CVIVFeb 9, 2023

To Perceive or Not to Perceive: Lightweight Stacked Hourglass Network

arXiv:2302.04815v1h-index: 6
Originality Synthesis-oriented
AI Analysis

This work addresses efficiency for real-time pose estimation applications, but it is incremental as it builds on existing stacked hourglass architectures.

The authors tackled the problem of reducing computational cost in human pose estimation by designing a lightweight version of the stacked hourglass network, achieving a 79% reduction in parameters with only a marginal drop in performance.

Human pose estimation (HPE) is a classical task in computer vision that focuses on representing the orientation of a person by identifying the positions of their joints. We design a lighterversion of the stacked hourglass network with minimal loss in performance of the model. The lightweight 2-stacked hourglass has a reduced number of channels with depthwise separable convolutions, residual connections with concatenation, and residual connections between the necks of the hourglasses. The final model has a marginal drop in performance with 79% reduction in the number of parameters and a similar drop in MAdds

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes