Repeatability Is Not Enough: Learning Affine Regions via Discriminability
Abstract
A method for learning local affine-covariant regions is presented. We show that maximizing geometric repeatability does not lead to local regions, a.k.a features, that are reliably matched and this necessitates descriptor-based learning. We explore factors that influence such learning and registration: the loss function, descriptor type, geometric parametrization and the trade-off between matchability and geometric accuracy and propose a novel hard negative-constant loss function for learning of affine regions. The affine shape estimator -- AffNet -- trained with the hard negative-constant loss outperforms the state-of-the-art in bag-of-words image retrieval and wide baseline stereo. The proposed training process does not require precisely geometrically aligned patches. The source codes and trained weights are available at https://github.com/ducha-aiki/affnet
Cite
Text
Mishkin et al. "Repeatability Is Not Enough: Learning Affine Regions via Discriminability." Proceedings of the European Conference on Computer Vision (ECCV), 2018. doi:10.1007/978-3-030-01240-3_18Markdown
[Mishkin et al. "Repeatability Is Not Enough: Learning Affine Regions via Discriminability." Proceedings of the European Conference on Computer Vision (ECCV), 2018.](https://mlanthology.org/eccv/2018/mishkin2018eccv-repeatability/) doi:10.1007/978-3-030-01240-3_18BibTeX
@inproceedings{mishkin2018eccv-repeatability,
title = {{Repeatability Is Not Enough: Learning Affine Regions via Discriminability}},
author = {Mishkin, Dmytro and Radenovic, Filip and Matas, Jiri},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2018},
doi = {10.1007/978-3-030-01240-3_18},
url = {https://mlanthology.org/eccv/2018/mishkin2018eccv-repeatability/}
}