A Metric Learning Reality Check

Abstract

Deep metric learning papers from the past four years have consistently claimed great advances in accuracy, often more than doubling the performance of decade-old methods. In this paper, we take a closer look at the field to see if this is actually true. We find flaws in the experimental setup of these papers, and propose a new way to evaluate metric learning algorithms. Finally, we present experimental results that show that the improvements over time have been marginal at best.

Cite

Text

Musgrave et al. "A Metric Learning Reality Check." Proceedings of the European Conference on Computer Vision (ECCV), 2020. doi:10.1007/978-3-030-58595-2_41

Markdown

[Musgrave et al. "A Metric Learning Reality Check." Proceedings of the European Conference on Computer Vision (ECCV), 2020.](https://mlanthology.org/eccv/2020/musgrave2020eccv-metric/) doi:10.1007/978-3-030-58595-2_41

BibTeX

@inproceedings{musgrave2020eccv-metric,
  title     = {{A Metric Learning Reality Check}},
  author    = {Musgrave, Kevin and Belongie, Serge and Lim, Ser-Nam},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2020},
  doi       = {10.1007/978-3-030-58595-2_41},
  url       = {https://mlanthology.org/eccv/2020/musgrave2020eccv-metric/}
}