Reusing Attention for One-stage Lane Topology Understanding

• URL: http://arxiv.org/abs/2507.17617v1
• Date: Wed, 23 Jul 2025 15:48:16 GMT
• Title: Reusing Attention for One-stage Lane Topology Understanding
• Authors: Yang Li, Zongzheng Zhang, Xuchong Qiu, Xinrun Li, Ziming Liu, Leichen Wang, Ruikai Li, Zhenxin Zhu, Huan-ang Gao, Xiaojian Lin, Zhiyong Cui, Hang Zhao, Hao Zhao,
• Abstract summary: We propose a one-stage architecture that simultaneously predicts traffic elements, lane centerlines and topology relationship.<n>Our key innovation lies in reusing intermediate attention resources within distinct transformer decoders.<n>Our approach outperforms baseline methods in both accuracy and efficiency.
• Score: 32.464423838732635
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Understanding lane toplogy relationships accurately is critical for safe autonomous driving. However, existing two-stage methods suffer from inefficiencies due to error propagations and increased computational overheads. To address these challenges, we propose a one-stage architecture that simultaneously predicts traffic elements, lane centerlines and topology relationship, improving both the accuracy and inference speed of lane topology understanding for autonomous driving. Our key innovation lies in reusing intermediate attention resources within distinct transformer decoders. This approach effectively leverages the inherent relational knowledge within the element detection module to enable the modeling of topology relationships among traffic elements and lanes without requiring additional computationally expensive graph networks. Furthermore, we are the first to demonstrate that knowledge can be distilled from models that utilize standard definition (SD) maps to those operates without using SD maps, enabling superior performance even in the absence of SD maps. Extensive experiments on the OpenLane-V2 dataset show that our approach outperforms baseline methods in both accuracy and efficiency, achieving superior results in lane detection, traffic element identification, and topology reasoning. Our code is available at https://github.com/Yang-Li-2000/one-stage.git.

Related papers

• TopoStreamer: Temporal Lane Segment Topology Reasoning in Autonomous Driving [52.25176274203747]
  TopoStreamer is an end-to-end temporal perception model for lane segment topology reasoning.<n>TopoStreamer introduces three key improvements: streaming attribute constraints, dynamic lane boundary positional encoding, and lane segment denoising.<n>On the Open-Lane-V2 dataset, TopoStreamer demonstrates significant improvements over state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-07-01T12:10:46Z)
• RelTopo: Enhancing Relational Modeling for Driving Scene Topology Reasoning [55.21557415676928]
  Road topology reasoning is critical for autonomous driving, enabling effective navigation and adherence to traffic regulations.<n>Existing methods typically focus on either lane detection or Lane-to-Lane (L2L) topology reasoning, often textitneglecting Lane-to-Traffic-element (L2T) relationships to optimize these tasks jointly.<n>We argue that relational modeling is beneficial for both perception and reasoning, as humans naturally leverage contextual relationships for road element recognition and their connectivity inference.
  arXiv  Detail & Related papers  (2025-06-16T14:40:28Z)
• SMART: Advancing Scalable Map Priors for Driving Topology Reasoning [24.614973933683352]
  Topology reasoning is crucial for autonomous driving as it enables comprehensive understanding of connectivity and relationships between lanes and traffic elements.<n>Recent approaches have shown success in perceiving driving topology using vehicle-mounted sensors.<n>We identify that the key factor in scalable lane perception and topology reasoning is the elimination of this sensor-dependent feature.
  arXiv  Detail & Related papers  (2025-02-06T18:59:57Z)
• Monocular Lane Detection Based on Deep Learning: A Survey [51.19079381823076]
  Lane detection plays an important role in autonomous driving perception systems.<n>As deep learning algorithms gain popularity, monocular lane detection methods based on them have demonstrated superior performance.<n>This paper presents a comprehensive overview of existing methods, encompassing both the increasingly mature 2D lane detection approaches and the developing 3D lane detection works.
  arXiv  Detail & Related papers  (2024-11-25T12:09:43Z)
• TopoSD: Topology-Enhanced Lane Segment Perception with SDMap Prior [70.84644266024571]
  We propose to train a perception model to "see" standard definition maps (SDMaps) We encode SDMap elements into neural spatial map representations and instance tokens, and then incorporate such complementary features as prior information. Based on the lane segment representation framework, the model simultaneously predicts lanes, centrelines and their topology.
  arXiv  Detail & Related papers  (2024-11-22T06:13:42Z)
• Attention-based U-Net Method for Autonomous Lane Detection [0.5461938536945723]
  Two deep learning-based lane recognition methods are proposed in this study. The first method employs the Feature Pyramid Network (FPN) model, delivering an impressive 87.59% accuracy in detecting road lanes. The second method, which incorporates attention layers into the U-Net model, significantly boosts the performance of semantic segmentation tasks.
  arXiv  Detail & Related papers  (2024-11-16T22:20:11Z)
• Cross Dataset Analysis and Network Architecture Repair for Autonomous Car Lane Detection [5.428120316375907]
  We have performed cross dataset analysis and network architecture repair for the lane detection application in autonomous vehicles. ERFCondLaneNet is an enhancement to the CondlaneNet used for lane identification framework to solve the difficulty of detecting lane lines with complex topologies.
  arXiv  Detail & Related papers  (2024-09-10T20:27:49Z)
• Graph-based Topology Reasoning for Driving Scenes [102.35885039110057]
  We present TopoNet, the first end-to-end framework capable of abstracting traffic knowledge beyond conventional perception tasks. We evaluate TopoNet on the challenging scene understanding benchmark, OpenLane-V2.
  arXiv  Detail & Related papers  (2023-04-11T15:23:29Z)
• Penalty-Based Imitation Learning With Cross Semantics Generation Sensor Fusion for Autonomous Driving [1.2749527861829049]
  In this paper, we provide a penalty-based imitation learning approach to integrate multiple modalities of information. We observe a remarkable increase in the driving score by more than 12% when compared to the state-of-the-art (SOTA) model, InterFuser. Our model achieves this performance enhancement while achieving a 7-fold increase in inference speed and reducing the model size by approximately 30%.
  arXiv  Detail & Related papers  (2023-03-21T14:29:52Z)
• A Driving Behavior Recognition Model with Bi-LSTM and Multi-Scale CNN [59.57221522897815]
  We propose a neural network model based on trajectories information for driving behavior recognition. We evaluate the proposed model on the public BLVD dataset, achieving a satisfying performance.
  arXiv  Detail & Related papers  (2021-03-01T06:47:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.