AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

RoadTagger: Robust Road Attribute Inference with Graph Neural Networks

Songtao He, Favyen Bastani, Satvat Jagwani, Edward Park, Sofiane Abbar, Mohammad Alizadeh, Hari Balakrishnan, Sanjay Chawla, Samuel Madden, Mohammad Amin Sadeghi

AAAI 2020 · Graph learning › Graph self-supervised learning · approach: Multi-view graph clustering · 40 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Replace independent CNN image classification with end-to-end CNN and graph neural network inferenceRoadTagger · Real-world datasetlane accuracy: 71.8% -> 77.2%Improved
Replace independent CNN image classification with end-to-end CNN and graph neural network inferenceRoadTagger · Real-world datasetroad type accuracy: 89.1% -> 93.1%Improved
Replace independent CNN image classification with end-to-end CNN and graph neural network inferenceRoadTagger · Real-world datasetabsolute lane error (ALE): 22.2%Improved
Add the road extraction graph instead of using only the original road network graph (ablation)RoadTagger · Real-world datasetlane accuracy: 74.0% -> 75.5%Improved
Use the original, directionally decomposed road extraction, and auxiliary parallel-road graphs rather than only the original graph (ablation)RoadTagger · Real-world datasetlane accuracy: 74.0% -> 77.2%Improved
Add random vertex dropout (ablation)RoadTagger · Real-world datasetlane accuracy: 74.7% -> 77.2%Improved
Add random vertex dropout (ablation)RoadTagger · Real-world datasetroad type accuracy: 92.7% -> 93.1%Improved
Add graph Laplace regularization (ablation)RoadTagger · Real-world datasetroad type accuracy: 90.8% -> 93.1%Improved
Add graph Laplace regularization (ablation)RoadTagger · Real-world datasetlane accuracy: 76.5% -> 77.2%Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy