# A feature refinement module for light-weight semantic segmentation network

arXiv: https://arxiv.org/abs/2412.08670 · HTML: https://mlsanity.com/paper/2412.08670/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 26 references that are in the map.
- First posted on arXiv 11 Dec 2024.

## Builds on (most cited first, 23 of 23)

- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation](https://mlsanity.com/paper/1606.02147/) (2016)
- [Exploring Cross-Image Pixel Contrast for Semantic Segmentation](https://mlsanity.com/paper/2101.11939/) (2021)
- [Visual Attention Network](https://mlsanity.com/paper/2202.09741/) (2022)
- [ParseNet: Looking Wider to See Better](https://mlsanity.com/paper/1506.04579/) (2015)
- [Disentangled Non-Local Neural Networks](https://mlsanity.com/paper/2006.06668/) (2020)
- [Semantic Flow for Fast and Accurate Scene Parsing](https://mlsanity.com/paper/2002.10120/) (2020)
- [DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation](https://mlsanity.com/paper/1904.02216/) (2019)
- [CGNet: A Light-weight Context Guided Network for Semantic Segmentation](https://mlsanity.com/paper/1811.08201/) (2018)
- [Cars Can't Fly up in the Sky: Improving Urban-Scene Segmentation via Height-driven Attention Networks](https://mlsanity.com/paper/2003.05128/) (2020)
- [Real-time Semantic Segmentation of Crop and Weed for Precision Agriculture Robots Leveraging Background Knowledge in CNNs](https://mlsanity.com/paper/1709.06764/) (2017)
- [Real-time Fusion Network for RGB-D Semantic Segmentation Incorporating Unexpected Obstacle Detection for Road-driving Images](https://mlsanity.com/paper/2002.10570/) (2020)
- [ContextNet: Exploring Context and Detail for Semantic Segmentation in Real-time](https://mlsanity.com/paper/1805.04554/) (2018)
- [Learning Implicit Feature Alignment Function for Semantic Segmentation](https://mlsanity.com/paper/2206.08655/) (2022)
- [RTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer](https://mlsanity.com/paper/2210.07124/) (2022)
- [PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation](https://mlsanity.com/paper/2103.06564/) (2021)
- [Stage-Aware Feature Alignment Network for Real-Time Semantic Segmentation of Street Scenes](https://mlsanity.com/paper/2203.04031/) (2022)
- [Dynamic Neural Representational Decoders for High-Resolution Semantic Segmentation](https://mlsanity.com/paper/2107.14428/) (2021)
- [Fast and Accurate Scene Parsing via Bi-direction Alignment Networks](https://mlsanity.com/paper/2105.11651/) (2021)

## Built on by (most cited first, 1 of 1)

- [AURASeg: Attention-Guided Upsampling with Residual-Assisted Boundary Refinement for Drivable-Area Segmentation](https://mlsanity.com/paper/2510.21536/) (2025)

## Abstract (arXiv)

Low computational complexity and high segmentation accuracy are both essential to the real-world semantic segmentation tasks. However, to speed up the model inference, most existing approaches tend to design light-weight networks with a very limited number of parameters, leading to a considerable degradation in accuracy due to the decrease of the representation ability of the networks. To solve the problem, this paper proposes a novel semantic segmentation method to improve the capacity of obtaining semantic information for the light-weight network. Specifically, a feature refinement module (FRM) is proposed to extract semantics from multi-stage feature maps generated by the backbone and capture non-local contextual information by utilizing a transformer block. On Cityscapes and Bdd100K datasets, the experimental results demonstrate that the proposed method achieves a promising trade-off between accuracy and computational cost, especially for Cityscapes test set where 80.4% mIoU is achieved and only 214.82 GFLOPs are required.