On Combining Animal Re-Identification Models to Address Small Datasets

Recent advancements in the automatic re-identification of animal individuals from images have opened up new possibilities for studying wildlife through camera traps and citizen science projects. Existing methods leverage distinct and permanent visual body markings, such as fur patterns or scars, and typically employ one of two approaches: local features or end-to-end learning. The end-to-end learning-based methods outperform local feature-based methods given a sufficient amount of good-quality training data, but the challenge of gathering such datasets for wildlife animals means that local feature-based methods remain a more practical approach for many species. In this study, we aim to achieve two goals: (1) to obtain a better understanding of the impact of training-set size on animal re-identification, and (2) to explore ways to combine various methods to leverage the advantages of their approaches for re-identification. In the work, we conduct comprehensive experiments across six different methods and six animal species with various training set sizes. Furthermore, we propose a simple yet effective combination strategy and show that a properly selected method combinations outperform the individual methods with both small and large training sets up to 30%. Additionally, the proposed combination strategy offers a generalizable framework to improve accuracy across species and address the challenges posed by small datasets, which are common in ecological research. This work lays the foundation for more robust and accessible tools to support wildlife conservation, population monitoring, and behavioral studies.