Towards ML Methods for Biodiversity: A Novel Wild Bee Dataset and Evaluations of XAI Methods for ML-Assisted Rare Species Annotations

TL;DR

This paper introduces a new wild bee dataset, evaluates a ResNet model for fine-grained insect classification, and explores XAI methods to aid biologists in annotating rare species.

Contribution

It provides a novel annotated wild bee dataset, trains a competitive ResNet model, and assesses XAI techniques for improving species annotation accuracy.

Findings

ResNet achieved classification scores comparable to state-of-the-art models.

The dataset enables better fine-grained insect classification research.

XAI methods can support biologists in annotating rare species.

Abstract

Insects are a crucial part of our ecosystem. Sadly, in the past few decades, their numbers have worryingly decreased. In an attempt to gain a better understanding of this process and monitor the insects populations, Deep Learning may offer viable solutions. However, given the breadth of their taxonomy and the typical hurdles of fine grained analysis, such as high intraclass variability compared to low interclass variability, insect classification remains a challenging task. There are few benchmark datasets, which impedes rapid development of better AI models. The annotation of rare species training data, however, requires expert knowledge. Explainable Artificial Intelligence (XAI) could assist biologists in these annotation tasks, but choosing the optimal XAI method is difficult. Our contribution to these research challenges is threefold: 1) a dataset of thoroughly annotated images of wild bees sampled from the iNaturalist database, 2) a ResNet model trained on the wild bee dataset achieving classification scores comparable to similar state-of-the-art models trained on other fine-grained datasets and 3) an investigation of XAI methods to support biologists in annotation tasks.