Ben McEwen

This paper develops data-driven sampling strategies to improve bird detection models by selecting the most impactful samples for fine-tuning with limited annotations.

This paper describes the BioDCASE data challenge, which aims to advance computational bioacoustics through structured public contests, and reports on its procedures, tasks, and recommendations for community initiatives.

This paper introduces stratified active learning to improve model generalisation across spatiotemporal strata in bioacoustic monitoring.