# Graph Attention Layer Evolves Semantic Segmentation for Road Pothole Detection: A Benchmark and Algorithms

arXiv: https://arxiv.org/abs/2109.02711 · HTML: https://mlsanity.com/paper/2109.02711/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 43 references that are in the map.
- First posted on arXiv 6 Sep 2021.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [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)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs](https://mlsanity.com/paper/1412.7062/) (2014)
- [Conditional Random Fields as Recurrent Neural Networks](https://mlsanity.com/paper/1502.03240/) (2015)
- [Gated-SCNN: Gated Shape CNNs for Semantic Segmentation](https://mlsanity.com/paper/1907.05740/) (2019)
- [Pyramid Attention Network for Semantic Segmentation](https://mlsanity.com/paper/1805.10180/) (2018)
- [ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation](https://mlsanity.com/paper/1803.06815/) (2018)
- [Pothole Detection Based on Disparity Transformation and Road Surface Modeling](https://mlsanity.com/paper/1908.00894/) (2019)
- [Road surface 3d reconstruction based on dense subpixel disparity map estimation](https://mlsanity.com/paper/1807.01874/) (2018)
- [Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation](https://mlsanity.com/paper/1903.02120/) (2019)
- [Rethinking Road Surface 3D Reconstruction and Pothole Detection: From Perspective Transformation to Disparity Map Segmentation](https://mlsanity.com/paper/2012.10802/) (2020)
- [Road Damage Detection Based on Unsupervised Disparity Map Segmentation](https://mlsanity.com/paper/1910.04988/) (2019)
- [Dynamic Fusion Module Evolves Drivable Area and Road Anomaly Detection: A Benchmark and Algorithms](https://mlsanity.com/paper/2103.02433/) (2021)
- [We Learn Better Road Pothole Detection: from Attention Aggregation to Adversarial Domain Adaptation](https://mlsanity.com/paper/2008.06840/) (2020)

## Built on by (most cited first, 15 of 15)

- [RoadFormer: Duplex Transformer for RGB-Normal Semantic Road Scene Parsing](https://mlsanity.com/paper/2309.10356/) (2023)
- [Computer Vision for Road Imaging and Pothole Detection: A State-of-the-Art Review of Systems and Algorithms](https://mlsanity.com/paper/2204.13590/) (2022)
- [SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learning](https://mlsanity.com/paper/2407.05283/) (2024)
- [UP-CrackNet: Unsupervised Pixel-Wise Road Crack Detection via Adversarial Image Restoration](https://mlsanity.com/paper/2401.15647/) (2024)
- [These Maps Are Made by Propagation: Adapting Deep Stereo Networks to Road Scenarios with Decisive Disparity Diffusion](https://mlsanity.com/paper/2411.03717/) (2024)
- [UDTIRI: An Online Open-Source Intelligent Road Inspection Benchmark Suite](https://mlsanity.com/paper/2304.08842/) (2023)
- [Dive Deeper into Rectifying Homography for Stereo Camera Online Self-Calibration](https://mlsanity.com/paper/2309.10314/) (2023)
- [TiCoSS: Tightening the Coupling between Semantic Segmentation and Stereo Matching within A Joint Learning Framework](https://mlsanity.com/paper/2407.18038/) (2024)
- [Computer-Aided Road Inspection: Systems and Algorithms](https://mlsanity.com/paper/2203.02355/) (2022)
- [E3CM: Epipolar-Constrained Cascade Correspondence Matching](https://mlsanity.com/paper/2308.16555/) (2023)
- [Shrinking unit: a Graph Convolution-Based Unit for CNN-like 3D Point Cloud Feature Extractors](https://mlsanity.com/paper/2209.12770/) (2022)
- [Classification of Potholes Based on Surface Area Using Pre-Trained Models of Convolutional Neural Network](https://mlsanity.com/paper/2309.17426/) (2023)
- [Establishing Reality-Virtuality Interconnections in Urban Digital Twins for Superior Intelligent Road Inspection and Simulation](https://mlsanity.com/paper/2412.17699/) (2024)
- [Fully Exploiting Vision Foundation Model's Profound Prior Knowledge for Generalizable RGB-Depth Driving Scene Parsing](https://mlsanity.com/paper/2502.06219/) (2025)
- [Integrating Disparity Confidence Estimation into Relative Depth Prior-Guided Unsupervised Stereo Matching](https://mlsanity.com/paper/2508.01275/) (2025)

## Abstract (arXiv)

Existing road pothole detection approaches can be classified as computer vision-based or machine learning-based. The former approaches typically employ 2-D image analysis/understanding or 3-D point cloud modeling and segmentation algorithms to detect road potholes from vision sensor data. The latter approaches generally address road pothole detection using convolutional neural networks (CNNs) in an end-to-end manner. However, road potholes are not necessarily ubiquitous and it is challenging to prepare a large well-annotated dataset for CNN training. In this regard, while computer vision-based methods were the mainstream research trend in the past decade, machine learning-based methods were merely discussed. Recently, we published the first stereo vision-based road pothole detection dataset and a novel disparity transformation algorithm, whereby the damaged and undamaged road areas can be highly distinguished. However, there are no benchmarks currently available for state-of-the-art (SoTA) CNNs trained using either disparity images or transformed disparity images. Therefore, in this paper, we first discuss the SoTA CNNs designed for semantic segmentation and evaluate their performance for road pothole detection with extensive experiments. Additionally, inspired by graph neural network (GNN), we propose a novel CNN layer, referred to as graph attention layer (GAL), which can be easily deployed in any existing CNN to optimize image feature representations for semantic segmentation. Our experiments compare GAL-DeepLabv3+, our best-performing implementation, with nine SoTA CNNs on three modalities of training data: RGB images, disparity images, and transformed disparity images. The experimental results suggest that our proposed GAL-DeepLabv3+ achieves the best overall pothole detection accuracy on all training data modalities.