mlsanityData to 14 Oct 2026

Object Discovery with a Copy-Pasting GAN

arXiv 1905.11369 ↗First posted 27 May 2019cs.CV cs.AI cs.LGcited by 29

Not on the map. Why?

Abstract (arXiv)

We tackle the problem of object discovery, where objects are segmented for a given input image, and the system is trained without using any direct supervision whatsoever. A novel copy-pasting GAN framework is proposed, where the generator learns to discover an object in one image by compositing it into another image such that the discriminator cannot tell that the resulting image is fake. After carefully addressing subtle issues, such as preventing the generator from `cheating', this game results in the generator learning to select objects, as copy-pasting objects is most likely to fool the discriminator. The system is shown to work well on four very different datasets, including large object appearance variations in challenging cluttered backgrounds.

Key facts. Cited by 29 papers in the map (data through 14 Oct 2026). First posted on arXiv 27 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 10; 2022: 6; 2023: 9; 2024: 1; 2025: 2; 2026: 1.

29 papers.

Sort:

  1. 2022Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localizationcited by 150
  2. 2021GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinementcited by 109
  3. 2021Context Decoupling Augmentation for Weakly Supervised Semantic Segmentationcited by 69
  4. 2021SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editingcited by 58
  5. 2022Unsupervised Salient Object Detection with Spectral Cluster Votingcited by 56
  6. 2021Unsupervised Layered Image Decomposition into Object Prototypescited by 50
  7. 2021Finding an Unsupervised Image Segmenter in Each of Your Deep Generative Modelscited by 44
  8. 2021Object-aware Contrastive Learning for Debiased Scene Representationcited by 35
  9. 2021Compositional Transformers for Scene Generationcited by 24
  10. 2022Decoder Denoising Pretraining for Semantic Segmentationcited by 20
  11. 2022MOVE: Unsupervised Movable Object Segmentation and Detectioncited by 20
  12. 2022AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking Keypointscited by 17
17 more
  1. 2022Promising or Elusive? Unsupervised Object Segmentation from Real-world Single Imagescited by 16
  2. 2023Unsupervised Object Localization in the Era of Self-Supervised ViTs: A Surveycited by 16
  3. 2021The Pursuit of Knowledge: Discovering and Localizing Novel Categories using Dual Memorycited by 13
  4. 2023Semantic 3D-aware Portrait Synthesis and Manipulation Based on Compositional Neural Radiance Fieldcited by 10
  5. 2025UCOD-DPL: Unsupervised Camouflaged Object Detection via Dynamic Pseudo-label Learningcited by 10
  6. 2023LOCATE: Self-supervised Object Discovery via Flow-guided Graph-cut and Bootstrapped Self-trainingcited by 8
  7. 2021Learning Foreground-Background Segmentation from Improved Layered GANscited by 7
  8. 2023Understanding Self-Supervised Features for Learning Unsupervised Instance Segmentationcited by 7
  9. 2021Unsupervised Image Decomposition with Phase-Correlation Networkscited by 6
  10. 2023Learning to Count without Annotationscited by 5
  11. 2023Learning Neural Eigenfunctions for Unsupervised Semantic Segmentationcited by 4
  12. 2023Benchmarking and Analysis of Unsupervised Object Segmentation from Real-world Single Imagescited by 4
  13. 2024Unsupervised Object Discovery: A Comprehensive Survey and Unified Taxonomycited by 4
  14. 2023Self-Supervised Instance Segmentation by Graspingcited by 3
  15. 2023SS-CPGAN: Self-Supervised Cut-and-Pasting Generative Adversarial Network for Object Segmentationcited by 1
  16. 2025SketchYourSeg: Mask-Free Subjective Image Segmentation via Freehand Sketchescited by 1
  17. 2026ORGAN: Object-Centric Representation Learning using Cycle Consistent Generative Adversarial Networkscited by 0