AI Paper Atlas

Research map / Detection and segmentation / CNN features

RESA: Recurrent Feature-Shift Aggregator for Lane Detection

Tu Zheng, Hao Fang, Yi Zhang, Wenjian Tang, Zheng Yang, Haifeng Liu, Deng Cai

AAAI 2021 · Detection and segmentation › CNN features · approach: Lane detection · 307 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 RESA to a ResNet-34 baseline (ablation)ResNet-34 lane detector · CULaneF1: 65.1 -> 74.3Improved
Replace direct bilinear up-sampling with BUSD (ablation)ResNet-34 lane detector · CULaneF1: 65.1 -> 68.6Improved
Add both RESA and BUSD (ablation)ResNet-34 lane detector · CULaneF1: 65.1 -> 74.5Improved
Add spatial aggregation directions progressively (ablation)RESA with ResNet-34 · CULaneF1-measure: 72.4 -> 73.7 -> 74.4 -> 74.5Improved
Replace addition with maximum feature aggregation (ablation)RESA_DULR · CULaneF1-measure: 74.5 -> 74.4No clear effect
Increase RESA iterations from 1 to 4 (ablation)RESA with ResNet-34 · CULaneF1-measure: 73.2 -> 74.5Improved
Increase RESA iterations from 4 to 5 (ablation)RESA with ResNet-34 · CULaneF1-measure: 74.5 -> 74.5No clear effect
Use RESA instead of SCNN (ablation)VGG16 lane detector · CULaneF1-measure: 72.3 -> 73.3Improved
Use RESA instead of SCNN (ablation)ResNet-34 lane detector · CULaneF1-measure: 72.7 -> 74.5Improved
Use RESA rather than SCNN message passingRESA and SCNN runtime comparison, kernel width 7 · Runtime comparisonruntime (ms): 43.5 -> 3.8Improved
Use RESA rather than SCNN message passingRESA and SCNN runtime comparison, kernel width 9 · Runtime comparisonruntime (ms): 44.0 -> 4.0Improved
Use RESA rather than SCNN message passingRESA and SCNN runtime comparison, kernel width 11 · Runtime comparisonruntime (ms): 44.6 -> 4.4Improved

Later papers that compared with this method

1 later accepted paper reports RESA as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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