mlsanityData to 7 Oct 2026

Efficient DETR: Improving End-to-End Object Detector with Dense Prior

arXiv 2104.01318 ↗First posted 3 Apr 2021cs.CVcited by 128

Not on the map. Why?

Abstract (arXiv)

The recently proposed end-to-end transformer detectors, such as DETR and Deformable DETR, have a cascade structure of stacking 6 decoder layers to update object queries iteratively, without which their performance degrades seriously. In this paper, we investigate that the random initialization of object containers, which include object queries and reference points, is mainly responsible for the requirement of multiple iterations. Based on our findings, we propose Efficient DETR, a simple and efficient pipeline for end-to-end object detection. By taking advantage of both dense detection and sparse set detection, Efficient DETR leverages dense prior to initialize the object containers and brings the gap of the 1-decoder structure and 6-decoder structure. Experiments conducted on MS COCO show that our method, with only 3 encoder layers and 1 decoder layer, achieves competitive performance with state-of-the-art object detection methods. Efficient DETR is also robust in crowded scenes. It outperforms modern detectors on CrowdHuman dataset by a large margin.

Key facts. Cited by 128 papers in the map (data through 7 Oct 2026). Builds on 39 of its 44 references that are in the map. First posted on arXiv 3 Apr 2021.

Builds on

39 of 44 references.

References · 39

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  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. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  12. 2015Fast R-CNNcited by 2,930
27 more
  1. 2018YOLOv3: An Incremental Improvementcited by 2,652
  2. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  3. 2017Deformable Convolutional Networkscited by 1,481
  4. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  5. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
  6. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  7. 2019Objects as Pointscited by 1,172
  8. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  9. 2018Deformable ConvNets v2: More Deformable, Better Resultscited by 666
  10. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  11. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 539
  12. 2020Sparse R-CNN: End-to-End Object Detection with Learnable Proposalscited by 494
  13. 2016R-FCN: Object Detection via Region-based Fully Convolutional Networkscited by 414
  14. 2016Dynamic Filter Networkscited by 318
  15. 2018CrowdHuman: A Benchmark for Detecting Human in a Crowdcited by 283
  16. 2021Fast Convergence of DETR with Spatially Modulated Co-Attentioncited by 176
  17. 2020Rethinking Transformer-based Set Prediction for Object Detectioncited by 156
  18. 2020Probabilistic Anchor Assignment with IoU Prediction for Object Detectioncited by 150
  19. 2015End-to-end people detection in crowded scenescited by 140
  20. 2017Single-Shot Refinement Neural Network for Object Detectioncited by 129
  21. 2020AutoAssign: Differentiable Label Assignment for Dense Object Detectioncited by 100
  22. 2019FreeAnchor: Learning to Match Anchors for Visual Object Detectioncited by 90
  23. 2020End-to-End Object Detection with Fully Convolutional Networkcited by 70
  24. 2015DenseBox: Unifying Landmark Localization with End to End Object Detectioncited by 58
  25. 2019Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolutioncited by 57
  26. 2020BorderDet: Border Feature for Dense Object Detectioncited by 39
  27. 2019Learning from Noisy Anchors for One-stage Object Detectioncited by 35

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 33; 2023: 35; 2024: 26; 2025: 22; 2026: 6.

128 papers.

Sort:

By area:

  1. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,306
  2. 2022DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETRcited by 569
  3. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 526
  4. 2022DN-DETR: Accelerate DETR Training by Introducing Query DeNoisingcited by 486
  5. 2022TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformerscited by 464
  6. 2023Scaling Open-Vocabulary Object Detectioncited by 335
  7. 2022Simple Open-Vocabulary Object Detection with Vision Transformerscited by 303
  8. 2022DETRs with Hybrid Matchingcited by 149
  9. 2023Transformer-Based Visual Segmentation: A Surveycited by 124
  10. 2021A Survey of Visual Transformerscited by 117
  11. 2024Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyondcited by 111
  12. 2021SGTR: End-to-end Scene Graph Generation with Transformercited by 102
38 more
  1. 2021Sparse DETR: Efficient End-to-End Object Detection with Learnable Sparsitycited by 98
  2. 2022Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignmentcited by 96
  3. 2022RelTR: Relation Transformer for Scene Graph Generationcited by 95
  4. 2022MonoDETR: Depth-guided Transformer for Monocular 3D Object Detectioncited by 85
  5. 2023Knowing Where to Focus: Event-aware Transformer for Video Groundingcited by 79
  6. 2022AdaMixer: A Fast-Converging Query-Based Object Detectorcited by 78
  7. 2023Dense Distinct Query for End-to-End Object Detectioncited by 76
  8. 2024DEIM: DETR with Improved Matching for Fast Convergencecited by 67
  9. 2021Sub-word Level Lip Reading With Visual Attentioncited by 60
  10. 2023FocalFormer3D : Focusing on Hard Instance for 3D Object Detectioncited by 58
  11. 2024IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detectioncited by 57
  12. 2023Detection Transformer with Stable Matchingcited by 43
  13. 2021Audio-Visual Synchronisation in the wildcited by 39
  14. 2023Object as Query: Lifting any 2D Object Detector to 3D Detectioncited by 38
  15. 2023Less is More: Focus Attention for Efficient DETRcited by 38
  16. 2023Lite DETR : An Interleaved Multi-Scale Encoder for Efficient DETRcited by 36
  17. 2024MS-DETR: Efficient DETR Training with Mixed Supervisioncited by 34
  18. 2022NMS Strikes Backcited by 33
  19. 2022Transformers in 3D Point Clouds: A Surveycited by 31
  20. 2024Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinementcited by 30
  21. 2024DAMSDet: Dynamic Adaptive Multispectral Detection Transformer with Competitive Query Selection and Adaptive Feature Fusioncited by 28
  22. 2022TSRFormer: Table Structure Recognition with Transformerscited by 27
  23. 2023Semi-DETR: Semi-Supervised Object Detection with Detection Transformerscited by 27
  24. 2024SparseLIF: High-Performance Sparse LiDAR-Camera Fusion for 3D Object Detectioncited by 25
  25. 2024Object Detection using Event Camera: A MoE Heat Conduction based Detector and A New Benchmark Datasetcited by 25
  26. 2023Localizing Moments in Long Video Via Multimodal Guidancecited by 23
  27. 2023Object Detection with Transformers: A Reviewcited by 22
  28. 2021Recurrent Glimpse-based Decoder for Detection with Transformercited by 21
  29. 2022DETR4D: Direct Multi-View 3D Object Detection with Sparse Attentioncited by 21
  30. 2023OmniTracker: Unifying Object Tracking by Tracking-with-Detectioncited by 19
  31. 2023Cascade-DETR: Delving into High-Quality Universal Object Detectioncited by 19
  32. 2022Dynamic Focus-aware Positional Queries for Semantic Segmentationcited by 16
  33. 20223DPPE: 3D Point Positional Encoding for Multi-Camera 3D Object Detection Transformerscited by 15
  34. 2022FusionRCNN: LiDAR-Camera Fusion for Two-stage 3D Object Detectioncited by 14
  35. 2023Transformer-Based Sensor Fusion for Autonomous Driving: A Surveycited by 14
  36. 2023Video OWL-ViT: Temporally-consistent open-world localization in videocited by 13
  37. 2022D^2ETR: Decoder-Only DETR with Computationally Efficient Cross-Scale Attentioncited by 12
  38. 2022KD-DETR: Knowledge Distillation for Detection Transformer with Consistent Distillation Points Samplingcited by 12

50 most cited of 128 All 128 (JSON)