# Linear Span Network for Object Skeleton Detection

arXiv: https://arxiv.org/abs/1807.09601 · HTML: https://mlsanity.com/paper/1807.09601/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jul 2018.

## Built on by (most cited first, 7 of 7)

- [Panoptic Segmentation Meets Remote Sensing](https://mlsanity.com/paper/2111.12126/) (2021)
- [Structure-Preserving Instance Segmentation via Skeleton-Aware Distance Transform](https://mlsanity.com/paper/2310.05262/) (2023)
- [Multimodal Industrial Anomaly Detection via Geometric Prior](https://mlsanity.com/paper/2603.22757/) (2026)
- [Mode-locking Theory for Long-Range Interaction in Artificial Neural Networks](https://mlsanity.com/paper/2303.05695/) (2023)
- [MCMS: Multi-Category Information and Multi-Scale Stripe Attention for Blind Motion Deblurring](https://mlsanity.com/paper/2405.01083/) (2024)
- [Topology-Aware Skeleton Detection via Lighthouse-Guided Structured Inference](https://mlsanity.com/paper/2604.20123/) (2026)
- [Depth-Dominant Skeleton Detection for Natural Scenes](https://mlsanity.com/paper/2608.16367/) (2026)

## Abstract (arXiv)

Robust object skeleton detection requires to explore rich representative visual features and effective feature fusion strategies. In this paper, we first re-visit the implementation of HED, the essential principle of which can be ideally described with a linear reconstruction model. Hinted by this, we formalize a Linear Span framework, and propose Linear Span Network (LSN) modified by Linear Span Units (LSUs), which minimize the reconstruction error of convolutional network. LSN further utilizes subspace linear span beside the feature linear span to increase the independence of convolutional features and the efficiency of feature integration, which enlarges the capability of fitting complex ground-truth. As a result, LSN can effectively suppress the cluttered backgrounds and reconstruct object skeletons. Experimental results validate the state-of-the-art performance of the proposed LSN.