A Metric Learning Reality Check
European Conference on Computer Vision(2020)
摘要
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 methodology of numerous metric learning papers, and show that the actual improvements over time have been marginal at best. Code is available at github.com/KevinMusgrave/powerful-benchmarker.
更多查看译文
关键词
Deep metric learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要