mlsanityData to 7 Oct 2026

Dynamic Head: Unifying Object Detection Heads with Attentions

arXiv 2106.08322 ↗First posted 15 Jun 2021cs.CVcited by 185

Not on the map. Why?

Abstract (arXiv)

The complex nature of combining localization and classification in object detection has resulted in the flourished development of methods. Previous works tried to improve the performance in various object detection heads but failed to present a unified view. In this paper, we present a novel dynamic head framework to unify object detection heads with attentions. By coherently combining multiple self-attention mechanisms between feature levels for scale-awareness, among spatial locations for spatial-awareness, and within output channels for task-awareness, the proposed approach significantly improves the representation ability of object detection heads without any computational overhead. Further experiments demonstrate that the effectiveness and efficiency of the proposed dynamic head on the COCO benchmark. With a standard ResNeXt-101-DCN backbone, we largely improve the performance over popular object detectors and achieve a new state-of-the-art at 54.0 AP. Furthermore, with latest transformer backbone and extra data, we can push current best COCO result to a new record at 60.6 AP. The code will be released at https://github.com/microsoft/DynamicHead.

Key facts. Cited by 185 papers in the map (data through 7 Oct 2026). Builds on 38 of its 48 references that are in the map. First posted on arXiv 15 Jun 2021.

Builds on

38 of 48 references.

References · 38

  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. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  6. 2020End-to-End Object Detection with Transformerscited by 7,384
  7. 2017Mask R-CNNcited by 7,259
  8. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  9. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  10. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  11. 2015Fast R-CNNcited by 2,930
  12. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
26 more
  1. 2017Non-local Neural Networkscited by 2,290
  2. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  3. 2017Deformable Convolutional Networkscited by 1,481
  4. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  5. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,128
  6. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
  7. 2018Path Aggregation Network for Instance Segmentationcited by 796
  8. 2017Focal Loss for Dense Object Detectioncited by 749
  9. 2018Deformable ConvNets v2: More Deformable, Better Resultscited by 666
  10. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  11. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595
  12. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 539
  13. 2019Object Detection in 20 Years: A Surveycited by 528
  14. 2020Sparse R-CNN: End-to-End Object Detection with Learnable Proposalscited by 494
  15. 2016R-FCN: Object Detection via Region-based Fully Convolutional Networkscited by 414
  16. 2020Rethinking Pre-training and Self-trainingcited by 352
  17. 2019RepPoints: Point Set Representation for Object Detectioncited by 264
  18. 2019Libra R-CNN: Towards Balanced Learning for Object Detectioncited by 255
  19. 2021Probabilistic two-stage detectioncited by 130
  20. 2017An Analysis of Scale Invariance in Object Detection - SNIPcited by 119
  21. 2018SNIPER: Efficient Multi-Scale Trainingcited by 87
  22. 2019SpineNet: Learning Scale-Permuted Backbone for Recognition and Localizationcited by 50
  23. 2020RepPoints V2: Verification Meets Regression for Object Detectioncited by 40
  24. 2020BorderDet: Border Feature for Dense Object Detectioncited by 39
  25. 2020RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decodercited by 31
  26. 2020Scale-Equalizing Pyramid Convolution for Object Detectioncited by 25

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 51; 2023: 56; 2024: 31; 2025: 18; 2026: 16.

185 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. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,215
  4. 2021Grounded Language-Image Pre-trainingcited by 1,147
  5. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  6. 2021Florence: A New Foundation Model for Computer Visioncited by 802
  7. 2022Exploring Plain Vision Transformer Backbones for Object Detectioncited by 723
  8. 2022EVA: Exploring the Limits of Masked Visual Representation Learning at Scalecited by 685
  9. 2022Vision Transformer Adapter for Dense Predictionscited by 564
  10. 2022Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Taskscited by 510
  11. 2022InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutionscited by 479
  12. 2023Perception Test: A Diagnostic Benchmark for Multimodal Video Modelscited by 310
38 more
  1. 2021Focal Self-attention for Local-Global Interactions in Vision Transformerscited by 286
  2. 2022GLIPv2: Unifying Localization and Vision-Language Understandingcited by 275
  3. 2023Universal Instance Perception as Object Discovery and Retrievalcited by 190
  4. 2022Focal Modulation Networkscited by 186
  5. 2022DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detectioncited by 176
  6. 2022DaViT: Dual Attention Vision Transformerscited by 174
  7. 2022Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNscited by 155
  8. 2022More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsitycited by 142
  9. 2022ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Modelscited by 141
  10. 2022Towards Large-Scale Small Object Detection: Survey and Benchmarkscited by 119
  11. 2022GRiT: A Generative Region-to-text Transformer for Object Understandingcited by 119
  12. 2022Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbonecited by 109
  13. 2023DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignmentcited by 90
  14. 2023V3Det: Vast Vocabulary Visual Detection Datasetcited by 81
  15. 2022AdaMixer: A Fast-Converging Query-Based Object Detectorcited by 78
  16. 2021CBNet: A Composite Backbone Network Architecture for Object Detectioncited by 77
  17. 2023Dense Distinct Query for End-to-End Object Detectioncited by 76
  18. 2023The effectiveness of MAE pre-pretraining for billion-scale pretrainingcited by 68
  19. 2022Medical Image Understanding with Pretrained Vision Language Models: A Comprehensive Studycited by 66
  20. 2025Detect Anything via Next Point Predictioncited by 66
  21. 2023Detecting Everything in the Open World: Towards Universal Object Detectioncited by 62
  22. 2023A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and Futurecited by 59
  23. 2024Rewrite the Starscited by 55
  24. 2022RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detectioncited by 54
  25. 2022X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusioncited by 49
  26. 2024Matching Anything by Segmenting Anythingcited by 49
  27. 2024DetCLIPv3: Towards Versatile Generative Open-vocabulary Object Detectioncited by 48
  28. 2023Multi-modal Queried Object Detection in the Wildcited by 47
  29. 2023RLIPv2: Fast Scaling of Relational Language-Image Pre-trainingcited by 44
  30. 2021Label, Verify, Correct: A Simple Few Shot Object Detection Methodcited by 43
  31. 2023Detection Transformer with Stable Matchingcited by 43
  32. 2023AutoPoster: A Highly Automatic and Content-aware Design System for Advertising Poster Generationcited by 41
  33. 2023Uni3D: A Unified Baseline for Multi-dataset 3D Object Detectioncited by 39
  34. 2023Explore the Power of Synthetic Data on Few-shot Object Detectioncited by 38
  35. 2024Splat-MOVER: Multi-Stage, Open-Vocabulary Robotic Manipulation via Editable Gaussian Splattingcited by 37
  36. 2023DilateFormer: Multi-Scale Dilated Transformer for Visual Recognitioncited by 34
  37. 2022BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-trainingcited by 33
  38. 2022NMS Strikes Backcited by 33

50 most cited of 185 All 185 (JSON)