mlsanityData to 7 Oct 2026

Improving Crowded Object Detection via Copy-Paste

arXiv 2211.12110 ↗First posted 22 Nov 2022cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Crowdedness caused by overlapping among similar objects is a ubiquitous challenge in the field of 2D visual object detection. In this paper, we first underline two main effects of the crowdedness issue: 1) IoU-confidence correlation disturbances (ICD) and 2) confused de-duplication (CDD). Then we explore a pathway of cracking these nuts from the perspective of data augmentation. Primarily, a particular copy-paste scheme is proposed towards making crowded scenes. Based on this operation, we first design a "consensus learning" method to further resist the ICD problem and then find out the pasting process naturally reveals a pseudo "depth" of object in the scene, which can be potentially used for alleviating CDD dilemma. Both methods are derived from magical using of the copy-pasting without extra cost for hand-labeling. Experiments show that our approach can easily improve the state-of-the-art detector in typical crowded detection task by more than 2% without any bells and whistles. Moreover, this work can outperform existing data augmentation strategies in crowded scenario.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 38 of its 47 references that are in the map. First posted on arXiv 22 Nov 2022.

Builds on

38 of 47 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2017Mask R-CNNcited by 7,259
  6. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  7. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  8. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  9. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  10. 2014Going Deeper with Convolutionscited by 4,231
  11. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  12. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
26 more
  1. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  2. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
  3. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  4. 2018AutoAugment: Learning Augmentation Policies from Datacited by 728
  5. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595
  6. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
  7. 2020Sparse R-CNN: End-to-End Object Detection with Learnable Proposalscited by 494
  8. 2018Deep Learning for Generic Object Detection: A Surveycited by 392
  9. 2018CrowdHuman: A Benchmark for Detecting Human in a Crowdcited by 283
  10. 2019Fast AutoAugmentcited by 243
  11. 2017Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detectioncited by 209
  12. 2017CityPersons: A Diverse Dataset for Pedestrian Detectioncited by 171
  13. 2019Learning Data Augmentation Strategies for Object Detectioncited by 139
  14. 2018Modeling Visual Context is Key to Augmenting Object Detection Datasetscited by 106
  15. 2019InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pastingcited by 95
  16. 2019Adaptive NMS: Refining Pedestrian Detection in a Crowdcited by 66
  17. 2017Repulsion Loss: Detecting Pedestrians in a Crowdcited by 62
  18. 2020Detection in Crowded Scenes: One Proposal, Multiple Predictionscited by 59
  19. 2018Occlusion-aware R-CNN: Detecting Pedestrians in a Crowdcited by 58
  20. 2018Learning to Segment via Cut-and-Pastecited by 42
  21. 2022Progressive End-to-End Object Detection in Crowded Scenescited by 31
  22. 2021Scale-aware Automatic Augmentation for Object Detectioncited by 23
  23. 2020Dynamic Scale Training for Object Detectioncited by 15
  24. 2021Variational Pedestrian Detectioncited by 10
  25. 2020Visibility Guided NMS: Efficient Boosting of Amodal Object Detection in Crowded Traffic Scenescited by 8
  26. 2020Visible Feature Guidance for Crowd Pedestrian Detectioncited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 1; 2025: 1; 2026: 2.

6 papers.

  1. 2023Integrating Language-Derived Appearance Elements with Visual Cues in Pedestrian Detectioncited by 10
  2. 2023CogCartoon: Towards Practical Story Visualizationcited by 8
  3. 2024Data Augmentation in Human-Centric Visioncited by 2
  4. 2025SDVPT: Semantic-Driven Visual Prompt Tuning for Open-World Object Countingcited by 2
  5. 2026OV-DEIM: Real-time DETR-Style Open-Vocabulary Object Detection with GridSynthetic Augmentationcited by 2
  6. 2026A Probabilistic Framework for Improving Dense Object Detection in Underwater Image Data via Annealing-Based Data Augmentationcited by 0