Wearable human activity recognition (WHAR) models often suffer from performance degradation under real-world cross-user distribution shifts. Test-time adaptation (TTA) mitigates this degradation by adapting models online using unlabeled test streams, yet existing methods largely inherit assumptions from vision tasks and underexploit the inherent inter-window temporal structure in WHAR streams. In this paper, we revisit such temporal structure as a feature-conditioned inference signal rather than merely an output-space smoothing prior. We derive the insight that temporal continuity and observation-induced feature deviations provide complementary cues for determining when to preserve or release temporal inertia and where to route prediction refinement during likely transitions. Building upon this insight, we propose SIGHT, a lightweight and backpropagation-free TTA framework for WHAR, enabling real-time edge deployment. SIGHT estimates predictive surprise by comparing the current feature with a prototype-based expected state, and then uses the resulting feature deviation to guide geometry-aware transition routing based on prototype alignment and stream-level marginal habit tracking. Evaluations on real-world datasets confirm that SIGHT outperforms existing TTA baselines while reducing computational and memory costs.

翻译：可穿戴人体活动识别（WHAR）模型在实际跨用户分布偏移场景中常出现性能衰退。测试时自适应（TTA）方法通过利用无标注测试流在线调整模型来缓解这种衰退，然而现有方法大多沿用视觉任务中的假设，未能充分利用WHAR数据流中固有的窗口间时序结构。本文重新审视该时序结构，将其视为一种以特征为条件的推理信号，而非仅作为输出空间的平滑先验。我们提出关键见解：时序连续性与观测引发的特征偏差能提供互补线索，用以判定何时保持或释放时序惯性，以及在潜在状态转换期间引导预测细化的路由方向。基于此见解，我们提出SIGHT——一种轻量级、无需反向传播的WHAR自适应框架，可实现实时边缘端部署。SIGHT通过比较当前特征与基于原型的期望状态来估计预测惊奇度，进而利用所得特征偏差指导基于原型对齐与流级边际习惯追踪的几何感知转换路由。真实数据集评估证实，SIGHT在降低计算与内存开销的同时，性能超越现有TTA基线方法。