Research map / Detection and segmentation / CNN features
Ultra Fast Deep Lane Detection With Hybrid Anchor Driven Ordinal Classification
Zequn Qin, Pengyi Zhang, 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 |
|---|---|---|---|
| use hybrid anchors instead of row anchors only (ablation) | UFLDv2 (ResNet-18) · CULane | F1 (%): 66.09 -> 74.70 | Improved |
| use hybrid anchors instead of column anchors only (ablation) | UFLDv2 (ResNet-18) · CULane | F1 (%): 57.29 -> 74.70 | Improved |
| use ordinal classification instead of regression (ablation) | UFLDv2 (ResNet-18) · CULane | F1 (%): 64.29 -> 74.70 | Improved |
| use ordinal classification (expectation, three losses) instead of standard classification (ablation) | UFLDv2 (ResNet-18) · CULane | F1 (%): 67.24 -> 74.70 | Improved |
| add expectation loss to base cross-entropy loss (ablation) | UFLDv2 (ResNet-18) · CULane | F1 (%): 74.18 -> 74.70 | Improved |
| use expectation loss alone instead of base loss (ablation) | UFLDv2 (ResNet-18) · CULane | F1 (%): 74.18 -> 69.70 | Hurt |
| add feature level test time augmentation (ablation) | UFLDv2 (ResNet-18) · CULane | F1 total (%): 74.7 -> 75.0 | Improved |
| add feature level test time augmentation (ablation) | UFLDv2 (ResNet-34) · CULane | F1 total (%): 75.9 -> 76.0 | No clear effect |
| use UFLDv2 (hybrid anchor, ordinal classification) over original UFLD | ResNet-18 · CULane | F1 total (%): 68.4 -> 74.7 | Improved |
| use classification formulation instead of segmentation (ResNet-18) | UFLDv2 · TuSimple | accuracy (%): 92.69 -> 95.84 | Improved |
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.
- RESA — RESA: Recurrent Feature-Shift Aggregator for Lane Detection (AAAI 2021) · better on 1 of 1 shared result
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
- A Hybrid Global-Local Perception Network for Lane Detection (AAAI 2024 · similarity 0.89)
- GEONet: Global Enhancement and Optimization Network for Lane Detection (AAAI 2025 · similarity 0.88)
- GSENet:Global Semantic Enhancement Network for Lane Detection (AAAI 2024 · similarity 0.88)
- Sketch and Refine: Towards Fast and Accurate Lane Detection (AAAI 2024 · similarity 0.87)
- Rethinking Lanes and Points in Complex Scenarios for Monocular 3D Lane Detection (CVPR 2025 · similarity 0.87)
- PVALane: Prior-Guided 3D Lane Detection with View-Agnostic Feature Alignment (AAAI 2024 · similarity 0.86)
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.
