# Real-time Semantic Image Segmentation via Spatial Sparsity

arXiv: https://arxiv.org/abs/1712.00213 · HTML: https://mlsanity.com/paper/1712.00213/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Dec 2017.

## Built on by (most cited first, 6 of 6)

- [Semantic Image Segmentation: Two Decades of Research](https://mlsanity.com/paper/2302.06378/) (2023)
- [SCTNet: Single-Branch CNN with Transformer Semantic Information for Real-Time Segmentation](https://mlsanity.com/paper/2312.17071/) (2023)
- [Deep Multi-Branch Aggregation Network for Real-Time Semantic Segmentation in Street Scenes](https://mlsanity.com/paper/2203.04037/) (2022)
- [Cross-CBAM: A Lightweight network for Scene Segmentation](https://mlsanity.com/paper/2306.02306/) (2023)
- [STDC-MA Network for Semantic Segmentation](https://mlsanity.com/paper/2205.04639/) (2022)
- [Efficient On-Board Processing of Oblique UAV Video for Rapid Flood Extent Mapping](https://mlsanity.com/paper/2601.11290/) (2026)

## Abstract (arXiv)

We propose an approach to semantic (image) segmentation that reduces the computational costs by a factor of 25 with limited impact on the quality of results. Semantic segmentation has a number of practical applications, and for most such applications the computational costs are critical. The method follows a typical two-column network structure, where one column accepts an input image, while the other accepts a half-resolution version of that image. By identifying specific regions in the full-resolution image that can be safely ignored, as well as carefully tailoring the network structure, we can process approximately 15 highresolution Cityscapes images (1024x2048) per second using a single GTX 980 video card, while achieving a mean intersection-over-union score of 72.9% on the Cityscapes test set.