Comparing fine-grained and coarse-grained object detection for ecology

TL;DR

This study evaluates how combining species into broader classes and adding negative samples affect the performance of object detection models in wildlife monitoring, providing practical insights for ecological applications.

Contribution

It investigates the impact of class merging and negative samples on model accuracy, offering guidelines for ecological object detection tasks.

Findings

Merging morphologically similar species improves detection accuracy.

Adding negative samples marginally enhances model performance.

Class merging depends on ecological questions and species similarity.

Abstract

Computer vision applications are increasingly popular for wildlife monitoring tasks. While some studies focus on the monitoring of a single species, such as a particular endangered species, others monitor larger functional groups, such as predators. In our study, we used camera trap images collected in north-western New South Wales, Australia, to investigate how model results were affected by combining multiple species in single classes, and whether the addition of negative samples can improve model performance. We found that species that benefited the most from merging into a single class were mainly species that look alike morphologically, i.e. macropods. Whereas species that looked distinctively different gave mixed results when merged, e.g. merging pigs and goats together as non-native large mammals. We also found that adding negative samples improved model performance marginally in most instances, and recommend conducting a more comprehensive study to explore whether the marginal gains were random or consistent. We suggest that practitioners could classify morphologically similar species together as a functional group or higher taxonomic group to draw ecological inferences. Nevertheless, whether to merge classes or not will depend on the ecological question to be explored.