arXiv：cs.LG· Bangxun Tang·· 4 小时前AI 评分37
REFIT：无需标签识别、修复并检测可穿戴传感器佩戴位置偏移
REFIT: Recognize, Fix, and Test Wearable Sensor Placement Shifts without Labels
AI 导读
REFIT 是一种针对冻结活动识别模型的输入校准方法，可在传感器佩戴方式与训练时不同（如手表换腕、绑带反戴）时，无需标签或重训练即可纠正轴向变换偏移。它通过拟合反射、旋转等轴变换族使简单统计量与训练数据匹配来识别偏移，并在冻结模型前应用最佳变换后重新估计归一化统计量。在真实左右传感器配对及真实与模拟重戴实验中，REFIT 在每个数据集上均优于无标签测试时适应方法，并恢复了大部分因重戴损失的精度。
正文
Abstract:We present REFIT, an input calibration for frozen activity-recognition models whose inertial sensors are worn differently at deployment than in training. When users move a watch to the other wrist or put a strap sensor back on turned, the model sees the same motion on changed axes. REFIT undoes such shifts without labels or retraining. It describes them by families of axis transforms, such as reflections and rotations, and fits each family to the user's data so that simple statistics match those of the training data. The family that removes most of the mismatch names the shift. REFIT fixes the shift by applying the best member of that family before the frozen model and re-estimating its normalization statistics. It tests the fixed model with a label-free accuracy estimate and asks the user to re-wear the sensor when it is low. Experiments on real left/right sensor pairs and on real and simulated re-attachment show that REFIT outperforms label-free test-time adaptation methods on every dataset and restores most of the accuracy lost to re-attachment. It names injected shifts far more reliably than a confidence-based selector. After a correction over all signed permutations of the axes, the estimate separates successful from failed corrections.
| Comments: | 25 pages, 5 figures, 14 tables. Under review |
| Subjects: | Machine Learning (cs.LG); Human-Computer Interaction (cs.HC) |
| Cite as: | arXiv:2610.08991 [cs.LG] |
| (or arXiv:2610.08991v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.08991 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Bangxun Tang [view email]
[v1]
Tue, 6 Oct 2026 18:49:52 UTC (1,073 KB)
来源：arXiv：cs.LG · arxiv.org