# Real-Time High-Performance Semantic Image Segmentation of Urban Street Scenes

arXiv: https://arxiv.org/abs/2003.08736 · HTML: https://mlsanity.com/paper/2003.08736/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Mar 2020.

## Built on by (most cited first, 19 of 19)

- [Distilling Inter-Class Distance for Semantic Segmentation](https://mlsanity.com/paper/2205.03650/) (2022)
- [Stage-Aware Feature Alignment Network for Real-Time Semantic Segmentation of Street Scenes](https://mlsanity.com/paper/2203.04031/) (2022)
- [Lightweight Real-time Semantic Segmentation Network with Efficient Transformer and CNN](https://mlsanity.com/paper/2302.10484/) (2023)
- [Deep Learning based Computer Vision Methods for Complex Traffic Environments Perception: A Review](https://mlsanity.com/paper/2211.05120/) (2022)
- [Iterative Loop Method Combining Active and Semi-Supervised Learning for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2301.13361/) (2023)
- [Threshold-adaptive Unsupervised Focal Loss for Domain Adaptation of Semantic Segmentation](https://mlsanity.com/paper/2208.10716/) (2022)
- [Exploiting Low-level Representations for Ultra-Fast Road Segmentation](https://mlsanity.com/paper/2402.02430/) (2024)
- [Deep Multi-Branch Aggregation Network for Real-Time Semantic Segmentation in Street Scenes](https://mlsanity.com/paper/2203.04037/) (2022)
- [Frequency-based Matcher for Long-tailed Semantic Segmentation](https://mlsanity.com/paper/2406.03917/) (2024)
- [CSRNet: Cascaded Selective Resolution Network for Real-time Semantic Segmentation](https://mlsanity.com/paper/2106.04400/) (2021)
- [S2-FPN: Scale-ware Strip Attention Guided Feature Pyramid Network for Real-time Semantic Segmentation](https://mlsanity.com/paper/2206.07298/) (2022)
- [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)
- [Spatial-Assistant Encoder-Decoder Network for Real Time Semantic Segmentation](https://mlsanity.com/paper/2309.10519/) (2023)
- [Elastic Interaction Energy-Informed Real-Time Traffic Scene Perception](https://mlsanity.com/paper/2310.01449/) (2023)
- [P2AT: Pyramid Pooling Axial Transformer for Real-time Semantic Segmentation](https://mlsanity.com/paper/2310.15025/) (2023)
- [HSDA: High-frequency Shuffle Data Augmentation for Bird's-Eye-View Map Segmentation](https://mlsanity.com/paper/2412.06127/) (2024)
- [Remote sensing colour image semantic segmentation of trails created by large herbivorous Mammals](https://mlsanity.com/paper/2504.12121/) (2025)

## Abstract (arXiv)

Deep Convolutional Neural Networks (DCNNs) have recently shown outstanding performance in semantic image segmentation. However, state-of-the-art DCNN-based semantic segmentation methods usually suffer from high computational complexity due to the use of complex network architectures. This greatly limits their applications in the real-world scenarios that require real-time processing. In this paper, we propose a real-time high-performance DCNN-based method for robust semantic segmentation of urban street scenes, which achieves a good trade-off between accuracy and speed. Specifically, a Lightweight Baseline Network with Atrous convolution and Attention (LBN-AA) is firstly used as our baseline network to efficiently obtain dense feature maps. Then, the Distinctive Atrous Spatial Pyramid Pooling (DASPP), which exploits the different sizes of pooling operations to encode the rich and distinctive semantic information, is developed to detect objects at multiple scales. Meanwhile, a Spatial detail-Preserving Network (SPN) with shallow convolutional layers is designed to generate high-resolution feature maps preserving the detailed spatial information. Finally, a simple but practical Feature Fusion Network (FFN) is used to effectively combine both shallow and deep features from the semantic branch (DASPP) and the spatial branch (SPN), respectively. Extensive experimental results show that the proposed method respectively achieves the accuracy of 73.6% and 68.0% mean Intersection over Union (mIoU) with the inference speed of 51.0 fps and 39.3 fps on the challenging Cityscapes and CamVid test datasets (by only using a single NVIDIA TITAN X card). This demonstrates that the proposed method offers excellent performance at the real-time speed for semantic segmentation of urban street scenes.