ARGUS：用于利用Wi-Fi遥测技术实现可扩展人员识别的注意力引导Transformer
ARGUS: Attention-Guided Transformers for Scalable Person Identification Using Wi-Fi Telemetry
浏览论文内容
中文总结 AI 辅助
本文提出Argus系统，通过注意力引导Transformer处理Wi-Fi CSI实现无设备被动人员识别，在154人数据集上获高准确率，同时大幅降低计算量，还在多用户基准上表现优异并揭示部署限制。
中文摘要 AI 辅助
无设备的被动人员识别为基于摄像头和可穿戴设备的生物识别技术提供了另一种选择，然而现有的无线方法大多依赖步态或活动线索，且很少在大规模场景下进行评估。本文提出了Argus，一种被动Wi-Fi感知系统，它能从商用信道状态信息（CSI）中识别人，无需附加设备或规定动作。Argus将短时间的CSI片段转换为紧凑的statgrams：基于给定设备上可用信道视图构建的统计映射。一个轻量级的仅解码器Transformer随后将粗略的statgram补丁作为标记读取，而片段级别的logit聚合则整合了随时间变化的证据。在包含154个受试者的CSI数据集上，采用严格的物理片段划分进行评估，Argus在6秒窗口的Top-1准确率达到78.88%±1.62%，在对60秒片段内的19个重叠窗口进行聚合后，准确率提升至84.85%±1.31%；Top-3和Top-5准确率分别达到98.61%和99.26%。对于60秒的statgram，Argus与原始CSI Transformer基线相比，准确率提升了7.75个百分点，同时每个窗口的浮点运算量（FLOPs）减少了4.4倍。注意力引导的压缩仅使用一半的EHealth补丁即可保持完整的单窗口准确率。在WiMANS（一个跨三个房间和两个Wi-Fi频段的多用户基准）上，Argus平均与最强的每个配置基线的准确率差距在1.23个百分点以内，同时推理FLOPs减少了27倍。这些结果表明，紧凑的CSI统计数据能够实现可扩展的被动识别，同时也揭示了其在开放集拒绝和跨房间迁移方面的部署限制。
英文摘要
Passive, device-free person identification offers an alternative to camera- and wearable-based biometrics, yet existing wireless approaches rely largely on gait or activity cues and are rarely evaluated at scale. In this paper, we present \emph{Argus}, a passive Wi-Fi sensing system that identifies people from commodity Channel State Information (CSI) without requiring an attached device or a prescribed motion. Argus converts short CSI spans into compact \emph{statgrams}: statistical maps built from the channel views available on a given device. A lightweight decoder-only Transformer then reads coarse statgram patches as tokens, and segment-level logit aggregation combines evidence over time. On a 154-subject CSI dataset evaluated with a strict physical-segment split, Argus reaches $78.88\% \pm 1.62\%$ Top-1 accuracy on 6-second windows and $84.85\% \pm 1.31\%$ after aggregating 19 overlapping windows over a 60-second segment; Top-3 and Top-5 reach $98.61\%$ and $99.26\%$. For a 60-second statgram, Argus improves over a raw-CSI Transformer baseline by 7.75 points while using $4.4\times$ fewer FLOPs per window. Attention-guided compression preserves full single-window accuracy with only half of the EHealth patches. On WiMANS, a multi-user benchmark across three rooms and two Wi-Fi bands, Argus remains within 1.23 percentage points of the strongest per-configuration baselines on average while using $27\times$ fewer inference FLOPs. These results show that compact CSI statistics can scale passive identification while also exposing deployment limits in open-set rejection and cross-room transfer.
