LGM-Pose: A Lightweight Global Modeling Network for Real-time Human Pose Estimation

TL;DR

LGM-Pose introduces a lightweight, single-branch global modeling network for real-time human pose estimation, effectively capturing global context while reducing parameters and increasing speed.

Contribution

The paper proposes a novel lightweight global modeling network with innovative modules that improve global feature extraction and multi-scale fusion in pose estimation.

Findings

Reduces model parameters compared to existing methods.

Achieves superior accuracy on COCO and MPII datasets.

Provides faster inference speeds.

Abstract

Most of the current top-down multi-person pose estimation lightweight methods are based on multi-branch parallel pure CNN network architecture, which often struggle to capture the global context required for detecting semantically complex keypoints and are hindered by high latency due to their intricate and redundant structures. In this article, an approximate single-branch lightweight global modeling network (LGM-Pose) is proposed to address these challenges. In the network, a lightweight MobileViM Block is designed with a proposed Lightweight Attentional Representation Module (LARM), which integrates information within and between patches using the Non-Parametric Transformation Operation(NPT-Op) to extract global information. Additionally, a novel Shuffle-Integrated Fusion Module (SFusion) is introduced to effectively integrate multi-scale information, mitigating performance degradation often observed in single-branch structures. Experimental evaluations on the COCO and MPII datasets demonstrate that our approach not only reduces the number of parameters compared to existing mainstream lightweight methods but also achieves superior performance and faster processing speeds.