提出DRAFE模型，提升跨城市交通目标检测精度与鲁棒性。
DRAFE: Domain-Robust Asymmetric Fusion of Heterogeneous Detection Transformers for Cross-City Fine-Grained Traffic Object Detection
- 采用异构检测器的非对称融合策略，提升跨城泛化能力。
- 在AI City挑战赛中达0.4022 mAP，较基线提升0.0553。
- 适合需要高精度细粒度交通识别的智能交通系统应用。
基于深度学习的目标检测器是智能交通系统的核心，支持交通监控、车辆分析和基础设施管理。然而，实现细粒度车辆识别与跨城市域泛化仍具挑战。本文提出领域鲁棒的异构检测器融合集成方法（DRAFE），结合独立训练的LW-DETR与RF-DETR检测器，用于跨城市细粒度交通目标检测。DRAFE采用两阶段训练：首先在多样化公开交通数据集上通过伪标签扩展与人工闭环标注优化，生成包含6,049张图像和203,619个标注的高质量语料库；随后在Project Hafnia Track 6数据集上进行符合竞赛要求的微调。推理时，DRAFE引入锚点条件下的类别一致性匹配、可靠性加权坐标融合、共识感知置信度校准及互补假设恢复机制。在AI City Challenge 2026 Track 6中，DRAFE取得0.4022 mAP，位列25支参赛队伍第6名，较相同基准下初步集成方案提升0.0553 mAP。
原文摘要 · Abstract (English)
Deep learning-based object detectors are fundamental to intelligent transportation systems, enabling traffic monitoring, vehicle analytics, and infrastructure management. However, achieving both fine-grained vehicle recognition and robust cross-city domain generalization remains challenging. We present the Domain-Robust Asymmetric Fusion Ensemble (DRAFE), which combines independently trained LW-DETR and RF-DETR detectors for cross-city fine-grained traffic object detection. DRAFE employs a two-stage training strategy that first pretrains complementary detectors on diverse public traffic datasets using pseudo-label expansion and human-in-the-loop annotation refinement, producing a curated corpus of 6,049 images and 203,619 annotations, before challenge-compliant fine-tuning on the Project Hafnia Track 6 dataset. At inference, DRAFE applies anchor-conditioned class-consistent matching, reliability-weighted coordinate fusion, agreement-aware confidence recalibration, and complementary hypothesis recovery. On AI City Challenge 2026 Track 6, DRAFE achieves 0.4022 mAP, ranks sixth among 25 participating teams, and improves by 0.0553 mAP over a preliminary ensemble evaluated under identical benchmark conditions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。