动态调整模态学习强度，提升多传感器动作识别准确率
Confidence-driven Gradient Modulation for Multimodal Human Activity Recognition: A Dynamic Contrastive Dual-Path Learning Approach
- 双路径结构并行处理不同传感器数据，增强特征表达
- 通过渐进式对比学习实现跨模态特征对齐，提升识别精度
- 根据模态置信度动态调节梯度，适合传感器数据不均衡场景
基于传感器的人体动作识别（HAR）是智能系统感知环境的核心技术。然而，多模态HAR系统仍面临跨模态特征对齐困难和模态贡献不平衡等挑战。为此，本文提出一种新型框架——动态对比双路径网络（DCDP-HAR）。该框架包含三个关键组件：首先，采用双路径特征提取架构，由ResNet与DenseNet分支协同处理多源传感器数据；其次，引入多阶段对比学习机制，实现从局部感知到语义抽象的渐进式对齐；第三，提出置信度驱动的梯度调制策略，在反向传播中动态监控并调整各模态分支的学习强度，有效缓解模态竞争。此外，采用基于动量的梯度累积策略以提升训练稳定性。我们在四个公开基准数据集上进行消融实验与广泛对比实验，验证了各组件的有效性。
原文摘要 · Abstract (English)
Sensor-based Human Activity Recognition (HAR) is a core technology that enables intelligent systems to perceive and interact with their environment. However, multimodal HAR systems still encounter key challenges, such as difficulties in cross-modal feature alignment and imbalanced modality contributions. To address these issues, we propose a novel framework called the Dynamic Contrastive Dual-Path Network (DCDP-HAR). The framework comprises three key components. First, a dual-path feature extraction architecture is employed, where ResNet and DenseNet branches collaboratively process multimodal sensor data. Second, a multi-stage contrastive learning mechanism is introduced to achieve progressive alignment from local perception to semantic abstraction. Third, we present a confidence-driven gradient modulation strategy that dynamically monitors and adjusts the learning intensity of each modality branch during backpropagation, effectively alleviating modality competition. In addition, a momentum-based gradient accumulation strategy is adopted to enhance training stability. We conduct ablation studies to validate the effectiveness of each component and perform extensive comparative experiments on four public benchmark datasets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。