AI Paper Atlas

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

Leveraging Crowdsourced GPS Data for Road Extraction From Aerial Imagery

Tao Sun, Zonglin Di, Pengyu Che, Chun Liu, Yin Wang

CVPR 2019 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 122 citations (OpenAlex)

Check 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
Add GPS input to aerial imageryD-LinkNet · Beijing test setIoU (%): 54.42 -> 56.96Improved
Replace 3×3 transpose convolutions with a 1D decoder (ablation)D-LinkNet with image + GPS input · Beijing test setIoU (%): 56.96 -> 57.96Improved
Add the GPS sampling-interval channel (ablation)D-LinkNet with image + GPS and 1D decoder · Beijing test setIoU (%): 57.96 -> 58.55Improved
Add GPS data augmentation (ablation)D-LinkNet with image + GPS, interval, and 1D decoder · Beijing test setIoU (%): 58.55 -> 59.18Improved
Add GPS input to image inputD-LinkNet · Shanghai test set, trained on BeijingIoU (%): 38.16 -> 44.57Improved
Add GPS augmentation (ablation)Image + GPS model · Shanghai test set, trained on BeijingIoU (%): 44.57 -> 48.69Improved
Use a 1D decoder instead of a plain decoder (ablation)U-Net with GPS input · Beijing test setIoU (%): 43.63 -> 48.10Improved
Use a 1D decoder instead of a plain decoder (ablation)Res U-Net with image + GPS input · Beijing test setIoU (%): 52.29 -> 54.24Improved
Use a 1D decoder instead of a plain decoder (ablation)LinkNet with image + GPS input · Beijing test setIoU (%): 57.48 -> 57.89Improved
Use a 1D decoder instead of a plain decoder (ablation)D-LinkNet with image input · Beijing test setIoU (%): 54.42 -> 55.15Improved
Use a 1D decoder instead of a plain decoder (ablation)Res U-Net with GPS input · Beijing test setIoU (%): 45.33 -> 48.52Improved
Use a 1D decoder instead of a plain decoder (ablation)LinkNet with image input · Beijing test setIoU (%): 53.96 -> 54.84Improved

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