# ShuffleSeg: Real-time Semantic Segmentation Network

arXiv: https://arxiv.org/abs/1803.03816 · HTML: https://mlsanity.com/paper/1803.03816/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Mar 2018.

## Built on by (most cited first, 9 of 9)

- [PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers](https://mlsanity.com/paper/2206.02066/) (2022)
- [On Efficient Real-Time Semantic Segmentation: A Survey](https://mlsanity.com/paper/2206.08605/) (2022)
- [Anatomy-guided Pathology Segmentation](https://mlsanity.com/paper/2407.05844/) (2024)
- [Multi-task Learning for Real-time Autonomous Driving Leveraging Task-adaptive Attention Generator](https://mlsanity.com/paper/2403.03468/) (2024)
- [Deep Learning Framework for Real-time Fetal Brain Segmentation in MRI](https://mlsanity.com/paper/2205.01675/) (2022)
- [Few-Shot Fruit Segmentation via Transfer Learning](https://mlsanity.com/paper/2405.02556/) (2024)
- [LightFormer: A lightweight and efficient decoder for remote sensing image segmentation](https://mlsanity.com/paper/2504.10834/) (2025)
- [NoFADE: Analyzing Diminishing Returns on CO2 Investment](https://mlsanity.com/paper/2111.14059/) (2021)
- [BAFNet: Bilateral Attention Fusion Network for Lightweight Semantic Segmentation of Urban Remote Sensing Images](https://mlsanity.com/paper/2409.10269/) (2024)

## Abstract (arXiv)

Real-time semantic segmentation is of significant importance for mobile and robotics related applications. We propose a computationally efficient segmentation network which we term as ShuffleSeg. The proposed architecture is based on grouped convolution and channel shuffling in its encoder for improving the performance. An ablation study of different decoding methods is compared including Skip architecture, UNet, and Dilation Frontend. Interesting insights on the speed and accuracy tradeoff is discussed. It is shown that skip architecture in the decoding method provides the best compromise for the goal of real-time performance, while it provides adequate accuracy by utilizing higher resolution feature maps for a more accurate segmentation. ShuffleSeg is evaluated on CityScapes and compared against the state of the art real-time segmentation networks. It achieves 2x GFLOPs reduction, while it provides on par mean intersection over union of 58.3% on CityScapes test set. ShuffleSeg runs at 15.7 frames per second on NVIDIA Jetson TX2, which makes it of great potential for real-time applications.