# Efficient Dense Modules of Asymmetric Convolution for Real-Time Semantic Segmentation

arXiv: https://arxiv.org/abs/1809.06323 · HTML: https://mlsanity.com/paper/1809.06323/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2018.

## Built on by (most cited first, 26 of 26)

- [LeViT-UNet: Make Faster Encoders with Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2107.08623/) (2021)
- [Capturing Omni-Range Context for Omnidirectional Segmentation](https://mlsanity.com/paper/2103.05687/) (2021)
- [HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers](https://mlsanity.com/paper/2106.06560/) (2021)
- [FBSNet: A Fast Bilateral Symmetrical Network for Real-Time Semantic Segmentation](https://mlsanity.com/paper/2109.00699/) (2021)
- [Stage-Aware Feature Alignment Network for Real-Time Semantic Segmentation of Street Scenes](https://mlsanity.com/paper/2203.04031/) (2022)
- [MSCFNet: A Lightweight Network With Multi-Scale Context Fusion for Real-Time Semantic Segmentation](https://mlsanity.com/paper/2103.13044/) (2021)
- [Asymmetric CNN for image super-resolution](https://mlsanity.com/paper/2103.13634/) (2021)
- [Computation-efficient Deep Learning for Computer Vision: A Survey](https://mlsanity.com/paper/2308.13998/) (2023)
- [SAGAN: Adversarial Spatial-asymmetric Attention for Noisy Nona-Bayer Reconstruction](https://mlsanity.com/paper/2110.08619/) (2021)
- [Online Video Super-Resolution with Convolutional Kernel Bypass Graft](https://mlsanity.com/paper/2208.02470/) (2022)
- [Spatio-Temporal Pixel-Level Contrastive Learning-based Source-Free Domain Adaptation for Video Semantic Segmentation](https://mlsanity.com/paper/2303.14361/) (2023)
- [On Efficient Real-Time Semantic Segmentation: A Survey](https://mlsanity.com/paper/2206.08605/) (2022)
- [eWaSR -- an embedded-compute-ready maritime obstacle detection network](https://mlsanity.com/paper/2304.11249/) (2023)
- [Monocular Lane Detection Based on Deep Learning: A Survey](https://mlsanity.com/paper/2411.16316/) (2024)
- [CSRNet: Cascaded Selective Resolution Network for Real-time Semantic Segmentation](https://mlsanity.com/paper/2106.04400/) (2021)
- [Cross-CBAM: A Lightweight network for Scene Segmentation](https://mlsanity.com/paper/2306.02306/) (2023)
- [Cross Dataset Analysis and Network Architecture Repair for Autonomous Car Lane Detection](https://mlsanity.com/paper/2409.17158/) (2024)
- [Bilateral Network with Residual U-blocks and Dual-Guided Attention for Real-time Semantic Segmentation](https://mlsanity.com/paper/2310.20305/) (2023)
- [SLP-Net:An efficient lightweight network for segmentation of skin lesions](https://mlsanity.com/paper/2312.12789/) (2023)
- [Entropy-Based Feature Extraction For Real-Time Semantic Segmentation](https://mlsanity.com/paper/2207.03233/) (2022)
- [Time Series Forecasting via Semi-Asymmetric Convolutional Architecture with Global Atrous Sliding Window](https://mlsanity.com/paper/2301.13691/) (2023)
- [Efficient Context Integration through Factorized Pyramidal Learning for Ultra-Lightweight Semantic Segmentation](https://mlsanity.com/paper/2302.11785/) (2023)
- [Spatial-Assistant Encoder-Decoder Network for Real Time Semantic Segmentation](https://mlsanity.com/paper/2309.10519/) (2023)
- [CNNs for JPEGs: A Study in Computational Cost](https://mlsanity.com/paper/2309.11417/) (2023)
- [EfficientCrackNet: A Lightweight Model for Crack Segmentation](https://mlsanity.com/paper/2409.18099/) (2024)
- [AVOID: The Adverse Visual Conditions Dataset with Obstacles for Driving Scene Understanding](https://mlsanity.com/paper/2512.23215/) (2025)

## Abstract (arXiv)

Real-time semantic segmentation plays an important role in practical applications such as self-driving and robots. Most semantic segmentation research focuses on improving estimation accuracy with little consideration on efficiency. Several previous studies that emphasize high-speed inference often fail to produce high-accuracy segmentation results. In this paper, we propose a novel convolutional network named Efficient Dense modules with Asymmetric convolution (EDANet), which employs an asymmetric convolution structure and incorporates dilated convolution and dense connectivity to achieve high efficiency at low computational cost and model size. EDANet is 2.7 times faster than the existing fast segmentation network, ICNet, while it achieves a similar mIoU score without any additional context module, post-processing scheme, and pretrained model. We evaluate EDANet on Cityscapes and CamVid datasets, and compare it with the other state-of-art systems. Our network can run with the high-resolution inputs at the speed of 108 FPS on one GTX 1080Ti.