# Detection Transformer with Stable Matching

arXiv: https://arxiv.org/abs/2304.04742 · HTML: https://mlsanity.com/paper/2304.04742/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 50 references that are in the map.
- First posted on arXiv 10 Apr 2023.

## Builds on (most cited first, 30 of 36)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [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)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding](https://mlsanity.com/paper/2104.12763/) (2021)
- [Florence: A New Foundation Model for Computer Vision](https://mlsanity.com/paper/2111.11432/) (2021)
- [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)
- [Hybrid Task Cascade for Instance Segmentation](https://mlsanity.com/paper/1901.07518/) (2019)
- [Conditional DETR for Fast Training Convergence](https://mlsanity.com/paper/2108.06152/) (2021)
- [Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection](https://mlsanity.com/paper/2006.04388/) (2020)
- [Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation](https://mlsanity.com/paper/2206.02777/) (2022)
- [End-to-End Semi-Supervised Object Detection with Soft Teacher](https://mlsanity.com/paper/2106.09018/) (2021)
- [TOOD: Task-aligned One-stage Object Detection](https://mlsanity.com/paper/2108.07755/) (2021)
- [Dynamic Head: Unifying Object Detection Heads with Attentions](https://mlsanity.com/paper/2106.08322/) (2021)
- [Fast Convergence of DETR with Spatially Modulated Co-Attention](https://mlsanity.com/paper/2101.07448/) (2021)
- [A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentation](https://mlsanity.com/paper/1810.07842/) (2018)
- [Mask2Former for Video Instance Segmentation](https://mlsanity.com/paper/2112.10764/) (2021)
- [DETRs with Hybrid Matching](https://mlsanity.com/paper/2207.13080/) (2022)
- [Efficient DETR: Improving End-to-End Object Detector with Dense Prior](https://mlsanity.com/paper/2104.01318/) (2021)
- [Sparse DETR: Efficient End-to-End Object Detection with Learnable Sparsity](https://mlsanity.com/paper/2111.14330/) (2021)

## Built on by (most cited first, 30 of 44)

- [DEIM: DETR with Improved Matching for Fast Convergence](https://mlsanity.com/paper/2412.04234/) (2024)
- [Rank-DETR for High Quality Object Detection](https://mlsanity.com/paper/2310.08854/) (2023)
- [Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning](https://mlsanity.com/paper/2309.02999/) (2023)
- [LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection](https://mlsanity.com/paper/2406.03459/) (2024)
- [MS-DETR: Efficient DETR Training with Mixed Supervision](https://mlsanity.com/paper/2401.03989/) (2024)
- [BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos](https://mlsanity.com/paper/2312.00083/) (2023)
- [Relation DETR: Exploring Explicit Position Relation Prior for Object Detection](https://mlsanity.com/paper/2407.11699/) (2024)
- [Latency-aware Unified Dynamic Networks for Efficient Image Recognition](https://mlsanity.com/paper/2308.15949/) (2023)
- [Frozen-DETR: Enhancing DETR with Image Understanding from Frozen Foundation Models](https://mlsanity.com/paper/2410.19635/) (2024)
- [Enhancing 3D Object Detection with 2D Detection-Guided Query Anchors](https://mlsanity.com/paper/2403.06093/) (2024)
- [Efficient Temporal Action Segmentation via Boundary-aware Query Voting](https://mlsanity.com/paper/2405.15995/) (2024)
- [Hausdorff Distance Matching with Adaptive Query Denoising for Rotated Detection Transformer](https://mlsanity.com/paper/2305.07598/) (2023)
- [MI-DETR: An Object Detection Model with Multi-time Inquiries Mechanism](https://mlsanity.com/paper/2503.01463/) (2025)
- [A Strong and Reproducible Object Detector with Only Public Datasets](https://mlsanity.com/paper/2304.13027/) (2023)
- [detrex: Benchmarking Detection Transformers](https://mlsanity.com/paper/2306.07265/) (2023)
- [LP-DETR: Layer-wise Progressive Relations for Object Detection](https://mlsanity.com/paper/2502.05147/) (2025)
- [RETR: Multi-View Radar Detection Transformer for Indoor Perception](https://mlsanity.com/paper/2411.10293/) (2024)
- [DAMap: Distance-aware MapNet for High Quality HD Map Construction](https://mlsanity.com/paper/2510.22675/) (2025)
- [Align-DETR: Enhancing End-to-end Object Detection with Aligned Loss](https://mlsanity.com/paper/2304.07527/) (2023)
- [OD-DETR: Online Distillation for Stabilizing Training of Detection Transformer](https://mlsanity.com/paper/2406.05791/) (2024)
- [PaQ-DETR: Learning Pattern and Quality-Aware Dynamic Queries for Object Detection](https://mlsanity.com/paper/2603.06917/) (2026)
- [CSPCL: Category Semantic Prior Contrastive Learning for Deformable DETR-Based Prohibited Item Detectors](https://mlsanity.com/paper/2501.16665/) (2025)
- [Dual-R-DETR: Resolving Query Competition with Pairwise Routing in Transformer Decoders](https://mlsanity.com/paper/2512.13876/) (2025)
- [DECO: Unleashing the Potential of ConvNets for Query-based Detection and Segmentation](https://mlsanity.com/paper/2312.13735/) (2023)
- [Enhancing DETRs Variants through Improved Content Query and Similar Query Aggregation](https://mlsanity.com/paper/2405.03318/) (2024)
- [MMCL: Correcting Content Query Distributions for Improved Anti-Overlapping X-Ray Object Detection](https://mlsanity.com/paper/2406.03176/) (2024)
- [LQ-Adapter: ViT-Adapter with Learnable Queries for Gallbladder Cancer Detection from Ultrasound Image](https://mlsanity.com/paper/2412.00374/) (2024)
- [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)
- [v-CLR: View-Consistent Learning for Open-World Instance Segmentation](https://mlsanity.com/paper/2504.01383/) (2025)

## Abstract (arXiv)

This paper is concerned with the matching stability problem across different decoder layers in DEtection TRansformers (DETR). We point out that the unstable matching in DETR is caused by a multi-optimization path problem, which is highlighted by the one-to-one matching design in DETR. To address this problem, we show that the most important design is to use and only use positional metrics (like IOU) to supervise classification scores of positive examples. Under the principle, we propose two simple yet effective modifications by integrating positional metrics to DETR's classification loss and matching cost, named position-supervised loss and position-modulated cost. We verify our methods on several DETR variants. Our methods show consistent improvements over baselines. By integrating our methods with DINO, we achieve 50.4 and 51.5 AP on the COCO detection benchmark using ResNet-50 backbones under 12 epochs and 24 epochs training settings, achieving a new record under the same setting. We achieve 63.8 AP on COCO detection test-dev with a Swin-Large backbone. Our code will be made available at https://github.com/IDEA-Research/Stable-DINO.