Overview of LifeCLEF Plant Identification task 2019: diving into data deficient tropical countries

TL;DR

The paper discusses the 2019 LifeCLEF Plant Identification challenge, which evaluates automated plant identification in data-deficient tropical regions using a specialized dataset and compares system performance with tropical flora experts.

Contribution

It introduces a new dataset focused on tropical biodiversity and provides an analysis of system performances in challenging, data-scarce environments.

Findings

Systems achieved competitive accuracy with expert performance

Diverse approaches yielded varying success in tropical plant identification

The dataset highlights the need for improved models in data-deficient regions

Abstract

Automated identification of plants has improved considerably thanks to the recent progress in deep learning and the availability of training data. However, this profusion of data only concerns a few tens of thousands of species, while the planet has nearly 369K. The LifeCLEF 2019 Plant Identification challenge (or "PlantCLEF 2019") was designed to evaluate automated identification on the flora of data deficient regions. It is based on a dataset of 10K species mainly focused on the Guiana shield and the Northern Amazon rainforest, an area known to have one of the greatest diversity of plants and animals in the world. As in the previous edition, a comparison of the performance of the systems evaluated with the best tropical flora experts was carried out. This paper presents the resources and assessments of the challenge, summarizes the approaches and systems employed by the participating research groups, and provides an analysis of the main outcomes.