mlsanityData to 7 Oct 2026

Information-Theoretic Segmentation by Inpainting Error Maximization

arXiv 2012.07287 ↗First posted 14 Dec 2020cs.CVcited by 22

Not on the map. Why?

Abstract (arXiv)

We study image segmentation from an information-theoretic perspective, proposing a novel adversarial method that performs unsupervised segmentation by partitioning images into maximally independent sets. More specifically, we group image pixels into foreground and background, with the goal of minimizing predictability of one set from the other. An easily computed loss drives a greedy search process to maximize inpainting error over these partitions. Our method does not involve training deep networks, is computationally cheap, class-agnostic, and even applicable in isolation to a single unlabeled image. Experiments demonstrate that it achieves a new state-of-the-art in unsupervised segmentation quality, while being substantially faster and more general than competing approaches.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 5; 2022: 7; 2023: 5; 2024: 2; 2025: 3.

22 papers.

Sort:

By area:

  1. 2021Illiterate DALL-E Learns to Composecited by 147
  2. 2022Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videoscited by 139
  3. 2022NeRF-SOS: Any-View Self-supervised Object Segmentation on Complex Scenescited by 71
  4. 2021Unsupervised Foreground Extraction via Deep Region Competitioncited by 26
  5. 2022Unsupervised Multi-View Object Segmentation Using Radiance Field Propagationcited by 22
  6. 2022MOVE: Unsupervised Movable Object Segmentation and Detectioncited by 20
  7. 2021GANSeg: Learning to Segment by Unsupervised Hierarchical Image Generationcited by 19
  8. 2022AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking Keypointscited by 17
  9. 2023Unsupervised Object Localization in the Era of Self-Supervised ViTs: A Surveycited by 16
  10. 2021Contrastive Fine-grained Class Clustering via Generative Adversarial Networkscited by 9
  11. 2021Learning Foreground-Background Segmentation from Improved Layered GANscited by 7
  12. 2022Foreground-Background Separation through Concept Distillation from Generative Image Foundation Modelscited by 5
10 more
  1. 2023SC-VAE: Sparse Coding-based Variational Autoencoder with Learned ISTAcited by 4
  2. 2023SEMPART: Self-supervised Multi-resolution Partitioning of Image Semanticscited by 4
  3. 2025Surface-SOS: Self-Supervised Object Segmentation via Neural Surface Representationcited by 3
  4. 2022ILSGAN: Independent Layer Synthesis for Unsupervised Foreground-Background Segmentationcited by 2
  5. 2023Co-Learning Semantic-aware Unsupervised Segmentation for Pathological Image Registrationcited by 2
  6. 2024Unsupervised Part Discovery via Dual Representation Alignmentcited by 2
  7. 2023Factorized Diffusion Architectures for Unsupervised Image Generation and Segmentationcited by 1
  8. 2024Spectral-Stimulus Information for Self-Supervised Stimulus Encodingcited by 0
  9. 2025Weakly Supervised Object Segmentation by Background Conditional Divergencecited by 0
  10. 2025Dialectics for Artificial Intelligencecited by 0