3.8 Proceedings Paper

Rove-Tree-11: The Not-so-Wild Rover a Hierarchically Structured Image Dataset for Deep Metric Learning Research

期刊

COMPUTER VISION - ACCV 2022, PT V
卷 13845, 期 -, 页码 425-441

出版社

SPRINGER INTERNATIONAL PUBLISHING AG
DOI: 10.1007/978-3-031-26348-4_25

关键词

Phylogeny; Dataset; Tree; Hierarchy; Hierarchical dataset; Rove; Staphylinidae; Phylogenetic tree

向作者/读者索取更多资源

We introduce a new dataset containing images of pinned insects with a known phylogeny, which can be used for clustering and deep hierarchical metric learning. This is the first dataset specifically created for generating phylogenetic trees. We also provide benchmarks for deep metric learning using state-of-the-art methods.
We present a new dataset of images of pinned insects from museum collections along with a ground truth phylogeny (a graph representing the relative evolutionary distance between species). The images include segmentations, and can be used for clustering and deep hierarchical metric learning. As far as we know, this is the first dataset released specifically for generating phylogenetic trees. We provide several benchmarks for deep metric learning using a selection of state-of-the-art methods.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

3.8
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据