AI Paper Atlas

Research map / Detection and segmentation / CNN features

Geometric Constrained Joint Lane Segmentation and Lane Boundary Detection

Jie Zhang, Yi Xu, Bingbing Ni, Zhenyu Duan

ECCV 2018 · Detection and segmentation › CNN features · approach: Lane detection · 71 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
add structure loss functions to the multi-task network (ablation)multi-task network · KITTI URBAN ROADIoU: 0.852 -> 0.861Improved
add inter-link encoder to the multi-task network (ablation)multi-task network · KITTI URBAN ROADIoU: 0.852 -> 0.865Improved
add both inter-link encoder and structure loss (ablation)multi-task network · KITTI URBAN ROADIoU: 0.852 -> 0.874Improved
add both inter-link encoder and structure loss (ablation)multi-task network · KITTI URBAN ROADF1: 0.920 -> 0.933Improved
add structure loss on top of inter-link encoder (ablation)inter-link network · KITTI lane boundary detectionF1: 0.788 -> 0.831Improved
add structure loss on top of inter-link encoder (ablation)inter-link network · KITTI lane boundary detectionprecision: 0.806 -> 0.838Improved
add structure loss on top of inter-link encoder (ablation)inter-link network · KITTI lane boundary detectionrecall: 0.771 -> 0.824Improved
add joint training of segmentation and boundary tasksbaseline segmentation · KITTI URBAN ROADIoU: 0.808 -> 0.852Improved
use the full model instead of Up-Conv-PolyOurs · KITTI URBAN ROADIoU: 0.854 -> 0.874Improved
use the full model instead of Up-Conv-PolyOurs · CULane lane segmentationIoU: 0.807 -> 0.824Improved
use the full model instead of CMAOurs · RVD NightF1: 0.976 -> 0.988Improved
use the full model instead of SCNN for boundaries on No line scenesOurs · CULane lane boundary detection (No line)F1: 0.365 -> 0.351Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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