提出自适应差分去噪网络，提升呼吸音分类在噪声下的准确性。
Adaptive Differential Denoising for Respiratory Sounds Classification
- 通过可学习频谱掩码与软压缩实现自适应频域去噪。
- 利用差异注意力层减少噪声引起的特征波动，提升稳定性。
- 无需干净标签即可联合优化分类性能与鲁棒性，适合临床应用。
自动呼吸音分类面临背景噪声干扰和现有系统去噪不足的挑战。本文提出自适应差分去噪网络（Adaptive Differential Denoising, ADD），通过三项创新实现降噪与病理特征保留的平衡：1）自适应频域滤波器，采用可学习频谱掩码与软压缩，在抑制噪声的同时保留诊断性高频成分；2）差分去噪层，利用差异注意力机制，通过增强样本对比降低噪声引起的特征变化；3）偏差去噪损失，无需干净标签即可联合优化分类准确率与模型鲁棒性。在ICBHI2017数据集上的实验表明，该方法取得65.53%的Score，较之前SOTA方法提升1.99%。代码已开源：https://github.com/deegy666/ADD-RSC。
原文摘要 · Abstract (English)
Automated respiratory sound classification faces practical challenges from background noise and insufficient denoising in existing systems. We propose Adaptive Differential Denoising network, that integrates noise suppression and pathological feature preservation via three innovations: 1) Adaptive Frequency Filter with learnable spectral masks and soft shrink to eliminate noise while retaining diagnostic high-frequency components; 2) A Differential Denoise Layer using differential attention to reduce noise-induced variations through augmented sample comparisons; 3) A bias denoising loss jointly optimizing classification and robustness without clean labels. Experiments on the ICBHI2017 dataset show that our method achieves 65.53\% of the Score, which is improved by 1.99\% over the previous sota method. The code is available in https://github.com/deegy666/ADD-RSC
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。