mlsanityData to 7 Oct 2026

Sparse R-CNN: End-to-End Object Detection with Learnable Proposals

arXiv 2011.12450 ↗First posted 25 Nov 2020cs.CVcited by 494

Not on the map. Why?

Abstract (arXiv)

We present Sparse R-CNN, a purely sparse method for object detection in images. Existing works on object detection heavily rely on dense object candidates, such as k anchor boxes pre-defined on all grids of image feature map of size H× W. In our method, however, a fixed sparse set of learned object proposals, total length of N, are provided to object recognition head to perform classification and location. By eliminating HWk (up to hundreds of thousands) hand-designed object candidates to N (e.g. 100) learnable proposals, Sparse R-CNN completely avoids all efforts related to object candidates design and many-to-one label assignment. More importantly, final predictions are directly output without non-maximum suppression post-procedure. Sparse R-CNN demonstrates accuracy, run-time and training convergence performance on par with the well-established detector baselines on the challenging COCO dataset, e.g., achieving 45.0 AP in standard 3× training schedule and running at 22 fps using ResNet-50 FPN model. We hope our work could inspire re-thinking the convention of dense prior in object detectors. The code is available at: https://github.com/PeizeSun/SparseR-CNN.

Key facts. Cited by 494 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 62; 2022: 115; 2023: 135; 2024: 102; 2025: 55; 2026: 25.

494 papers.

Sort:

By area:

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  2. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  3. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  4. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,215
  5. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  6. 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 812
  7. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 749
  8. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
  9. 2022DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETRcited by 569
  10. 2022Vision Transformer Adapter for Dense Predictionscited by 564
  11. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 526
  12. 2024YOLOv10: Real-Time End-to-End Object Detectioncited by 508
38 more
  1. 2022TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformerscited by 464
  2. 2022DiffusionDet: Diffusion Model for Object Detectioncited by 354
  3. 2021Focal Self-attention for Local-Global Interactions in Vision Transformerscited by 286
  4. 2022Visual Attention Networkcited by 210
  5. 2021DetCo: Unsupervised Contrastive Learning for Object Detectioncited by 205
  6. 2023Universal Instance Perception as Object Discovery and Retrievalcited by 190
  7. 2022Focal Modulation Networkscited by 186
  8. 2021Dynamic Head: Unifying Object Detection Heads with Attentionscited by 185
  9. 2022Language as Queries for Referring Video Object Segmentationcited by 180
  10. 2022Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusioncited by 161
  11. 2021Instances as Queriescited by 157
  12. 2023SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videoscited by 149
  13. 2022MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectorscited by 148
  14. 2022More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsitycited by 142
  15. 2021CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attentioncited by 139
  16. 2021Visformer: The Vision-friendly Transformercited by 137
  17. 2021Efficient DETR: Improving End-to-End Object Detector with Dense Priorcited by 128
  18. 2021CycleMLP: A MLP-like Architecture for Dense Predictioncited by 126
  19. 2022Vision-Centric BEV Perception: A Surveycited by 126
  20. 2023Transformer-Based Visual Segmentation: A Surveycited by 124
  21. 2021MPViT: Multi-Path Vision Transformer for Dense Predictioncited by 122
  22. 2022Towards Large-Scale Small Object Detection: Survey and Benchmarkscited by 119
  23. 2021A Survey of Visual Transformerscited by 117
  24. 2021Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformercited by 115
  25. 2022Global Tracking Transformerscited by 110
  26. 2021Beyond Self-attention: External Attention using Two Linear Layers for Visual Taskscited by 109
  27. 2021Efficient Training of Visual Transformers with Small Datasetscited by 107
  28. 2021Oriented RepPoints for Aerial Object Detectioncited by 102
  29. 2021SGTR: End-to-end Scene Graph Generation with Transformercited by 102
  30. 2021AS-MLP: An Axial Shifted MLP Architecture for Visioncited by 101
  31. 2022CODA: A Real-World Road Corner Case Dataset for Object Detection in Autonomous Drivingcited by 100
  32. 2021SeqFormer: Sequential Transformer for Video Instance Segmentationcited by 98
  33. 2022Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignmentcited by 96
  34. 2022Learning Object-Language Alignments for Open-Vocabulary Object Detectioncited by 95
  35. 2022Towards Grand Unification of Object Trackingcited by 93
  36. 2021CAT: Cross Attention in Vision Transformercited by 92
  37. 2022MonoDETR: Depth-guided Transformer for Monocular 3D Object Detectioncited by 85
  38. 2022CLRNet: Cross Layer Refinement Network for Lane Detectioncited by 82

50 most cited of 494 All 494 (JSON)