Research Papers 论文研究 5h ago Updated 1h ago 更新于 1小时前 43

Dynamic Influence-Weighted Distillation for Single-IMU Activity Recognition 动态影响加权蒸馏用于单IMU活动识别

Dynamic Influence-Weighted Distillation (DIW) enables a single right-arm IMU student model to leverage multi-IMU training data from four body locations without requiring all sensors at inference time DIW introduces sample-wise adaptive gating for both logit and feature distillation losses, determined by testing one-step candidate updates on held-out fold-internal training participants On the WEAR dataset (19 activity labels, 68,298 windows, 22 participants), DIW achieves a macro-F1 of 0.638451, 提出动态影响加权(DIW)知识蒸馏方法,利用训练时四个同步IMU的信息改进推理时仅需右臂单IMU的活动识别模型 在WEAR数据集上,DIW的macro-F1达到0.638451,相比监督学习提升7.66个百分点,相比固定权重KD提升6.68个百分点 通过样本级门控机制动态分配logit和特征损失权重,在19个标签中18个、22名参与者中21名均超越监督学习基线 推理时保持仅80,915参数的单IMU学生模型,无需改变部署传感器配置或前向计算图

55
Hot 热度
72
Quality 质量
62
Impact 影响力

Analysis 深度分析

TL;DR

  • Dynamic Influence-Weighted Distillation (DIW) enables a single right-arm IMU student model to leverage multi-IMU training data from four body locations without requiring all sensors at inference time
  • DIW introduces sample-wise adaptive gating for both logit and feature distillation losses, determined by testing one-step candidate updates on held-out fold-internal training participants
  • On the WEAR dataset (19 activity labels, 68,298 windows, 22 participants), DIW achieves a macro-F1 of 0.638451, outperforming supervised learning (0.561820) by 7.66 percentage points and fixed-weight KD (0.571623) by 6.68 percentage points
  • The student model retains only 80,915 parameters at inference, using the same single right-arm IMU input across all approaches, making deployment practically unchanged
  • DIW exceeds supervised performance on 18 of 19 activity labels and 21 of 22 held-out participants, demonstrating robust generalization across subjects and activities

Why It Matters

This work addresses a critical deployment bottleneck in wearable-based activity recognition: the gap between multi-sensor training setups and single-sensor inference constraints. By showing that multi-position IMU data can effectively distill into a lightweight single-IMU model through adaptive weighting, it offers a practical pathway for reducing hardware costs and user burden in real-world deployments without sacrificing accuracy.

Technical Details

  • Architecture: A frozen four-IMU teacher model provides both logit and feature-level distillation targets to a smaller right-arm-only student model (80,915 parameters), with no changes to the student's forward computation graph at inference
  • Dynamic Influence Weighting (DIW): For each training sample, DIW evaluates a one-step candidate parameter update on a held-out subset of fold-internal training participants, then assigns separate adaptive gates to the logit loss and feature loss components based on their individual influence
  • Baseline comparison: Fixed-weight knowledge distillation applies uniform loss weights across all samples, while DIW dynamically modulates per-sample contribution, recognizing that not all training samples benefit equally from multi-IMU teacher signals
  • Evaluation protocol: Subject-disjoint five-fold cross-validation on the WEAR dataset with 22 participants, 19 activity labels, and 68,298 complete windows, ensuring generalization to unseen users
  • Performance gains: DIW achieves macro-F1 of 0.638451 versus 0.561820 (supervised) and 0.571623 (fixed-weight KD), with consistent improvements across nearly all labels and participants

Industry Insight

  • The DIW approach demonstrates that careful sample-level weighting during distillation can unlock significant value from multi-sensor training data, suggesting that similar adaptive weighting strategies could benefit other sensor-fusion-to-single-sensor compression scenarios in wearable and IoT applications
  • The near-universal improvement across 18/19 labels and 21/22 participants indicates that the method generalizes well to unseen users, a critical factor for commercial deployment where per-user calibration is impractical
  • The minimal parameter footprint (80,915 parameters) combined with single-IMU inference makes this approach highly suitable for edge deployment on resource-constrained wearables, potentially reducing hardware costs while maintaining competitive accuracy

TL;DR

  • 提出动态影响加权(DIW)知识蒸馏方法,利用训练时四个同步IMU的信息改进推理时仅需右臂单IMU的活动识别模型
  • 在WEAR数据集上,DIW的macro-F1达到0.638451,相比监督学习提升7.66个百分点,相比固定权重KD提升6.68个百分点
  • 通过样本级门控机制动态分配logit和特征损失权重,在19个标签中18个、22名参与者中21名均超越监督学习基线
  • 推理时保持仅80,915参数的单IMU学生模型,无需改变部署传感器配置或前向计算图

为什么值得看

  • 解决了多传感器训练与单传感器部署之间的实际鸿沟,为资源受限的边缘设备活动识别提供了高效方案
  • 动态影响加权机制为知识蒸馏领域提供了新的自适应权重分配思路,具有跨领域推广潜力

技术解析

  • 采用冻结的四IMU教师模型向单IMU学生模型进行知识蒸馏,引入DIW机制:在折叠内训练参与者上测试一步候选更新,据此为每个样本动态分配logit损失和特征损失的独立门控权重
  • 实验基于WEAR数据集,包含19个活动标签、68,298个完整时间窗口、22名参与者,采用主体不相交的五折交叉验证
  • 推理阶段仅需右臂IMU数据,学生模型参数量固定为80,915,相比监督学习基线(macro-F1=0.561820)和固定权重KD(0.571623)均有显著提升

行业启示

  • 多位置传感器训练+单位置部署的范式可广泛应用于可穿戴设备、智能手机等场景,降低硬件成本与用户佩戴负担
  • 动态样本级权重分配机制为知识蒸馏的"一刀切"问题提供了新思路,可推广至其他模态蒸馏和模型压缩任务
  • 在不增加推理复杂度的前提下实现性能跃升,对工业界部署轻量化活动识别模型具有直接参考价值

Disclaimer: The above content is generated by AI and is for reference only. 免责声明:以上内容由 AI 生成,仅供参考。

Research 科学研究 Training 训练 Dataset 数据集