mlsanityData to 7 Oct 2026

DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR

arXiv 2201.12329 ↗First posted 28 Jan 2022cs.CVcited by 569

Not on the map. Why?

Abstract (arXiv)

We present in this paper a novel query formulation using dynamic anchor boxes for DETR (DEtection TRansformer) and offer a deeper understanding of the role of queries in DETR. This new formulation directly uses box coordinates as queries in Transformer decoders and dynamically updates them layer-by-layer. Using box coordinates not only helps using explicit positional priors to improve the query-to-feature similarity and eliminate the slow training convergence issue in DETR, but also allows us to modulate the positional attention map using the box width and height information. Such a design makes it clear that queries in DETR can be implemented as performing soft ROI pooling layer-by-layer in a cascade manner. As a result, it leads to the best performance on MS-COCO benchmark among the DETR-like detection models under the same setting, e.g., AP 45.7% using ResNet50-DC5 as backbone trained in 50 epochs. We also conducted extensive experiments to confirm our analysis and verify the effectiveness of our methods. Code is available at urlhttps://github.com/SlongLiu/DAB-DETR.

Key facts. Cited by 569 papers in the map (data through 7 Oct 2026). Builds on 20 of its 24 references that are in the map. First posted on arXiv 28 Jan 2022.

Builds on

20 of 24 references.

References · 20

  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. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  7. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  8. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  9. 2015Fast R-CNNcited by 2,930
  10. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
  11. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  12. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
8 more
  1. 2019Objects as Pointscited by 1,172
  2. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,064
  3. 2017Focal Loss for Dense Object Detectioncited by 749
  4. 2020Sparse R-CNN: End-to-End Object Detection with Learnable Proposalscited by 494
  5. 2021Conditional DETR for Fast Training Convergencecited by 422
  6. 2021Fast Convergence of DETR with Spatially Modulated Co-Attentioncited by 176
  7. 2020Rethinking Transformer-based Set Prediction for Object Detectioncited by 156
  8. 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: 64; 2023: 149; 2024: 167; 2025: 115; 2026: 74.

569 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. 2024Grounded SAM: Assembling Open-World Models for Diverse Visual Taskscited by 914
  4. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 550
  5. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 526
  6. 2024YOLOv10: Real-Time End-to-End Object Detectioncited by 508
  7. 2022DN-DETR: Accelerate DETR Training by Introducing Query DeNoisingcited by 486
  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. 2025YOLOv12: Attention-Centric Real-Time Object Detectorscited by 300
38 more
  1. 2022DETRs with Collaborative Hybrid Assignments Trainingcited by 273
  2. 2022Motion Transformer with Global Intention Localization and Local Movement Refinementcited by 267
  3. 2022Visual Attention Networkcited by 210
  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. 2023Query-Dependent Video Representation for Moment Retrieval and Highlight Detectioncited by 166
  7. 2022DETRs with Hybrid Matchingcited by 149
  8. 2023SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videoscited by 149
  9. 2022MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectorscited by 148
  10. 2023MTR++: Multi-Agent Motion Prediction with Symmetric Scene Modeling and Guided Intention Queryingcited by 139
  11. 2023CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matchingcited by 133
  12. 2025DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Drivingcited by 125
  13. 2023Transformer-Based Visual Segmentation: A Surveycited by 124
  14. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
  15. 2024GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editingcited by 114
  16. 2022ConvMAE: Masked Convolution Meets Masked Autoencoderscited by 105
  17. 2022CenterFormer: Center-based Transformer for 3D Object Detectioncited by 99
  18. 2022Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignmentcited by 96
  19. 2024T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergycited by 94
  20. 2023MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Trackingcited by 86
  21. 2023Knowing Where to Focus: Event-aware Transformer for Video Groundingcited by 79
  22. 2023Dense Distinct Query for End-to-End Object Detectioncited by 76
  23. 2022DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spottingcited by 74
  24. 2024D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinementcited by 73
  25. 2025RF-DETR: Neural Architecture Search for Real-Time Detection Transformerscited by 70
  26. 2023Sparse4D v3: Advancing End-to-End 3D Detection and Trackingcited by 69
  27. 2023Cross Modal Transformer: Towards Fast and Robust 3D Object Detectioncited by 68
  28. 2025Vision-R1: Evolving Human-Free Alignment in Large Vision-Language Models via Vision-Guided Reinforcement Learningcited by 68
  29. 2024DEIM: DETR with Improved Matching for Fast Convergencecited by 67
  30. 2023SPTS v2: Single-Point Scene Text Spottingcited by 66
  31. 2025Detect Anything via Next Point Predictioncited by 66
  32. 2023A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and Futurecited by 59
  33. 2024TR-DETR: Task-Reciprocal Transformer for Joint Moment Retrieval and Highlight Detectioncited by 59
  34. 2024Multiple Object Tracking as ID Predictioncited by 58
  35. 2023Exploring Predicate Visual Context in Detecting Human-Object Interactionscited by 56
  36. 2024OPUS: Occupancy Prediction Using a Sparse Setcited by 56
  37. 2022AO2-DETR: Arbitrary-Oriented Object Detection Transformercited by 55
  38. 2022RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detectioncited by 54

50 most cited of 569 All 569 (JSON)