Research map / Detection and segmentation / CNN features
Keep Your Eyes on the Lane: Real-Time Attention-Guided Lane Detection
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 LaneATT with ResNet-18 rather than the compared real-time baselines | Lane detection on CULane · CULane | F1 (%): 75.09 vs. 72.30 | Helped |
| use LaneATT with ResNet-34 rather than PolyLaneNet | Lane detection · LLAMAS | F1 (%): 88.40 -> 93.74 | Helped |
| add anchor-based pooling instead of using only a single feature-map point per anchor (ablation) | LaneATT · CULane | F1 (%): 64.89 -> 76.68 | Helped |
| use shared prediction layers rather than separate layers for each image boundary (ablation) | LaneATT · CULane | F1 (%): 75.45 -> 76.68 | Helped |
| use shared prediction layers rather than separate layers for each image boundary (ablation) | LaneATT · CULane | FPS: 142 -> 171 | Helped |
| use Focal Loss instead of Cross Entropy (ablation) | LaneATT · CULane | F1 (%): 75.54 -> 76.68 | Helped |
| add the attention mechanism (ablation) | LaneATT · CULane | F1 (%): 75.78 -> 76.68 | Helped |
| add the attention mechanism (ablation) | LaneATT · CULane | FPS: 196 -> 171 | Hurt |
| reduce anchor count from 1000 to 250 (ablation) | LaneATT with ResNet-34 · CULane | F1 (%): 76.66 -> 68.68 | Hurt |
| increase anchor count from 1000 to 1250 (ablation) | LaneATT with ResNet-34 · CULane | F1 (%): 76.66 -> 75.91 | Hurt |
| reduce input size from 360 × 640 to 180 × 320 (ablation) | LaneATT with ResNet-34 · CULane | F1 (%): 76.66 -> 66.74 | Hurt |
| reduce input size from 360 × 640 to 288 × 512 (ablation) | LaneATT with ResNet-34 · CULane | F1 (%): 76.66 -> 75.02 | Hurt |
Closest papers by meaning
- GEONet: Global Enhancement and Optimization Network for Lane Detection (AAAI 2025 · similarity 0.90)
- Sketch and Refine: Towards Fast and Accurate Lane Detection (AAAI 2024 · similarity 0.89)
- Rethinking Lanes and Points in Complex Scenarios for Monocular 3D Lane Detection (CVPR 2025 · similarity 0.89)
- GSENet:Global Semantic Enhancement Network for Lane Detection (AAAI 2024 · similarity 0.89)
- A Hybrid Global-Local Perception Network for Lane Detection (AAAI 2024 · similarity 0.89)
- PVALane: Prior-Guided 3D Lane Detection with View-Agnostic Feature Alignment (AAAI 2024 · 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.