AI 中文总结
本研究针对稀疏正标签下的鸟类生物声学监测难题，提出多源可靠性迁移学习框架，在BirdCLEF+ 2026基准上取得优于朴素策略的性能，揭示该领域迁移学习的本质是弱监督与负迁移问题。
AI 中文摘要
被动声学监测是生物多样性评估和野生动物保护的重要工具，它支持在大时空尺度下对物种进行连续、非侵入式监测。然而，由于许多数据集包含稀疏正标签，即仅能确认物种存在，无法假定未标注物种不存在，因此稳健监测仍具挑战性。本研究以BirdCLEF+ 2026为目标基准，以BirdCLEF 2021、iNatSounds、WABAD和BirdSet为外部生物声学源，研究稀疏正标签下的迁移学习。我们提出一种多源可靠性框架，将异构生物声学数据集建模为具有不同可靠性的独立监督源。该方法在公开BirdCLEF+ 2026验证标签上实现了0.584的平均精度和0.860的宏AUC，且优于朴素源池化策略；在被动声学监测数据集及基于生物学信息的源选择中，增益最为显著。研究表明，生物声学领域的迁移学习本质上是弱监督与负迁移问题。
英文摘要
Passive acoustic monitoring is an important tool for biodiversity assessment and wildlife conservation because it supports continuous and non-invasive monitoring of species across large spatial and temporal scales. Robust monitoring remains challenging because many datasets contain sparse positive labels, where species presences may be confirmed while unannotated species cannot be assumed absent. In this work, we study transfer learning under sparse positive labels using BirdCLEF+ 2026 as a target benchmark and BirdCLEF 2021, iNatSounds, WABAD, and BirdSet as external bioacoustic sources. We introduce a multi-source reliability framework that models heterogeneous bioacoustic datasets as distinct supervision sources with differing reliability. Our approach achieves 0.584 macro average precision and 0.860 macro AUC on public BirdCLEF+ 2026 validation labels while outperforming naive source pooling strategies. The strongest gains arise from passive acoustic monitoring datasets and biologically informed source selection. Our findings suggest that transfer learning in bioacoustics is fundamentally a weak supervision and negative transfer problem.
CommentsAccepted to IEEE MLSP 2026
