Deep Randomized Ensembles for Metric Learning
Abstract
Learning embedding functions, which map semantically related inputs to nearby locations in a feature space supports a variety of classification and information retrieval tasks. In this work, we propose a novel, generalizable and fast method to define a family of embedding functions that can be used as an ensemble to give improved results. Each embedding function is learned by randomly bagging the training labels into small subsets. We show experimentally that these embedding ensembles create effective embedding functions. The ensemble output defines a metric space that improves state of the art performance for image retrieval on CUB-200-2011, Cars-196, In-Shop Clothes Retrieval and VehicleID.
Cite
Text
Xuan et al. "Deep Randomized Ensembles for Metric Learning." Proceedings of the European Conference on Computer Vision (ECCV), 2018. doi:10.1007/978-3-030-01270-0_44Markdown
[Xuan et al. "Deep Randomized Ensembles for Metric Learning." Proceedings of the European Conference on Computer Vision (ECCV), 2018.](https://mlanthology.org/eccv/2018/xuan2018eccv-deep/) doi:10.1007/978-3-030-01270-0_44BibTeX
@inproceedings{xuan2018eccv-deep,
title = {{Deep Randomized Ensembles for Metric Learning}},
author = {Xuan, Hong and Souvenir, Richard and Pless, Robert},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2018},
doi = {10.1007/978-3-030-01270-0_44},
url = {https://mlanthology.org/eccv/2018/xuan2018eccv-deep/}
}