不用训练就能选好穿戴设备动作识别模型，省时省力
Models Got Talent: Identifying High Performing Wearable Human Activity Recognition Models Without Training
- 用一次前向传播快速评估模型性能，替代耗时训练
- 选出的模型性能接近全量训练结果，误差小于5%
- 对数据噪声鲁棒，适合真实场景中的模型筛选
一种替代计算成本高昂的神经架构搜索（NAS）的方法是开发零成本代理（ZCP），其能通过在随机采样数据批上进行一次前向/反向传播，就与训练后性能高度相关。本文研究了六种基准数据集上ZCP在可穿戴人体动作识别（HAR）中的有效性，结果表明，它能从1500个随机采样的架构中发现性能仅比全量训练低5%的优秀模型，显著节省计算资源。实验不仅首次将ZCP引入基于传感器的HAR任务，还证明其对数据噪声具有鲁棒性，展现出在实际应用中的适用性。
原文摘要 · Abstract (English)
A promising alternative to the computationally expensive Neural Architecture Search (NAS) involves the development of Zero Cost Proxies (ZCPs), which correlate well with trained performance, but can be computed through a single forward/backward pass on a randomly sampled batch of data. In this paper, we investigate the effectiveness of ZCPs for HAR on six benchmark datasets, and demonstrate that they discover network architectures that obtain within 5% of performance attained by full-scale training involving 1500 randomly sampled architectures. This results in substantial computational savings as high-performing architectures can be discovered with minimal training. Our experiments not only introduce ZCPs to sensor-based HAR, but also demonstrate that they are robust to data noise, further showcasing their suitability for practical scenarios.
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。