Stratified Active Learning for Spatiotemporal Generalisation in Large-Scale Bioacoustic Monitoring
McEwen, B.; Bernard, C.; Stowell, D.
Show abstract
Active learning optimises machine learning model training through the data-efficient selection of informative samples for annotation and training. In the context of biodiversity monitoring using passive acoustic monitoring, active learning offers a promising strategy to reduce the fundamental annotation bottleneck and improve global training efficiency. However, the generalisability of model performance across ecologically relevant strata (e.g. sites, season etc) is often overlooked. As passive acoustic monitoring is extended to larger scales and finer resolutions, inter-strata spatiotemporal variability also increases. We introduce and investigate the concept of stratified active learning to achieve reliable and generalisable model performance across deployment conditions. We compare between implicit cluster-based diversification methods and explicit stratification, demonstrating that cross-strata generalisation is a function of stratum divergence, not sampling balance. Additionally, mutual information as well as exclusion analysis show that spatiotemporal context can explain a substantial proportion of species label variance and inform sampling decisions.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- Improving the workflow to crack Small, Unbalanced, Noisy, but Genuine (SUNG) datasets in bioacoustics: the case of bonobo calls 94%
- Visualization and quantification of coral reef soundscapes using CoralSoundExplorer software 93%
- Bird song comparison using deep learning trained from avian perceptual judgments 93%
Similar papers in this journal
- DISCO: A deep learning ensemble for uncertainty-aware segmentation of acoustic signals 93%
- Assemblage of Focal Species Recognizers - AFSR: A technique for decreasing false positive rates of acoustic automatic identification in a multiple species context 93%
- Utilizing CNNs for classification and uncertainty quantification for 15 families of European fly pollinators 93%
Similar papers in this journal
- Towards interpretable learned representations for Ecoacoustics using variational auto-encoding 95%
- Insect Size Matters: Using Image and Dimensions Together Improves Image Classification 93%
- Using machine learning to count Antarctic shag (Leucocarbo bransfieldensis) nests on images captured by Remotely Piloted Aircraft Systems 93%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.