轻量级人体姿态估计算法，用注意力机制减少计算开销。
Attention-Enhanced Lightweight Hourglass Network for Human Pose Estimation
- 基于小时钟结构，融合深度可分离卷积与注意力模块
- 仅230万参数、37亿浮点运算，精度达72.07%
- 适合移动端部署，性能优于6种同类轻量模型
人体姿态估计在计算机视觉中具有广泛应用，如行为监控和人机交互。然而，现有方法大多计算复杂或结构臃肿。本文提出一种基于注意力机制的轻量级姿态估计算法，采用深度可分离卷积与卷积块注意力模块（CBAM）构建小时钟主干网络。该模型将计算复杂度（浮点运算量）和模型规模（参数量）显著降低，仅含原始八层堆叠小时钟网络约10%的参数量。在COCO和MPII数据集上使用两层堆叠小时钟结构进行实验，结果表明，该模型在六种轻量级姿态估计模型中表现优异，平均精度达72.07%，仅需230万参数和37亿浮点运算。
原文摘要 · Abstract (English)
Pose estimation is a critical task in computer vision with a wide range of applications from activity monitoring to human-robot interaction. However,most of the existing methods are computationally expensive or have complex architecture. Here we propose a lightweight attention based pose estimation network that utilizes depthwise separable convolution and Convolutional Block Attention Module on an hourglass backbone. The network significantly reduces the computational complexity (floating point operations) and the model size (number of parameters) containing only about 10% of parameters of original eight stack Hourglass network. Experiments were conducted on COCO and MPII datasets using a two stack hourglass backbone. The results showed that our model performs well in comparison to six other lightweight pose estimation models with an average precision of 72.07. The model achieves this performance with only 2.3M parameters and 3.7G FLOPs.
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。