留一受试者评估下的高效架构搜索
Efficient Architecture Search under Leave-One-Subject-Out Evaluation
浏览论文内容
中文总结 AI 辅助
本文提出PainNAS，一种基于块且防泄漏的神经架构搜索方法，在留一受试者评估中通过共享搜索将计算复杂度从O(N^2)降至O(B)，在BioVid数据集上以更少参数和FLOPs保持相当准确率。
中文摘要 AI 辅助
深度神经架构广泛用于自动疼痛评估系统中的信号处理。然而，尽管神经架构搜索（NAS）具有潜在的效率优势，架构设计在很大程度上仍是一项手动任务。将NAS嵌入留一受试者（LOSO）评估在计算上要求很高，因为完全嵌套的实现需要$N$次独立的架构搜索，并且假设训练成本近似线性，其规模为$\mathcal{O}(N^2)$。我们提出了一种基于块、防泄漏的方法，在受试者之间共享NAS运行，将搜索次数从$N$减少到$B$，其中$B \ll N$，称为PainNAS。在BioVid热痛数据集上，PainNAS在显著减少参数和FLOPs的情况下，达到了相当的受试者级准确率。
英文摘要
Deep neural architectures are widely used for signal processing in automated pain assessment systems. However, architecture design has remained largely a manual task despite the potential efficiency benefits of Neural Architecture Search (NAS). Embedding NAS in a Leave-One-Subject-Out (LOSO) evaluation is computationally demanding because a fully nested implementation requires $N$ independent architecture searches and, assuming approximately linear training cost, scales as $\mathcal{O}(N^2)$. We propose a block-based, leakage-controlled approach that shares NAS runs between subjects, reducing the number of searches from $N$ to $B$, where $B \ll N$, dubbed PainNAS. On the BioVid Heat Pain dataset, PainNAS yields comparable subject-level accuracy with substantially fewer parameters and FLOPs.
发表机构
- IU International University of Applied Sciences（IU国际应用科学大学）
- Ulm University（乌尔姆大学）
机构由 AI 辅助整理，请以论文原文为准。
