Peter N.},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {1998},
pages = {553-558},
doi = {10.1109/CVPR.1998.698660},
url = {https://mlanthology.org/cvpr/1998/cox1998cvpr-optimized/}
}