Plant identification based on noisy web data: the amazing performance of deep learning (LifeCLEF 2017)

TL;DR

This paper evaluates the effectiveness of deep learning for large-scale plant identification using noisy web data, demonstrating competitive performance despite label errors, and compares web-sourced data with expert-verified datasets.

Contribution

It introduces a large-scale plant identification challenge using noisy web data and analyzes the performance of deep learning models trained on such data versus trusted datasets.

Findings

Deep learning models perform well with noisy web data.

Web-sourced data can rival expert-verified datasets in plant identification.

The challenge provides insights into large-scale, real-world plant classification.

Abstract

The 2017-th edition of the LifeCLEF plant identification challenge is an important milestone towards automated plant identification systems working at the scale of continental floras with 10.000 plant species living mainly in Europe and North America illustrated by a total of 1.1M images. Nowadays, such ambitious systems are enabled thanks to the conjunction of the dazzling recent progress in image classification with deep learning and several outstanding international initiatives, such as the Encyclopedia of Life (EOL), aggregating the visual knowledge on plant species coming from the main national botany institutes. However, despite all these efforts the majority of the plant species still remain without pictures or are poorly illustrated. Outside the institutional channels, a much larger number of plant pictures are available and spread on the web through botanist blogs, plant lovers web-pages, image hosting websites and on-line plant retailers. The LifeCLEF 2017 plant challenge presented in this paper aimed at evaluating to what extent a large noisy training dataset collected through the web and containing a lot of labelling errors can compete with a smaller but trusted training dataset checked by experts. To fairly compare both training strategies, the test dataset was created from a third data source, i.e. the Pl@ntNet mobile application that collects millions of plant image queries all over the world. This paper presents more precisely 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.