Improving Wildlife Out-of-Distribution Detection: Africas Big Five

TL;DR

This paper explores out-of-distribution detection methods for wildlife classification, focusing on the Big Five African animals, and demonstrates that feature-based approaches outperform existing methods in generalization and accuracy.

Contribution

It introduces and compares parametric and non-parametric OOD detection methods using pretrained features for wildlife, highlighting the effectiveness of feature-based approaches.

Findings

NCM with ImageNet features improves OOD detection metrics significantly.

Feature-based methods outperform traditional OOD detection techniques.

Pretrained features enhance generalization across varying thresholds.

Abstract

Mitigating human-wildlife conflict seeks to resolve unwanted encounters between these parties. Computer Vision provides a solution to identifying individuals that might escalate into conflict, such as members of the Big Five African animals. However, environments often contain several varied species. The current state-of-the-art animal classification models are trained under a closed-world assumption. They almost always remain overconfident in their predictions even when presented with unknown classes. This study investigates out-of-distribution (OOD) detection of wildlife, specifically the Big Five. To this end, we select a parametric Nearest Class Mean (NCM) and a non-parametric contrastive learning approach as baselines to take advantage of pretrained and projected features from popular classification encoders. Moreover, we compare our baselines to various common OOD methods in the literature. The results show feature-based methods reflect stronger generalisation capability across varying classification thresholds. Specifically, NCM with ImageNet pre-trained features achieves a 2%, 4% and 22% improvement on AUPR-IN, AUPR-OUT and AUTC over the best OOD methods, respectively. The code can be found here https://github.com/pxpana/BIG5OOD