# Relation DETR: Exploring Explicit Position Relation Prior for Object Detection

arXiv: https://arxiv.org/abs/2407.11699 · HTML: https://mlsanity.com/paper/2407.11699/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 52 references that are in the map.
- First posted on arXiv 16 Jul 2024.

## Builds on (most cited first, 30 of 38)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (2022)
- [DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR](https://mlsanity.com/paper/2201.12329/) (2022)
- [DN-DETR: Accelerate DETR Training by Introducing Query DeNoising](https://mlsanity.com/paper/2203.01305/) (2022)
- [YOLACT: Real-time Instance Segmentation](https://mlsanity.com/paper/1904.02689/) (2019)
- [Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection](https://mlsanity.com/paper/2006.04388/) (2020)
- [A Survey of Transformers](https://mlsanity.com/paper/2106.04554/) (2021)
- [Soft-NMS -- Improving Object Detection With One Line of Code](https://mlsanity.com/paper/1704.04503/) (2017)
- [EVA-02: A Visual Representation for Neon Genesis](https://mlsanity.com/paper/2303.11331/) (2023)
- [Relation Networks for Object Detection](https://mlsanity.com/paper/1711.11575/) (2017)
- [DETRs with Collaborative Hybrid Assignments Training](https://mlsanity.com/paper/2211.12860/) (2022)
- [VarifocalNet: An IoU-aware Dense Object Detector](https://mlsanity.com/paper/2008.13367/) (2020)
- [TOOD: Task-aligned One-stage Object Detection](https://mlsanity.com/paper/2108.07755/) (2021)
- [DETRs with Hybrid Matching](https://mlsanity.com/paper/2207.13080/) (2022)
- [Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment](https://mlsanity.com/paper/2207.13085/) (2022)
- [Dense Distinct Query for End-to-End Object Detection](https://mlsanity.com/paper/2303.12776/) (2023)
- [Adaptive NMS: Refining Pedestrian Detection in a Crowd](https://mlsanity.com/paper/1904.03629/) (2019)

