无需训练即可提升预训练模型在新环境声音分类中的表现
Trainingless Adaptation of Pretrained Models for Environmental Sound Classification
- 通过恢复中间层时频结构实现无训练适配
- 在ESC-50上准确率提升20.4个百分点
- 适合计算资源有限的研究者使用
基于深度神经网络（DNN）的环境声音分类模型对未见领域数据缺乏鲁棒性。传统适应方法如微调和迁移学习需依赖大量计算资源（如GPU），使资源受限的研究者难以跟上前沿。本文提出一种无需训练的预训练模型适配方法，首先设计一种恢复DNN中间层时频结构的操作，进而提出非梯度优化的无训练频率滤波方法。在ESC-50数据集上的实验表明，该方法相比传统方法分类准确率提升20.40个百分点。
原文摘要 · Abstract (English)
Deep neural network (DNN)-based models for environmental sound classification are not robust against a domain to which training data do not belong, that is, out-of-distribution or unseen data. To utilize pretrained models for the unseen domain, adaptation methods, such as finetuning and transfer learning, are used with rich computing resources, e.g., the graphical processing unit (GPU). However, it is becoming more difficult to keep up with research trends for those who have poor computing resources because state-of-the-art models are becoming computationally resource-intensive. In this paper, we propose a trainingless adaptation method for pretrained models for environmental sound classification. To introduce the trainingless adaptation method, we first propose an operation of recovering time--frequency-ish (TF-ish) structures in intermediate layers of DNN models. We then propose the trainingless frequency filtering method for domain adaptation, which is not a gradient-based optimization widely used. The experiments conducted using the ESC-50 dataset show that the proposed adaptation method improves the classification accuracy by 20.40 percentage points compared with the conventional method.
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。