无需微调和标注数据，用预训练特征+kNN实现跨域异常声音检测
Deep Generic Representations for Domain-Generalized Anomalous Sound Detection
- 用预训练模型提取通用特征，结合kNN进行异常检测
- 在DCASE2023T2上达到73.79%的官方得分，优于现有方法
- 适合数据稀缺或跨域场景，无需为每类设备重新训练
构建可靠的异常声音检测（ASD）系统需应对噪声、域偏移以及少量训练数据的挑战。现有主流方法依赖每类目标设备的大量标注数据，通过异常暴露（OE）训练特征提取器，但性能仍不理想。本文提出GenRep，利用鲁棒的大规模预训练特征提取器生成通用特征表示，并结合kNN实现跨域泛化检测，无需微调。GenRep引入MemMixup，通过最近源样本增强目标内存库，配合域归一化缓解源-目标域间不平衡问题。在DCASE2023T2 Eval集上，其官方得分为73.79%，优于无需标注数据的最佳OE方法，在低数据场景下也表现稳健。代码开源。
原文摘要 · Abstract (English)
Developing a reliable anomalous sound detection (ASD) system requires robustness to noise, adaptation to domain shifts, and effective performance with limited training data. Current leading methods rely on extensive labeled data for each target machine type to train feature extractors using Outlier-Exposure (OE) techniques, yet their performance on the target domain remains sub-optimal. In this paper, we present \textit{GenRep}, which utilizes generic feature representations from a robust, large-scale pre-trained feature extractor combined with kNN for domain-generalized ASD, without the need for fine-tuning. \textit{GenRep} incorporates MemMixup, a simple approach for augmenting the target memory bank using nearest source samples, paired with a domain normalization technique to address the imbalance between source and target domains. \textit{GenRep} outperforms the best OE-based approach without a need for labeled data with an Official Score of 73.79\% on the DCASE2023T2 Eval set and demonstrates robustness under limited data scenarios. The code is available open-source.
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。