## Built on by (most cited first, 28 of 28)

- [Relation3D: Enhancing Relation Modeling for Point Cloud Instance Segmentation](https://mlsanity.com/paper/2506.17891/) (2025)
- [MI-DETR: An Object Detection Model with Multi-time Inquiries Mechanism](https://mlsanity.com/paper/2503.01463/) (2025)
- [LP-DETR: Layer-wise Progressive Relations for Object Detection](https://mlsanity.com/paper/2502.05147/) (2025)
- [InteractionMap: Improving Online Vectorized HDMap Construction with Interaction](https://mlsanity.com/paper/2503.21659/) (2025)
- [PaQ-DETR: Learning Pattern and Quality-Aware Dynamic Queries for Object Detection](https://mlsanity.com/paper/2603.06917/) (2026)
- [GigaCheck: Detecting LLM-generated Content via Object-Centric Span Localization](https://mlsanity.com/paper/2410.23728/) (2024)
- [Geometry-Guided Representations for Coherent Lane and Traffic Topology Reasoning in Driving Scenes](https://mlsanity.com/paper/2506.13553/) (2025)
- [Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processing](https://mlsanity.com/paper/2603.24326/) (2026)
- [Multiscale Tensor Summation Factorization as a New Neural Network Layer (MTS Layer) for Multidimensional Data Processing](https://mlsanity.com/paper/2504.13975/) (2025)
- [RelMap: Enhancing Online Map Construction with Class-Aware Spatial Relation and Semantic Priors](https://mlsanity.com/paper/2507.21567/) (2025)
- [Integrating Diverse Assignment Strategies into DETRs](https://mlsanity.com/paper/2601.09247/) (2026)
- [Mr. DETR++: Instructive Multi-Route Training for Detection Transformers with Mixture-of-Experts](https://mlsanity.com/paper/2412.10028/) (2024)
- [CQ-DINO: Mitigating Gradient Dilution via Category Queries for Vast Vocabulary Object Detection](https://mlsanity.com/paper/2503.18430/) (2025)
- [FruitProm: Probabilistic Maturity Estimation and Detection of Fruits and Vegetables](https://mlsanity.com/paper/2510.24885/) (2025)
- [PARL: Position-Aware Relation Learning Network for Document Layout Analysis](https://mlsanity.com/paper/2601.07620/) (2026)
- [Salience-SGG: Enhancing Unbiased Scene Graph Generation with Iterative Salience Estimation](https://mlsanity.com/paper/2601.08728/) (2026)
- [TopoHR: Hierarchical Centerline Representation for Cyclic Topology Reasoning in Driving Scenes with Point-to-Instance Relations](https://mlsanity.com/paper/2604.24119/) (2026)
- [MDS-DETR: DETR with Masked Duplicate Suppressor](https://mlsanity.com/paper/2605.23507/) (2026)
- [Fine-Grained Open-Vocabulary Object Recognition via User-Guided Segmentation](https://mlsanity.com/paper/2411.15620/) (2024)
- [FreeVPS: Repurposing Training-Free SAM2 for Generalizable Video Polyp Segmentation](https://mlsanity.com/paper/2508.19705/) (2025)
- [Holi-DETR: Holistic Fashion Item Detection Leveraging Contextual Information](https://mlsanity.com/paper/2512.23221/) (2025)
- [FUSEP: A Multi-Center Benchmark for Diverse Tasks in Early Pregnancy Fetal Ultrasound Screening](https://mlsanity.com/paper/2608.04766/) (2026)
- [Local Gains and Fixed-Assignment Set Losses in Shared Set Decoders](https://mlsanity.com/paper/2608.14717/) (2026)
- [GSO-Net: Visual State Machines for Hazardous Freight Transfer Compliance at Petrochemical Logistics Nodes](https://mlsanity.com/paper/2609.12408/) (2026)
- [End-to-End Cell Detection via Instance-aware Graph Modeling](https://mlsanity.com/paper/2609.15354/) (2026)
- [Enhanced Knowledge Distillation for Detection Transformer via Teacher Prediction Refinement](https://mlsanity.com/paper/2609.19964/) (2026)
- [Match One, Learn with Graph: One-to-Graph Query Collaboration with Backward Sharing for Object Detection](https://mlsanity.com/paper/2609.26092/) (2026)
- [Order Matters: Competition-Guided Query Ordering for RNN-Based Object Detection](https://mlsanity.com/paper/2610.05191/) (2026)

## Abstract (arXiv)

This paper presents a general scheme for enhancing the convergence and performance of DETR (DEtection TRansformer). We investigate the slow convergence problem in transformers from a new perspective, suggesting that it arises from the self-attention that introduces no structural bias over inputs. To address this issue, we explore incorporating position relation prior as attention bias to augment object detection, following the verification of its statistical significance using a proposed quantitative macroscopic correlation (MC) metric. Our approach, termed Relation-DETR, introduces an encoder to construct position relation embeddings for progressive attention refinement, which further extends the traditional streaming pipeline of DETR into a contrastive relation pipeline to address the conflicts between non-duplicate predictions and positive supervision. Extensive experiments on both generic and task-specific datasets demonstrate the effectiveness of our approach. Under the same configurations, Relation-DETR achieves a significant improvement (+2.0% AP compared to DINO), state-of-the-art performance (51.7% AP for 1x and 52.1% AP for 2x settings), and a remarkably faster convergence speed (over 40% AP with only 2 training epochs) than existing DETR detectors on COCO val2017. Moreover, the proposed relation encoder serves as a universal plug-in-and-play component, bringing clear improvements for theoretically any DETR-like methods. Furthermore, we introduce a class-agnostic detection dataset, SA-Det-100k. The experimental results on the dataset illustrate that the proposed explicit position relation achieves a clear improvement of 1.3% AP, highlighting its potential towards universal object detection. The code and dataset are available at https://github.com/xiuqhou/Relation-DETR.