Research map / Detection and segmentation / CNN features
Ultra Fast Structure-aware Deep Lane Detection
Zequn Qin, Huanyu Wang, Xi Li
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 changed | Where | Measured | Effect |
|---|---|---|---|
| replace segmentation with row-based selecting formulation (ablation) | Ours · TuSimple (module ablation, ResNet-34) | accuracy: 92.84 -> 95.64 | Improved |
| add lane structural loss (ablation) | Ours · TuSimple (module ablation, ResNet-34) | accuracy: 95.64 -> 95.96 | Improved |
| add feature aggregation (ablation) | Ours · TuSimple (module ablation, ResNet-34) | accuracy: 95.64 -> 95.98 | Improved |
| add both structural loss and feature aggregation (ablation) | Ours · TuSimple (module ablation, ResNet-34) | accuracy: 95.64 -> 96.06 | Improved |
| use classification instead of regression (ablation) | Ours · TuSimple | accuracy: 71.59 -> 95.77 | Improved |
| normalize regression targets (ablation) | Ours · TuSimple | accuracy: 71.59 -> 67.24 | Hurt |
| use expectation-based localization instead of argmax (ablation) | Ours · TuSimple | accuracy: 95.77 -> 95.87 | Improved |
| increase number of gridding cells (ablation) | Ours · TuSimple | classification accuracy | Hurt |
| use lane similarity loss (ablation) | Ours · TuSimple | accuracy | Improved |
| use row-based formulation vs plain segmentation with ResNet-34 | Res34 · TuSimple test | runtime (ms): 50.5 -> 5.9 | Improved |
| use row-based formulation vs plain segmentation with ResNet-34 | Res34 · TuSimple test | accuracy: 92.84 -> 96.06 | Improved |
| use ResNet-34 instead of ResNet-18 backbone | Ours · CULane test (total) | F1-measure: 68.4 -> 72.3 | Improved |
Closest papers by meaning
- GEONet: Global Enhancement and Optimization Network for Lane Detection (AAAI 2025 · similarity 0.89)
- Sketch and Refine: Towards Fast and Accurate Lane Detection (AAAI 2024 · similarity 0.89)
- A Hybrid Global-Local Perception Network for Lane Detection (AAAI 2024 · similarity 0.89)
- GSENet:Global Semantic Enhancement Network for Lane Detection (AAAI 2024 · similarity 0.89)
- LaneCPP: Continuous 3D Lane Detection using Physical Priors (CVPR 2024 · similarity 0.88)
- Rethinking Lanes and Points in Complex Scenarios for Monocular 3D Lane Detection (CVPR 2025 · similarity 0.88)
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.
