轻量级网络LGM-Pose实现实时人体姿态估计，兼顾精度与速度。
LGM-Pose: A Lightweight Global Modeling Network for Real-time Human Pose Estimation
- 单分支结构结合轻量注意力模块，高效提取全局上下文信息。
- 参数量更少，推理速度更快，在COCO和MPII上性能领先。
- 适合移动端或嵌入式设备部署，适用于实时人体姿态识别场景。
现有主流轻量级多人姿态估计方法多采用多分支并行纯卷积网络，难以捕捉语义复杂关键点所需的全局上下文，且因结构复杂冗余导致延迟较高。本文提出一种近似单分支的轻量级全局建模网络LGM-Pose。网络中设计了轻量级MobileViM Block，集成轻量注意力表示模块（LARM），利用无参数变换操作（NPT-Op）在块内与块间融合信息以提取全局特征。同时引入新型混洗融合模块（SFusion），有效整合多尺度信息，缓解单分支结构常见的性能下降问题。在COCO和MPII数据集上的实验表明，该方法相比现有主流轻量级方法参数更少，且达到更高精度与更快推理速度。
原文摘要 · Abstract (English)
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.
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。