AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

MetaPerch: Learning from metadata for bioacoustics foundation models

Mustafa Chasmai, Vincent Dumoulin, Jenny Hamer

ICML 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add location, season and background-species metadata prediction lossesBioBaseline · BirdSet (trained head) meanROC-AUC: 0.891 -> 0.906Improved
add metadata auxiliary lossesBioBaseline · BEANS classification meanaccuracy: 0.854 -> 0.870Improved
add metadata auxiliary lossesBioBaseline · BEANS detection meancmAP: 0.506 -> 0.512Improved
add metadata auxiliary lossesBioBaseline · WABAD (linear probe)ROC-AUC: 0.741 -> 0.811Improved
add metadata auxiliary lossesBioBaseline · WABAD (prototype head)ROC-AUC: 0.928 -> 0.946Improved
add metadata auxiliary lossesBioBaseline · WABAD (1-shot)ROC-AUC: 0.912 -> 0.917Improved
add metadata losses (underrepresented regions PER, UHH, NES)BioBaseline · BirdSetROC-AUC: 0.025 average gain vs 0.006 for HSN, NBP, SSW, SNEImproved
add metadata losses on desert recordingsBioBaseline · WABAD Deserts / Xeric ShrublandsROC-AUC: 0.936 -> 0.912Hurt
add metadata losses on Hainan GibbonsBioBaseline · BEANS GibbonscmAP: 0.519 -> 0.500Hurt
use tuned loss weights instead of dynamic equalization (ablation)MetaPerch · WABAD (prototype head)ROC-AUC: 0.905 -> 0.946Improved
use tuned loss weights instead of gradient surgery (ablation)MetaPerch · WABAD (prototype head)ROC-AUC: 0.944 -> 0.946No clear effect
mix metadata when present in any recording rather than iff all (ablation)MetaPerch · WABAD (prototype head)ROC-AUC: 0.945 -> 0.946No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy