LifeCLEF 2020 Plant Identification Challenge
Description
Despite recent progress in automated plant identification, a vast majority of the 300K+ plant species on earth can still not be recognized easily because of the lack of training data for that species. On the other side, for several centuries, botanists have collected, catalogued and systematically stored plant specimens in herbaria. These physical specimens are used to study the variability of species, their phylogenetic relationship, their evolution, or phenological trends. Millions of such specimens are now digitized and publicly available. Using them for training deep learning models is thus a very promising approach to help identifying data deficient species. However, their visual appearance is very different from field pictures which makes it a challenging cross-domain classification task.
The goal of the challenge is to identify plants in field pictures based on a training set of digitized herbarium specimens. Concretely, this will consist in a cross-domain classification task with a training set composed of digitized herbarium sheets and a test set composed of field pictures. To enable learning a mapping between the herbarium sheets domain and the field pictures domain, we will provide both herbarium sheets and field pictures for a subset of species.
This dataset is used in the context of LifeCLEF Plant Identification:
https://www.aicrowd.com/challenges/lifeclef-2020-plant
Notes
Files
Files
(36.1 GB)
Name | Size | Download all |
---|---|---|
md5:b76663bafc070b6b161c34571f2b45dd
|
36.1 GB | Download |