3 papers
cs.SD2026
Adaptive Loss Balancing for Multi-Task Bioacoustic Classification of Bird Species and Call Types
Paria Vali Zadeh, Sven Tomforde
Reliable analysis of bird vocalisations in passive acoustic monitoring requires models handling multiple, imbalanced annotation targets. We extend BirdCallNet for joint species and…
cs.SD2026
Foundation Models for Bioacoustics -- a Comparative Review
Raphael Schwinger, Paria Vali Zadeh, Lukas Rauch +4
Automated bioacoustic analysis is essential for biodiversity monitoring and conservation, requiring advanced deep learning models that can adapt to diverse bioacoustic tasks. This…
cs.SD2026
Uncertainty Calibration of Multi-Label Bird Sound Classifiers
Raphael Schwinger, Ben McEwen, Vincent S. Kather +3
Passive acoustic monitoring enables large-scale biodiversity assessment, but reliable classification of bioacoustic sounds requires not only high accuracy but also well-calibrated…