Lane Detection On Tusimple

평가 지표

Accuracy

F1 score

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Accuracy	F1 score	Paper Title	Repository
LaneATT (ResNet-18)	95.57%	96.71	Keep your Eyes on the Lane: Real-time Attention-guided Lane Detection
CLRNet(ResNet-101)	-	97.62	CLRNet: Cross Layer Refinement Network for Lane Detection
BézierLaneNet (ResNet-34)	95.65%	-	Rethinking Efficient Lane Detection via Curve Modeling
EL-GAN	96.40%	96.26	EL-GAN: Embedding Loss Driven Generative Adversarial Networks for Lane Detection	-
BézierLaneNet (ResNet-18)	95.41%	-	Rethinking Efficient Lane Detection via Curve Modeling
ENet-Label	96.29%	95.23	Agnostic Lane Detection	-
LaneATT (ResNet-122)	96.10%	96.06	Keep your Eyes on the Lane: Real-time Attention-guided Lane Detection
Pairwise pixel supervision + FCN	96.50%	94.31	Learning to Cluster for Proposal-Free Instance Segmentation
Eigenlanes (ResNet-18)	95.62%	-	Eigenlanes: Data-Driven Lane Descriptors for Structurally Diverse Lanes	-
R-34-E2E	96.22%	96.58	End-to-End Lane Marker Detection via Row-wise Classification
CondLaneNet-M(ResNet-34)	95.37%	96.98	CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution
CANet-L(ResNet101)	96.76%	97.77	CANet: Curved Guide Line Network with Adaptive Decoder for Lane Detection	-
LaneAF	95.64%	96.49	LaneAF: Robust Multi-Lane Detection with Affinity Fields
SCNN_UNet_Attention_PL*	98.38	-	Robust Lane Detection through Self Pre-training with Masked Sequential Autoencoders and Fine-tuning with Customized PolyLoss	-
FOLOLane(ERFNet)	96.92	-	Focus on Local: Detecting Lane Marker from Bottom Up via Key Point	-
End-to-end ERFNet	95.24%	90.82	Lane Detection and Classification using Cascaded CNNs
ERFNet	94.5%	-	-	-
GANet(ResNet-18)	-	97.68	A Keypoint-based Global Association Network for Lane Detection
CLLD	96.82	-	Contrastive Learning for Lane Detection via cross-similarity
CANet-S	96.56%	97.51	CANet: Curved Guide Line Network with Adaptive Decoder for Lane Detection	-

0 of 41 row(s) selected.