# DRAFE: Domain-Robust Asymmetric Fusion of Heterogeneous Detection Transformers for Cross-City Fine-Grained Traffic Object Detection

arXiv: https://arxiv.org/abs/2608.16632 · HTML: https://mlsanity.com/paper/2608.16632/

## Key facts

- No citing papers in the map yet (data through 7 Oct 2026).
- Builds on 30 of its 45 references that are in the map.
- First posted on arXiv 17 Aug 2026.

## Builds on (most cited first, 30 of 30)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation](https://mlsanity.com/paper/2012.07177/) (2020)
- [YOLOv10: Real-Time End-to-End Object Detection](https://mlsanity.com/paper/2405.14458/) (2024)
- [Domain Adaptive Faster R-CNN for Object Detection in the Wild](https://mlsanity.com/paper/1803.03243/) (2018)
- [Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming](https://mlsanity.com/paper/1907.07484/) (2019)
- [YOLOv12: Attention-Centric Real-Time Object Detectors](https://mlsanity.com/paper/2502.12524/) (2025)
- [A Simple Semi-Supervised Learning Framework for Object Detection](https://mlsanity.com/paper/2005.04757/) (2020)
- [Strong-Weak Distribution Alignment for Adaptive Object Detection](https://mlsanity.com/paper/1812.04798/) (2018)
- [Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax](https://mlsanity.com/paper/2006.10408/) (2020)
- [Cross-Domain Adaptive Teacher for Object Detection](https://mlsanity.com/paper/2111.13216/) (2021)
- [Learning non-maximum suppression](https://mlsanity.com/paper/1705.02950/) (2017)
- [UA-DETRAC: A New Benchmark and Protocol for Multi-Object Detection and Tracking](https://mlsanity.com/paper/1511.04136/) (2015)
- [CLIP the Gap: A Single Domain Generalization Approach for Object Detection](https://mlsanity.com/paper/2301.05499/) (2023)
- [Augmentation for small object detection](https://mlsanity.com/paper/1902.07296/) (2019)
- [D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement](https://mlsanity.com/paper/2410.13842/) (2024)
- [RF-DETR: Neural Architecture Search for Real-Time Detection Transformers](https://mlsanity.com/paper/2511.09554/) (2025)
- [DEIM: DETR with Improved Matching for Fast Convergence](https://mlsanity.com/paper/2412.04234/) (2024)
- [Equalized Focal Loss for Dense Long-Tailed Object Detection](https://mlsanity.com/paper/2201.02593/) (2022)
- [LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection](https://mlsanity.com/paper/2406.03459/) (2024)
- [Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignment](https://mlsanity.com/paper/2405.14497/) (2024)
- [Roboflow 100: A Rich, Multi-Domain Object Detection Benchmark](https://mlsanity.com/paper/2211.13523/) (2022)
- [Simplifying Source-Free Domain Adaptation for Object Detection: Effective Self-Training Strategies and Performance Insights](https://mlsanity.com/paper/2407.07586/) (2024)
- [The 9th AI City Challenge](https://mlsanity.com/paper/2508.13564/) (2025)
- [Large Self-Supervised Models Bridge the Gap in Domain Adaptive Object Detection](https://mlsanity.com/paper/2503.23220/) (2025)
- [Fine-Grained Vehicle Classification in Urban Traffic Scenes using Deep Learning](https://mlsanity.com/paper/2111.09403/) (2021)
- [DoubleAUG: Single-domain Generalized Object Detector in Urban via Color Perturbation and Dual-style Memory](https://mlsanity.com/paper/2311.13198/) (2023)

## Abstract (arXiv)

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.