mlsanityData to 7 Oct 2026

Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation

arXiv 2012.07177 ↗First posted 13 Dec 2020cs.CVcited by 595

Not on the map. Why?

Cited by 31 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Building instance segmentation models that are data-efficient and can handle rare object categories is an important challenge in computer vision. Leveraging data augmentations is a promising direction towards addressing this challenge. Here, we perform a systematic study of the Copy-Paste augmentation ([13, 12]) for instance segmentation where we randomly paste objects onto an image. Prior studies on Copy-Paste relied on modeling the surrounding visual context for pasting the objects. However, we find that the simple mechanism of pasting objects randomly is good enough and can provide solid gains on top of strong baselines. Furthermore, we show Copy-Paste is additive with semi-supervised methods that leverage extra data through pseudo labeling (e.g. self-training). On COCO instance segmentation, we achieve 49.1 mask AP and 57.3 box AP, an improvement of +0.6 mask AP and +1.5 box AP over the previous state-of-the-art. We further demonstrate that Copy-Paste can lead to significant improvements on the LVIS benchmark. Our baseline model outperforms the LVIS 2020 Challenge winning entry by +3.6 mask AP on rare categories.

Key facts. Cited by 595 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 71; 2022: 124; 2023: 153; 2024: 104; 2025: 80; 2026: 63.

595 papers.

Sort:

By area:

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  2. 2023Segment Anythingcited by 8,158
  3. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  4. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  5. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,215
  6. 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,147
  7. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,064
  8. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,051
  9. 2022Exploring Plain Vision Transformer Backbones for Object Detectioncited by 723
  10. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 703
  11. 2022EVA: Exploring the Limits of Masked Visual Representation Learning at Scalecited by 685
  12. 2022Detecting Twenty-thousand Classes using Image-level Supervisioncited by 613
38 more
  1. 2021RegionCLIP: Region-based Language-Image Pretrainingcited by 612
  2. 2022Vision Transformer Adapter for Dense Predictionscited by 564
  3. 2021MViTv2: Improved Multiscale Vision Transformers for Classification and Detectioncited by 516
  4. 2024YOLOv10: Real-Time End-to-End Object Detectioncited by 508
  5. 2022InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutionscited by 479
  6. 2021Scaling Open-Vocabulary Image Segmentation with Image-Level Labelscited by 471
  7. 2021A Survey of Data Augmentation Approaches for NLPcited by 408
  8. 2023EVA-02: A Visual Representation for Neon Genesiscited by 377
  9. 2023Segment Anything in High Qualitycited by 373
  10. 2023Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Modelscited by 371
  11. 2021Bottleneck Transformers for Visual Recognitioncited by 364
  12. 2021High-Performance Large-Scale Image Recognition Without Normalizationcited by 359
  13. 2021Pix2seq: A Language Modeling Framework for Object Detectioncited by 345
  14. 2022Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentationcited by 341
  15. 2023Scaling Open-Vocabulary Object Detectioncited by 335
  16. 2022OneFormer: One Transformer to Rule Universal Image Segmentationcited by 327
  17. 2022Simple Open-Vocabulary Object Detection with Vision Transformerscited by 303
  18. 2022MultiMAE: Multi-modal Multi-task Masked Autoencoderscited by 287
  19. 2023Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistlescited by 287
  20. 2021Focal Self-attention for Local-Global Interactions in Vision Transformerscited by 286
  21. 2022DETRs with Collaborative Hybrid Assignments Trainingcited by 273
  22. 2021Knowledge distillation: A good teacher is patient and consistentcited by 255
  23. 2022RTMDet: An Empirical Study of Designing Real-Time Object Detectorscited by 192
  24. 2023Cut and Learn for Unsupervised Object Detection and Instance Segmentationcited by 186
  25. 2021Dynamic Head: Unifying Object Detection Heads with Attentionscited by 185
  26. 2023Putting the Object Back into Video Object Segmentationcited by 182
  27. 2023Towards Open Vocabulary Learning: A Surveycited by 165
  28. 2021Occluded Video Instance Segmentation: A Benchmarkcited by 154
  29. 2023mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Videocited by 154
  30. 2022DETRs with Hybrid Matchingcited by 149
  31. 2022F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Modelscited by 149
  32. 2023A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAScited by 149
  33. 2023PACO: Parts and Attributes of Common Objectscited by 146
  34. 2022Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detectioncited by 145
  35. 2022SeqTR: A Simple yet Universal Network for Visual Groundingcited by 138
  36. 2021Benchmarking Detection Transfer Learning with Vision Transformerscited by 130
  37. 2021Mix3D: Out-of-Context Data Augmentation for 3D Scenescited by 126
  38. 2023Transformer-Based Visual Segmentation: A Surveycited by 124

50 most cited of 595 All 595 (JSON)