A Testbed for Cross-Dataset Analysis
Abstract
Despite the increasing interest towards domain adaptation and transfer learning techniques to generalize over image collections and overcome their biases, the visual community misses a large scale testbed for cross-dataset analysis. In this paper we discuss the challenges faced when aligning twelve existing image databases in a unique corpus, and we propose two cross-dataset setups that introduce new interesting research questions. Moreover, we report on a first set of experimental domain adaptation tests showing the effectiveness of iterative self-labeling for large scale problems.
Cite
Text
Tommasi and Tuytelaars. "A Testbed for Cross-Dataset Analysis." European Conference on Computer Vision, 2014. doi:10.1007/978-3-319-16199-0_2Markdown
[Tommasi and Tuytelaars. "A Testbed for Cross-Dataset Analysis." European Conference on Computer Vision, 2014.](https://mlanthology.org/eccv/2014/tommasi2014eccv-testbed/) doi:10.1007/978-3-319-16199-0_2BibTeX
@inproceedings{tommasi2014eccv-testbed,
title = {{A Testbed for Cross-Dataset Analysis}},
author = {Tommasi, Tatiana and Tuytelaars, Tinne},
booktitle = {European Conference on Computer Vision},
year = {2014},
pages = {18-31},
doi = {10.1007/978-3-319-16199-0_2},
url = {https://mlanthology.org/eccv/2014/tommasi2014eccv-testbed/}
}