# To Perceive or Not to Perceive: Lightweight Stacked Hourglass Network

arXiv: https://arxiv.org/abs/2302.04815 · HTML: https://mlsanity.com/paper/2302.04815/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 7 references that are in the map.
- First posted on arXiv 9 Feb 2023.

## Builds on (most cited first, 4 of 4)

- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [GhostNet: More Features from Cheap Operations](https://mlsanity.com/paper/1911.11907/) (2019)
- [DiCENet: Dimension-wise Convolutions for Efficient Networks](https://mlsanity.com/paper/1906.03516/) (2019)

## Abstract (arXiv)

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