Problem
Research questions and friction points this paper is trying to address.
Human Activity Recognition
Domain Generalization
Distribution Shifts
Smartphone-based
Domain Generalization for Smartphone-Based Human Activity Recognition: A Systematic Analysis of Components and Interactions
🤖 AI Summary
本文通过系统分析多种组件及其交互作用，采用域泛化方法解决智能手机活动识别模型在不同分布偏移下的性能下降问题。
📝 Abstract
Smartphone-based Human Activity Recognition (HAR) models often degrade under distribution shifts caused by changes in users, devices, sensor placements, environments, and acquisition protocols. Domain Generalization (DG) addresses this problem by learning from source domains without access to target data. Existing DG methods span training objectives, representation initialization, and architectural modifications, but these components are typically evaluated in isolation despite operating at different stages of the learning pipeline. We present a large-scale controlled benchmark of DG for smartphone-based HAR, comprising more than 410,000 experiments across four model architectures, thirteen training objectives including Empirical Risk Minimization (ERM), five initialization strategies, four architectural configurations, and two shift scenarios: cross-dataset and cross-position. Results show that individual DG components provide limited and highly conditional gains. Alternative objectives rarely outperform ERM consistently, self-supervised initialization helps in specific settings, and architectural modifications, particularly Dynamic Domain Generalization, provide the clearest standalone improvements. Joint configurations, however, frequently outperform their individual components and exhibit complementary and sometimes super-additive interactions, although gains remain model- and shift-dependent. Class-level analysis shows that the strongest configurations mainly improve difficult, shift-sensitive decision boundaries. Finally, oracle checkpoint analysis reveals substantial unrealized performance: source-validation selection recovers only 53% and 26% of the available oracle gain in cross-dataset and cross-position settings, respectively. Overall, effective HAR domain generalization requires jointly designing DG components and robust model-selection strategies.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Domain Generalization
Human Activity Recognition
Dynamic Domain Generalization
Training Objectives
Initialization Strategies
🔎 Similar Papers
No similar papers found.
