AI Paper Atlas

Research map / Detection and segmentation / CNN features

Rethinking Efficient Lane Detection via Curve Modeling

Zhengyang Feng, Shaohua Guo, Xin Tan, Ke Xu, Min Wang, Lizhuang Ma

CVPR 2022 · Detection and segmentation › CNN features · approach: Lane detection · 218 citations (OpenAlex)

This paper tried a common change: Add data augmentation

Add strong data augmentation · CULane test · F1: 55.11 -> 75.41 Improved

What 689 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

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
Use on-image cubic Bézier curves instead of 3rd-order polynomial curves (ablation)BézierLaneNet · CULane testF1: 5.01 -> 75.41Improved
Use sampling loss instead of direct control-point loss (ablation)Bézier curve fitting · CULane testF1: 63.74 -> 68.89Improved
Add feature flip fusion (ablation)BézierLaneNet · CULane testF1: 68.89 -> 70.28Improved
Add auxiliary segmentation loss without feature flip fusion (ablation)Sampling-loss baseline · CULane testF1: 68.89 -> 65.82Hurt
Add auxiliary segmentation loss alongside feature flip fusion (ablation)BézierLaneNet · CULane testF1: 70.28 -> 73.97Improved
Use deformable convolution to align flipped features (ablation)Feature flip fusion · CULane testF1: 70.28 -> 72.96Improved
Use deformable convolution rather than standard convolution in feature flip fusion with auxiliary segmentation (ablation)BézierLaneNet · CULane testF1: 73.97 -> 75.41Improved
Add strong data augmentation (ablation)BézierLaneNet (ResNet-34) · CULane testF1: 55.11 -> 75.41Improved
Add strong data augmentation (ablation)LSTR (ResNet-18, 2×) · CULane testF1: 39.77 -> 68.72Improved
Add feature flip fusion (ablation)Bézier baseline · TuSimple testAccuracy: 93.36 -> 95.26 (+ 1.90)Improved
Add feature flip fusion (ablation)Bézier baseline · LLAMAS valF1: 95.27 -> 96.00~(+ 0.73)Improved
Apply strong augmentation to segmentation-based methods (ablation)Segmentation-based lane detectors · TuSimpleperformance: 1~2%Hurt

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