Cross-domain Activity Recognition via Substructural Optimal Transport

TL;DR

This paper introduces a novel substructure-level domain adaptation method using optimal transport for human activity recognition, significantly improving accuracy and efficiency over existing approaches.

Contribution

It proposes Substructural Optimal Transport (SOT), a new method leveraging activity substructures for better domain adaptation in HAR tasks.

Findings

SOT achieves over 9% accuracy improvement on benchmark datasets.

SOT is 5 times faster than traditional OT-based domain adaptation methods.

The method effectively captures fine-grained locality information for improved transfer learning.

Abstract

It is expensive and time-consuming to collect sufficient labeled data for human activity recognition (HAR). Domain adaptation is a promising approach for cross-domain activity recognition. Existing methods mainly focus on adapting cross-domain representations via domain-level, class-level, or sample-level distribution matching. However, they might fail to capture the fine-grained locality information in activity data. The domain- and class-level matching are too coarse that may result in under-adaptation, while sample-level matching may be affected by the noise seriously and eventually cause over-adaptation. In this paper, we propose substructure-level matching for domain adaptation (SSDA) to better utilize the locality information of activity data for accurate and efficient knowledge transfer. Based on SSDA, we propose an optimal transport-based implementation, Substructural Optimal Transport (SOT), for cross-domain HAR. We obtain the substructures of activities via clustering methods and seeks the coupling of the weighted substructures between different domains. We conduct comprehensive experiments on four public activity recognition datasets (i.e. UCI-DSADS, UCI-HAR, USC-HAD, PAMAP2), which demonstrates that SOT significantly outperforms other state-of-the-art methods w.r.t classification accuracy (9%+ improvement). In addition, our mehtod is 5x faster than traditional OT-based DA methods with the same hyper-parameters.