Fine-Grained Visual Classification of Plant Species In The Wild: Object Detection as A Reinforced Means of Attention

TL;DR

This paper proposes a novel approach for plant species identification in the wild by using object detection as a form of attention, combining organ detection with species classification, and introduces a new dataset for evaluation.

Contribution

It introduces a bottom-up method that detects plant organs and fuses multiple organ-based classifiers, along with a new long-tail dataset for evaluation.

Findings

Effective organ detection and classification in wild plants

Improved accuracy over baseline methods

Public availability of a new long-tail dataset

Abstract

Plant species identification in the wild is a difficult problem in part due to the high variability of the input data, but also because of complications induced by the long-tail effects of the datasets distribution. Inspired by the most recent fine-grained visual classification approaches which are based on attention to mitigate the effects of data variability, we explore the idea of using object detection as a form of attention. We introduce a bottom-up approach based on detecting plant organs and fusing the predictions of a variable number of organ-based species classifiers. We also curate a new dataset with a long-tail distribution for evaluating plant organ detection and organ-based species identification, which is publicly available.