用边界提议网络提升鲸鱼叫声检测准确率，显著降低误报。
WhaleVAD-BPN: Improving Baleen Whale Call Detection with Boundary Proposal Networks and Post-processing Optimisation
- 引入边界提议网络，利用中间特征动态控制输出，减少误检。
- 对少数类叫声（d-call、bp-call）的F1值分别提升21.3%和9.4%。
- 通过搜索优化后处理参数，系统整体F1提升9.8%，适合海洋声学研究者。
尽管现有声音事件检测（SED）系统能识别海洋音频中的须鲸叫声，但误报和少数类别检测仍存挑战。本文提出边界提议网络（BPN），扩展了轻量级现有SED系统。BPN受图像目标检测启发，利用骨干分类模型内的中间隐层表示来门控最终输出，从而减少误报。在原有系统中加入BPN后，精度绝对提升16.8%，对少数类d-call和bp-call的F1值分别提升21.3%和9.4%。此外，我们提出前向搜索与后向搜索两种后处理超参数选择方法，分别优化事件级与帧级参数，性能显著优于经验法设定。完整WhaleVAD-BPN系统在交叉验证下的开发集F1得分为0.475，相比基线绝对提升9.8%。
原文摘要 · Abstract (English)
While recent sound event detection (SED) systems can identify baleen whale calls in marine audio, challenges related to false positive and minority-class detection persist. We propose the boundary proposal network (BPN), which extends an existing lightweight SED system. The BPN is inspired by work in image object detection and aims to reduce the number of false positive detections. It achieves this by using intermediate latent representations computed within the backbone classification model to gate the final output. When added to an existing SED system, the BPN achieves a 16.8 % absolute increase in precision, as well as 21.3 % and 9.4 % improvements in the F1-score for minority-class d-calls and bp-calls, respectively. We further consider two approaches to the selection of post-processing hyperparameters: a forward-search and a backward-search. By separately optimising event-level and frame-level hyperparameters, these two approaches lead to considerable performance improvements over parameters selected using empirical methods. The complete WhaleVAD-BPN system achieves a cross-validated development F1-score of 0.475, which is a 9.8 % absolute improvement over the baseline.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。