Weakly Supervised Multiple Instance Learning for Whale Call Detection and Localization in Long-Duration Passive Acoustic Monitoring

Marine ecosystem monitoring via Passive Acoustic Monitoring (PAM) generates vast data, but deep learning often requires precise annotations and short segments. We introduce DSMIL-LocNet, a Multiple Instance Learning framework for whale call detection and localization using only bag-level labels. Our dual-stream model processes 2-30 minute audio segments, leveraging spectral and temporal features with attention-based instance selection. Tests on Antarctic whale data show longer contexts improve classification (F1: 0.8-0.9) while medium instances ensure localization precision (0.65-0.70). This suggests MIL can enhance scalable marine monitoring. Code:this https URL

@article{nihal2025_2502.20838,
  title={ Weakly Supervised Multiple Instance Learning for Whale Call Detection and Localization in Long-Duration Passive Acoustic Monitoring },
  author={ Ragib Amin Nihal and Benjamin Yen and Runwu Shi and Kazuhiro Nakadai },
  journal={arXiv preprint arXiv:2502.20838},
  year={ 2025 }
}