mlsanityData to 7 Oct 2026

DN-DETR: Accelerate DETR Training by Introducing Query DeNoising

arXiv 2203.01305 ↗First posted 2 Mar 2022cs.CV cs.AIcited by 486

Not on the map. Why?

Abstract (arXiv)

We present in this paper a novel denoising training method to speedup DETR (DEtection TRansformer) training and offer a deepened understanding of the slow convergence issue of DETR-like methods. We show that the slow convergence results from the instability of bipartite graph matching which causes inconsistent optimization goals in early training stages. To address this issue, except for the Hungarian loss, our method additionally feeds ground-truth bounding boxes with noises into Transformer decoder and trains the model to reconstruct the original boxes, which effectively reduces the bipartite graph matching difficulty and leads to a faster convergence. Our method is universal and can be easily plugged into any DETR-like methods by adding dozens of lines of code to achieve a remarkable improvement. As a result, our DN-DETR results in a remarkable improvement (+1.9AP) under the same setting and achieves the best result (AP 43.4 and 48.6 with 12 and 50 epochs of training respectively) among DETR-like methods with ResNet-50 backbone. Compared with the baseline under the same setting, DN-DETR achieves comparable performance with 50% training epochs. Code is available at urlhttps://github.com/FengLi-ust/DN-DETR.

Key facts. Cited by 486 papers in the map (data through 7 Oct 2026). Builds on 18 of its 29 references that are in the map. First posted on arXiv 2 Mar 2022.

Builds on

18 of 29 references.

References · 18

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2020End-to-End Object Detection with Transformerscited by 7,384
  6. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  7. 2018YOLOv3: An Incremental Improvementcited by 2,652
  8. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  9. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  10. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  11. 2017Focal Loss for Dense Object Detectioncited by 749
  12. 2022DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETRcited by 569
6 more
  1. 2019Hybrid Task Cascade for Instance Segmentationcited by 479
  2. 2021Conditional DETR for Fast Training Convergencecited by 422
  3. 2021Pix2seq: A Language Modeling Framework for Object Detectioncited by 345
  4. 2021Fast Convergence of DETR with Spatially Modulated Co-Attentioncited by 176
  5. 2020Rethinking Transformer-based Set Prediction for Object Detectioncited by 156
  6. 2021Efficient DETR: Improving End-to-End Object Detector with Dense Priorcited by 128

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 51; 2023: 139; 2024: 126; 2025: 95; 2026: 75.

486 papers.

Sort:

By area:

  1. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  2. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,306
  3. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  4. 2024Grounded SAM: Assembling Open-World Models for Diverse Visual Taskscited by 914
  5. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 526
  6. 2024YOLOv10: Real-Time End-to-End Object Detectioncited by 508
  7. 2023Segment Anything in High Qualitycited by 373
  8. 2022DiffusionDet: Diffusion Model for Object Detectioncited by 354
  9. 2022PETRv2: A Unified Framework for 3D Perception from Multi-Camera Imagescited by 351
  10. 2022Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentationcited by 341
  11. 2022OneFormer: One Transformer to Rule Universal Image Segmentationcited by 327
  12. 2023Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detectioncited by 313
38 more
  1. 2025YOLOv12: Attention-Centric Real-Time Object Detectorscited by 300
  2. 2022DETRs with Collaborative Hybrid Assignments Trainingcited by 273
  3. 2022VectorMapNet: End-to-end Vectorized HD Map Learningcited by 243
  4. 2023A Simple Framework for Open-Vocabulary Segmentation and Detectioncited by 197
  5. 2023MapTRv2: An End-to-End Framework for Online Vectorized HD Map Constructioncited by 192
  6. 2023Universal Instance Perception as Object Discovery and Retrievalcited by 190
  7. 2023Query-Dependent Video Representation for Moment Retrieval and Highlight Detectioncited by 166
  8. 2022DETRs with Hybrid Matchingcited by 149
  9. 2023SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videoscited by 149
  10. 2022MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectorscited by 148
  11. 2023Transformer-Based Visual Segmentation: A Surveycited by 124
  12. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
  13. 2024GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editingcited by 114
  14. 2022Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignmentcited by 96
  15. 2024T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergycited by 94
  16. 2022MonoDETR: Depth-guided Transformer for Monocular 3D Object Detectioncited by 85
  17. 2023Knowing Where to Focus: Event-aware Transformer for Video Groundingcited by 79
  18. 2023Dense Distinct Query for End-to-End Object Detectioncited by 76
  19. 2024D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinementcited by 73
  20. 2023Far3D: Expanding the Horizon for Surround-view 3D Object Detectioncited by 70
  21. 2023Sparse4D v3: Advancing End-to-End 3D Detection and Trackingcited by 69
  22. 2023Cross Modal Transformer: Towards Fast and Robust 3D Object Detectioncited by 68
  23. 2024MapTracker: Tracking with Strided Memory Fusion for Consistent Vector HD Mappingcited by 67
  24. 2024DEIM: DETR with Improved Matching for Fast Convergencecited by 67
  25. 2023Detecting Everything in the Open World: Towards Universal Object Detectioncited by 62
  26. 2023FocalFormer3D : Focusing on Hard Instance for 3D Object Detectioncited by 58
  27. 2024OPUS: Occupancy Prediction Using a Sparse Setcited by 56
  28. 2023Hierarchical Open-vocabulary Universal Image Segmentationcited by 53
  29. 2023CrossKD: Cross-Head Knowledge Distillation for Object Detectioncited by 50
  30. 2023Rank-DETR for High Quality Object Detectioncited by 49
  31. 2023Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimationcited by 48
  32. 2026Ultralytics YOLO26: Unified Real-Time End-to-End Vision Modelscited by 47
  33. 2024Leveraging Enhanced Queries of Point Sets for Vectorized Map Constructioncited by 46
  34. 2023Mask-Attention-Free Transformer for 3D Instance Segmentationcited by 45
  35. 2023RLIPv2: Fast Scaling of Relational Language-Image Pre-trainingcited by 44
  36. 2023Detection Transformer with Stable Matchingcited by 43
  37. 2024Stream Query Denoising for Vectorized HD Map Constructioncited by 43
  38. 2024TAPTR: Tracking Any Point with Transformers as Detectioncited by 43

50 most cited of 486 All 486 (JSON)