About This Document
- sl:arxiv_author :
- sl:arxiv_firstAuthor : Kevin Musgrave
- sl:arxiv_num : 2003.08505
- sl:arxiv_published : 2020-03-18T23:28:04Z
- sl:arxiv_summary : 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.@en
- sl:arxiv_title : A Metric Learning Reality Check@en
- sl:arxiv_updated : 2020-03-18T23:28:04Z
- sl:bookmarkOf : https://arxiv.org/abs/2003.08505
- sl:creationDate : 2020-05-10
- sl:creationTime : 2020-05-10T11:06:07Z
Documents with similar tags (experimental)