# FDDWNet: A Lightweight Convolutional Neural Network for Real-time Sementic Segmentation

arXiv: https://arxiv.org/abs/1911.00632 · HTML: https://mlsanity.com/paper/1911.00632/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Nov 2019.

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

- [FBSNet: A Fast Bilateral Symmetrical Network for Real-Time Semantic Segmentation](https://mlsanity.com/paper/2109.00699/) (2021)
- [Lightweight Real-time Semantic Segmentation Network with Efficient Transformer and CNN](https://mlsanity.com/paper/2302.10484/) (2023)
- [S2-FPN: Scale-ware Strip Attention Guided Feature Pyramid Network for Real-time Semantic Segmentation](https://mlsanity.com/paper/2206.07298/) (2022)
- [A De-raining semantic segmentation network for real-time foreground segmentation](https://mlsanity.com/paper/2104.07877/) (2021)
- [Efficient Semantic Segmentation via Lightweight Multiple-Information Interaction Network](https://mlsanity.com/paper/2410.02224/) (2024)
- [ECMNet:Lightweight Semantic Segmentation with Efficient CNN-Mamba Network](https://mlsanity.com/paper/2506.08629/) (2025)
- [Technical Report on Subspace Pyramid Fusion Network for Semantic Segmentation](https://mlsanity.com/paper/2204.01278/) (2022)

## Abstract (arXiv)

This paper introduces a lightweight convolutional neural network, called FDDWNet, for real-time accurate semantic segmentation. In contrast to recent advances of lightweight networks that prefer to utilize shallow structure, FDDWNet makes an effort to design more deeper network architecture, while maintains faster inference speed and higher segmentation accuracy. Our network uses factorized dilated depth-wise separable convolutions (FDDWC) to learn feature representations from different scale receptive fields with fewer model parameters. Additionally, FDDWNet has multiple branches of skipped connections to gather context cues from intermediate convolution layers. The experiments show that FDDWNet only has 0.8M model size, while achieves 60 FPS running speed on a single RTX 2080Ti GPU with a 1024x512 input image. The comprehensive experiments demonstrate that our model achieves state-of-the-art results in terms of available speed and accuracy trade-off on CityScapes and CamVid datasets.