AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

CARLANE: A Lane Detection Benchmark for Unsupervised Domain Adaptation from Simulation to multiple Real-World Domains

Bonifaz Stuhr, Johann Kaspar Ludwig Haselberger, Julian Gebele

NeurIPS 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 0 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
Adapt UFLD-SO to the target domain with SGPCSUFLD-SO (ResNet-18) · MoLane testlane accuracy (LA): 88.15 -> 93.29$\pm$0.07Improved
Adapt UFLD-SO to the target domain with SGPCSUFLD-SO (ResNet-18) · TuLane testlane accuracy (LA): 87.43 -> 91.55$\pm$0.13Improved
Adapt UFLD-SO to the target domain with SGPCSUFLD-SO (ResNet-18) · MuLane testlane accuracy (LA): 79.61 -> 82.91$\pm$0.19Improved
Adapt UFLD-SO using DANNUFLD-SO (ResNet-18) · MoLane testlane accuracy (LA): 88.15 -> 85.25$\pm$0.49Hurt
Adapt UFLD-SO using DANNUFLD-SO (ResNet-18) · MuLane testlane accuracy (LA): 79.61 -> 78.25$\pm$0.62Hurt
Use target-domain labeled training data rather than source-only trainingUFLD · MoLane testlane accuracy (LA): 88.15 -> 97.15Improved
Use target-domain labeled training data rather than source-only trainingUFLD · TuLane testlane accuracy (LA): 87.43 -> 94.97Improved
Use target-domain labeled training data rather than source-only trainingUFLD · MuLane testlane accuracy (LA): 79.61 -> 87.64Improved

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