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

TL;DR

This paper presents DSMIL-LocNet, a weakly supervised learning framework that effectively detects and localizes whale calls in long-duration acoustic data using only segment-level labels, improving scalability in marine monitoring.

Contribution

Introduction of DSMIL-LocNet, a novel dual-stream MIL framework that processes long audio segments for whale call detection and localization with minimal supervision.

Findings

Longer audio contexts improve classification accuracy (F1: 0.8-0.9).

Medium-sized instances enhance localization precision (0.65-0.70).

MIL approach enables scalable marine acoustic monitoring.

Abstract

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: https://github.com/Ragib-Amin-Nihal/DSMIL-Loc