mlsanityData to 7 Oct 2026

DeePaste -- Inpainting for Pasting

arXiv 2112.10600 ↗First posted 20 Dec 2021cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

One of the challenges of supervised learning training is the need to procure an substantial amount of tagged data. A well-known method of solving this problem is to use synthetic data in a copy-paste fashion, so that we cut objects and paste them onto relevant backgrounds. Pasting the objects naively results in artifacts that cause models to give poor results on real data. We present a new method for cleanly pasting objects on different backgrounds so that the dataset created gives competitive performance on real data. The main emphasis is on the treatment of the border of the pasted object using inpainting. We show state-of-the-art results both on instance detection and foreground segmentation

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 27 of its 53 references that are in the map. First posted on arXiv 20 Dec 2021.

Builds on

27 of 53 references.

References · 27

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2018YOLOv3: An Incremental Improvementcited by 2,652
  5. 2020Image Segmentation Using Deep Learning: A Surveycited by 659
  6. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595
  7. 2018Free-Form Image Inpainting with Gated Convolutioncited by 594
  8. 2018Generative Image Inpainting with Contextual Attentioncited by 578
  9. 2017Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detectioncited by 209
  10. 2017Deep Image Mattingcited by 150
  11. 2019DoveNet: Deep Image Harmonization via Domain Verificationcited by 134
  12. 2017Deep Image Harmonizationcited by 120
15 more
  1. 2016High-Resolution Image Inpainting using Multi-Scale Neural Patch Synthesiscited by 89
  2. 2017Generative Face Completioncited by 79
  3. 2017GP-GAN: Towards Realistic High-Resolution Image Blendingcited by 64
  4. 2019Deep Image Blendingcited by 62
  5. 2016Synthesizing Training Images for Boosting Human 3D Pose Estimationcited by 52
  6. 2019Learning to Generate Synthetic Data via Compositingcited by 52
  7. 2017On Pre-Trained Image Features and Synthetic Images for Deep Learningcited by 51
  8. 2018Learning Multi-scale Features for Foreground Segmentationcited by 27
  9. 2016Multiview RGB-D Dataset for Object Instance Detectioncited by 26
  10. 2014On Rendering Synthetic Images for Training an Object Detectorcited by 18
  11. 2021BSUV-Net 2.0: Spatio-Temporal Data Augmentations for Video-Agnostic Supervised Background Subtractioncited by 15
  12. 2015Towards Benchmarking Scene Background Initializationcited by 13
  13. 2017Object Detection Using Deep CNNs Trained on Synthetic Imagescited by 9
  14. 2017Pixel Objectnesscited by 2
  15. 2020Using a Supervised Method without supervision for foreground segmentationcited by 1

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025ForAug: Mitigating Biases in Image Classification via Controlled Image Compositionscited by 2