Mining on Manifolds: Metric Learning Without Labels
Abstract
In this work we present a novel unsupervised framework for hard training example mining. The only input to the method is a collection of images relevant to the target application and a meaningful initial representation, provided e.g. by pre-trained CNN. Positive examples are distant points on a single manifold, while negative examples are nearby points on different manifolds. Both types of examples are revealed by disagreements between Euclidean and manifold similarities. The discovered examples can be used in training with any discriminative loss. The method is applied to unsupervised fine-tuning of pre-trained networks for fine-grained classification and particular object retrieval. Our models are on par or are outperforming prior models that are fully or partially supervised.
Cite
Text
Iscen et al. "Mining on Manifolds: Metric Learning Without Labels." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018. doi:10.1109/CVPR.2018.00797Markdown
[Iscen et al. "Mining on Manifolds: Metric Learning Without Labels." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.](https://mlanthology.org/cvpr/2018/iscen2018cvpr-mining/) doi:10.1109/CVPR.2018.00797BibTeX
@inproceedings{iscen2018cvpr-mining,
title = {{Mining on Manifolds: Metric Learning Without Labels}},
author = {Iscen, Ahmet and Tolias, Giorgos and Avrithis, Yannis and Chum, Ondřej},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2018},
doi = {10.1109/CVPR.2018.00797},
url = {https://mlanthology.org/cvpr/2018/iscen2018cvpr-mining/}
}