首个将预训练模型用于传感器活动识别的在线持续学习方法。
Efficient Online Continual Learning in Sensor-Based Human Activity Recognition
- 用对比损失少量数据预训练特征提取器并冻结，降低计算开销。
- 替换全连接层为关系模块网络，减少标签数据需求。
- 在三个公开数据集上优于现有方法，适合资源受限场景。
面向传感器人体活动识别（HAR）的机器学习模型需在部署后适应新活动及旧活动的新表现方式。为此，提出在线持续学习（OCL）机制，使模型能随新数据增量更新知识并保留已有信息。然而，现有基于传感器的OCL方法计算开销大，且需大量标注样本。近期基于预训练模型（PTM）的OCL在计算机视觉中表现优异，通过大规模预训练和微调实现强泛化能力。但将其应用于传感器HAR面临数据集异质性强、部署后标注数据稀缺等挑战。本文提出PTRN-HAR，首次成功将PTM-based OCL应用于传感器HAR。不同于以往方法，PTRN-HAR仅用少量数据通过对比损失预训练特征提取器，并在流式阶段冻结该提取器；同时以关系模块网络替代传统全连接分类层。实验表明，该设计显著降低训练资源消耗，提升数据效率，仅需较少标注数据即可实现有效持续学习，在三个公开数据集上超越当前最优方法。
原文摘要 · Abstract (English)
Machine learning models for sensor-based human activity recognition (HAR) are expected to adapt post-deployment to recognize new activities and different ways of performing existing ones. To address this need, Online Continual Learning (OCL) mechanisms have been proposed, allowing models to update their knowledge incrementally as new data become available while preserving previously acquired information. However, existing OCL approaches for sensor-based HAR are computationally intensive and require extensive labeled samples to represent new changes. Recently, pre-trained model-based (PTM-based) OCL approaches have shown significant improvements in performance and efficiency for computer vision applications. These methods achieve strong generalization capabilities by pre-training complex models on large datasets, followed by fine-tuning on downstream tasks for continual learning. However, applying PTM-based OCL approaches to sensor-based HAR poses significant challenges due to the inherent heterogeneity of HAR datasets and the scarcity of labeled data in post-deployment scenarios. This paper introduces PTRN-HAR, the first successful application of PTM-based OCL to sensor-based HAR. Unlike prior PTM-based OCL approaches, PTRN-HAR pre-trains the feature extractor using contrastive loss with a limited amount of data. This extractor is then frozen during the streaming stage. Furthermore, it replaces the conventional dense classification layer with a relation module network. Our design not only significantly reduces the resource consumption required for model training while maintaining high performance, but also improves data efficiency by reducing the amount of labeled data needed for effective continual learning, as demonstrated through experiments on three public datasets, outperforming the state-of-the-art. The code can be found here: https://anonymous.4open.science/r/PTRN-HAR-AF60/
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。