Attention-Enhanced Lightweight Hourglass Network for Human Pose Estimation

2024-12-09

arXiv.org

AI Summary

Existing pose estimation methods suffer from high computational overhead and model complexity. To address this, we propose a lightweight dual-stacked hourglass network. Our key innovation lies in the first integration of depthwise separable convolutions with the Convolutional Block Attention Module (CBAM) into the hourglass architecture, enabling simultaneous model compression and enhanced feature representation. Compared to the original eight-stacked hourglass baseline, our model reduces parameters to only 10% (2.3M) and computational cost to 3.7G FLOPs, while achieving competitive accuracy—72.07 AP on COCO and MPII benchmarks—surpassing six state-of-the-art lightweight models. This design achieves a superior trade-off among accuracy, parameter count, and inference efficiency, offering a practical and efficient solution for real-time human pose estimation on edge devices.

Technology Category

• Computer Vision: Biometrics, Face, Gesture & Pose
• Intelligent Robots: State Estimation
• Machine Learning: Learning on the Edge & Model Compression

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

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.

Problem

• Reducing computational cost in human pose estimation
• Simplifying architecture of pose estimation networks
• Maintaining accuracy with fewer model parameters

Innovation

• Lightweight attention-based hourglass network
• Depthwise separable convolution reduces complexity
• Convolutional Block Attention Module enhances performance