Reevaluating Automated Wildlife Species Detection: A Reproducibility Study on a Custom Image Dataset

TL;DR

This study reproduces and evaluates the performance of a pretrained CNN model for wildlife species detection on a new dataset, highlighting reproducibility issues and the need for species-specific adaptation.

Contribution

It demonstrates the reproducibility of previous wildlife detection results and assesses the generalizability of pretrained models across different datasets.

Findings

Overall accuracy of 62%, close to original 71%

Significant variation in per-class performance

Pretrained CNNs serve as practical baselines

Abstract

This study revisits the findings of Carl et al., who evaluated the pre-trained Google Inception-ResNet-v2 model for automated detection of European wild mammal species in camera trap images. To assess the reproducibility and generalizability of their approach, we reimplemented the experiment from scratch using openly available resources and a different dataset consisting of 900 images spanning 90 species. After minimal preprocessing, we obtained an overall classification accuracy of 62%, closely aligning with the 71% reported in the original work despite differences in datasets. As in the original study, per-class performance varied substantially, as indicated by a macro F1 score of 0.28,highlighting limitations in generalization when labels do not align directly with ImageNet classes. Our results confirm that pretrained convolutional neural networks can provide a practical baseline for wildlife species identification but also reinforce the need for species-specific adaptation or transfer learning to achieve consistent, high-quality predictions.