发表机构
University of Bonn; University of Cambridge; University of Siegen; Lamarr Institute for Machine Learning and Artificial Intelligence（波恩大学; 剑桥大学; 锡根大学; 拉马尔机器学习和人工智能研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
MorphCL提出形态对比学习框架，通过结构感知分组注入全局结构，显著提升惯性活动识别编码器性能，F1分数最高提升15个百分点，且训练数据减少4600倍。
AI 中文摘要
尽管传感器在可穿戴和移动设备中无处不在，并且它们产生大量人体运动数据，但将未标记的记录转化为基础运动模型仍然是一个开放的挑战。自监督学习（SSL）减轻了对昂贵标注的需求，然而现有方法在很大程度上未充分利用大规模运动数据的全局结构，依赖于随机采样的批次和局部比较，这对于以静止、低方差行为为主的野外惯性数据尤其成问题。在此，我们引入了形态对比学习（MorphCL），一种自监督预训练框架，利用结构感知分组将全局结构的显式建模注入到基于惯性的SSL方法中。基于运动分析的两个成熟支柱，即运动基元（或主题）的发现和特定领域的特征描述符，我们展示了MorphCL显著提高了学习编码器的线性探测和微调结果，F1分数最多提升15个百分点。在与现有基础模型的比较中，我们证明了MorphCL预训练的编码器在线性探测性能上达到或超越这些模型，同时训练数据量减少了4600倍。对所得嵌入空间的定性分析进一步揭示了具有形态学意义的聚类结构，改善了运动学相似活动类别的分离。
英文摘要
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.
