AI Paper Atlas

Research map / Benchmarks / CULane

CULane leaderboard

11 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on CULane. Best F1: 81.83 (HGLNet, AAAI 2024).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

CULane · F1

11 papers, each with its best reported number for its own method; higher is better.

#F1 ↑MethodPaperTopic
181.83HGLNet
DLA-34
A Hybrid Global-Local Perception Network for Lane Detection
AAAI 2024 · Table 1
CNN features
280.85Our method (base)
Swin Transformer base
A Siamese Transformer with Hierarchical Refinement for Lane Detection
NeurIPS 2024 · Table 2
CNN features
380.77Ours
ResNet-101
Generating Dynamic Kernels via Transformers for Lane Detection
ICCV 2023 · Table 2
CNN features
480.5RCLane-LRCLane: Relay Chain Prediction for Lane Detection
ECCV 2022 · Table 2
CNN features
579.64Lane2Seq (segmentation)
ViT-Base
Lane2Seq: Towards Unified Lane Detection via Sequence Generation
CVPR 2024 · Table 6
CNN features
679.63GANet-L
ResNet-101
A Keypoint-Based Global Association Network for Lane Detection
CVPR 2022 · Table: Comparison with state-o
Point cloud classification
778.9SRLane
ResNet18
Sketch and Refine: Towards Fast and Accurate Lane Detection
AAAI 2024 · Table: Comparison of F1-measur
CNN features
877.06Laneformer (ResNet-50)
ResNet-50
Laneformer: Object-Aware Row-Column Transformers for Lane Detection
AAAI 2022 · Table 1
CNN features
977.02LaneATT (ResNet-122)
ResNet-122
Keep Your Eyes on the Lane: Real-Time Attention-Guided Lane Detection
CVPR 2021 · Table: State-of-the-art result
CNN features
1075.57BézierLaneNet (ResNet-34)
ResNet-34
Rethinking Efficient Lane Detection via Curve Modeling
CVPR 2022 · Table 1
CNN features
1 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.