用智能筛选替代盲目扩数据，提升毫米波人体姿态估计的泛化能力
WiCompass: Oracle-driven Data Scaling for mmWave Human Pose Estimation
- 基于动作捕捉库构建通用姿态空间，识别数据冗余与缺失动作
- 闭环策略优先采集高信息量缺失样本，在相同预算下显著提升跨分布准确率
- 适合需要高效数据采集的毫米波感知研究者，尤其关注真实场景鲁棒性
毫米波人体姿态估计（mmWave HPE）具有隐私优势，但在分布外（OOD）场景下泛化能力差。我们证明，盲目扩增数据对提升OOD鲁棒性无效，效率与覆盖度才是关键瓶颈。为此，提出WiCompass——一种覆盖感知的数据采集框架。该框架利用大规模动作捕捉语料库构建通用姿态空间‘预言机’，量化数据冗余并识别未充分覆盖的动作。基于此预言机，采用闭环策略优先采集信息量高的缺失样本。实验表明，WiCompass在相同预算下持续提升OOD准确率，且相比传统采集策略展现出更优的可扩展性。本工作将数据采集重点从暴力扩增转向覆盖感知，为实现稳健的毫米波感知提供了实用路径。
原文摘要 · Abstract (English)
Millimeter-wave Human Pose Estimation (mmWave HPE) promises privacy but suffers from poor generalization under distribution shifts. We demonstrate that brute-force data scaling is ineffective for out-of-distribution (OOD) robustness; efficiency and coverage are the true bottlenecks. To address this, we introduce WiCompass, a coverage-aware data-collection framework. WiCompass leverages large-scale motion-capture corpora to build a universal pose space ``oracle'' that quantifies dataset redundancy and identifies underrepresented motions. Guided by this oracle, WiCompass employs a closed-loop policy to prioritize collecting informative missing samples. Experiments show that WiCompass consistently improves OOD accuracy at matched budgets and exhibits superior scaling behavior compared to conventional collection strategies. By shifting focus from brute-force scaling to coverage-aware data acquisition, this work offers a practical path toward robust mmWave sensing.
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。