Affiliations 

  • 1 GLAM - Group on Language, Audio, & Music, Department of Computing, Imperial College London, London SW7 2RH, UK
  • 2 Department of Life Sciences, Imperial College London, Ascot SL5 7PY, UK
  • 3 DICE - Durrell Institute of Conservation and Ecology, University of Kent, Canterbury CT2 7NR, UK
Patterns (N Y), 2024 Mar 08;5(3):100932.
PMID: 38487806 DOI: 10.1016/j.patter.2024.100932

Abstract

Along with propagating the input toward making a prediction, Bayesian neural networks also propagate uncertainty. This has the potential to guide the training process by rejecting predictions of low confidence, and recent variational Bayesian methods can do so without Monte Carlo sampling of weights. Here, we apply sample-free methods for wildlife call detection on recordings made via passive acoustic monitoring equipment in the animals' natural habitats. We further propose uncertainty-aware label smoothing, where the smoothing probability is dependent on sample-free predictive uncertainty, in order to downweigh data samples that should contribute less to the loss value. We introduce a bioacoustic dataset recorded in Malaysian Borneo, containing overlapping calls from 30 species. On that dataset, our proposed method achieves an absolute percentage improvement of around 1.5 points on area under the receiver operating characteristic (AU-ROC), 13 points in F1, and 19.5 points in expected calibration error (ECE) compared to the point-estimate network baseline averaged across all target classes.

* Title and MeSH Headings from MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine.