LAPX: Lightweight Hourglass Network with Global Context

TL;DR

LAPX is a lightweight hourglass network with self-attention that captures global context, achieving competitive human pose estimation accuracy on benchmarks with minimal parameters and real-time performance for edge deployment.

Contribution

The paper introduces LAPX, a novel lightweight hourglass network with integrated self-attention and refined modules, optimized for efficient edge-device human pose estimation.

Findings

Achieves competitive accuracy on MPII and COCO datasets.

Uses only 2.3 million parameters.

Operates in real-time on edge devices.

Abstract

Human pose estimation is a crucial task in computer vision. Methods that have SOTA (State-of-the-Art) accuracy, often involve a large number of parameters and incur substantial computational cost. Many lightweight variants have been proposed to reduce the model size and computational cost of them. However, several of these methods still contain components that are not well suited for efficient deployment on edge devices. Moreover, models that primarily emphasize inference speed on edge devices often suffer from limited accuracy due to their overly simplified designs. To address these limitations, we propose LAPX, an Hourglass network with self-attention that captures global contextual information, based on previous work, LAP. In addition to adopting the self-attention module, LAPX advances the stage design and refine the lightweight attention modules. It achieves competitive results on two benchmark datasets, MPII and COCO, with only 2.3M parameters, and demonstrates real-time performance, confirming its edge-device suitability.