Applying the MFFT active learning strategy to bioacoustic sound event detection reaches 68-71% mAP with 2.3% of labels, close to the 75% fully supervised baseline.
Robust sound event detection in bioacoustic sensor networks,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Hybrid Disagreement-Diversity Active Learning for Bioacoustic Sound Event Detection
Applying the MFFT active learning strategy to bioacoustic sound event detection reaches 68-71% mAP with 2.3% of labels, close to the 75% fully supervised baseline.