Loss function ablation experiment results.

<div><p>Lane detection seeks to accurately identify the position and geometry of lane markings in real-world driving environments. However, existing models often struggle with robustness and accuracy due to insufficient integration of high-level semantic understanding and low-level geome...

Full description

Saved in:

Bibliographic Details
Main Author:	Mingliang Chen (210279) (author)
Other Authors:	Qinhao Jia (22537886) (author), Jing Yang (13969) (author), Shuxian Liu (5105021) (author)
Published:	2025
Subjects:	Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified world driving environments similar parameter sizes level semantic understanding experimental results show enhance feature interactions cross attention mechanism applies polynomial regression stage backbone network level geometric features lane detection seeks lane detection model div >< p approach lies lmamba refine stage model architecture lane markings geometric structures synergistic combination sequential patterns refine paradigm publicly release mamba architecture lmamba achieves lmamba </ lightweight three lane criss insufficient integration f1 score effectively capturing curvelet transform clam ), boost performance accurately identify accuracy due accelerates inference
Tags:	Add Tag No Tags, Be the first to tag this record!

Loss function ablation experiment results.

Similar Items