arXiv：cs.LG· Marius Bock, Yuwei Zhang, Juergen Gall, Michael Moeller, Kristof Van Laerhoven, Cecilia Mascolo·· 4 小时前AI 评分33
MorphCL：面向惯性人体活动识别的形态学对比学习
MorphCL: Morphological Contrastive Learning for Inertial-based Human Activity Recognition
AI 导读
MorphCL 是一种自监督预训练框架，通过结构感知分组把全局结构显式建模引入惯性数据 SSL，将学习编码器的线性探测与微调 F1-score 最高提升 15 个百分点。与现有基础模型相比，其预训练编码器在线性探测上持平或超越，而训练数据用量少 4600 倍。嵌入空间还呈现形态学上有意义的聚类结构，改善了运动学相似活动类别的分离。
正文
Abstract:Despite the ubiquity of sensors in wearable and mobile devices and the abundance of human movement data they generate, translating unlabeled recordings into foundational motion models remains an open challenge. Self-supervised learning (SSL) has alleviated the need for costly annotations, yet existing approaches leave the global structure of large-scale motion data largely untapped, relying on randomly sampled batches and local comparisons that become particularly problematic for in-the-wild inertial data dominated by stationary, low-variance behaviors. Here we introduce Morphological Contrastive Learning (MorphCL), a self-supervised pretraining framework that uses structure-aware grouping to inject explicit modeling of global structure into inertial-based SSL approaches. Building on two well-established pillars of motion analysis, the discovery of motion primitives, or motifs, and domain-specific feature descriptors, we show that MorphCL substantially improves linear probing and finetuning results of learned encoders by up to 15 percentage points in F1-score. In a comparison with existing foundation models, we demonstrate that MorphCL-pretrained encoders match or surpass them models in linear probing performance while trained on $4600\times$ less data. Qualitative analysis of the resulting embedding spaces further reveals morphologically meaningful cluster structure, with improved separation of kinematically similar activity classes.
| Subjects: | Machine Learning (cs.LG); Human-Computer Interaction (cs.HC) |
| Cite as: | arXiv:2610.10245 [cs.LG] |
| (or arXiv:2610.10245v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.10245 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Marius Bock [view email]
[v1]
Wed, 7 Oct 2026 15:27:48 UTC (2,360 KB)
来源：arXiv：cs.LG · arxiv.org