The 5th edition of ACM GoodIT took place from 3 to 5 September 2025 in Antwerp, Belgium. The International Conference on Information Technology for Social Good is a premier international conference focusing on research and developments of Information Technologies for social good.
Hannes Kath presented the work “Speeding Up Bioacoustic Data Analysis: Fine-Tuning Deep Models with Active Learning for Efficient Wildlife Detection”. The research addresses the growing challenge of efficiently analyzing large-scale bioacoustic data to monitor biodiversity loss. The study demonstrates how fine-tuning transfer learning models combined with active learning can significantly accelerate passive acoustic monitoring (PAM) data analysis. A key contribution is the use of dynamically increasing batch sizes for sample selection, achieving an optimal balance between computation time and model performance.
This work paves the way for user-friendly and scalable tools for biodiversity monitoring and promotes the wider adoption of PAM technologies.
