mlsanityData to 7 Oct 2026

MOVE: Unsupervised Movable Object Segmentation and Detection

arXiv 2210.07920 ↗First posted 14 Oct 2022cs.CV cs.AI cs.LGcited by 20

Not on the map. Why?

Abstract (arXiv)

We introduce MOVE, a novel method to segment objects without any form of supervision. MOVE exploits the fact that foreground objects can be shifted locally relative to their initial position and result in realistic (undistorted) new images. This property allows us to train a segmentation model on a dataset of images without annotation and to achieve state of the art (SotA) performance on several evaluation datasets for unsupervised salient object detection and segmentation. In unsupervised single object discovery, MOVE gives an average CorLoc improvement of 7.2% over the SotA, and in unsupervised class-agnostic object detection it gives a relative AP improvement of 53% on average. Our approach is built on top of self-supervised features (e.g. from DINO or MAE), an inpainting network (based on the Masked AutoEncoder) and adversarial training.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 58 of its 96 references that are in the map. First posted on arXiv 14 Oct 2022.

Builds on

58 of 96 references.

References · 58

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  6. 2020End-to-End Object Detection with Transformerscited by 7,384
  7. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  8. 2017Mask R-CNNcited by 7,259
  9. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  10. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  11. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  12. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,610
38 more
  1. 2019Contrastive Multiview Codingcited by 1,297
  2. 2019Objects as Pointscited by 1,172
  3. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,148
  4. 2020Dense Contrastive Learning for Self-Supervised Visual Pre-Trainingcited by 512
  5. 2018Invariant Information Clustering for Unsupervised Image Classification and Segmentationcited by 454
  6. 2019MONet: Unsupervised Scene Decomposition and Representationcited by 388
  7. 2021Deep ViT Features as Dense Visual Descriptorscited by 327
  8. 2015DeepDriving: Learning Affordance for Direct Perception in Autonomous Drivingcited by 229
  9. 2021Localizing Objects with Self-Supervised Transformers and no Labelscited by 227
  10. 2016Simple Does It: Weakly Supervised Instance and Semantic Segmentationcited by 226
  11. 2016Attend, Infer, Repeat: Fast Scene Understanding with Generative Modelscited by 209
  12. 2021Projected GANs Converge Fastercited by 204
  13. 2015Visual Saliency Based on Multiscale Deep Featurescited by 185
  14. 2022Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cutcited by 166
  15. 2022Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localizationcited by 150
  16. 2022FreeSOLO: Learning to Segment Objects without Annotationscited by 102
  17. 2022Self-Supervised Learning of Object Parts for Semantic Segmentationcited by 90
  18. 2015The Fast Bilateral Solvercited by 86
  19. 2021DETReg: Unsupervised Pretraining with Region Priors for Object Detectioncited by 76
  20. 2019Unsupervised Object Segmentation by Redrawingcited by 74
  21. 2019Unsupervised Moving Object Detection via Contextual Information Separationcited by 72
  22. 2015Unsupervised Object Discovery and Localization in the Wild: Part-based Matching with Bottom-up Region Proposalscited by 69
  23. 2020Toward unsupervised, multi-object discovery in large-scale image collectionscited by 65
  24. 2017Learning to Segment Every Thingcited by 64
  25. 2020Agriculture-Vision: A Large Aerial Image Database for Agricultural Pattern Analysiscited by 61
  26. 2020Autoregressive Unsupervised Image Segmentationcited by 60
  27. 2017W-Net: A Deep Model for Fully Unsupervised Image Segmentationcited by 57
  28. 2019Emergence of Object Segmentation in Perturbed Generative Modelscited by 57
  29. 2022Unsupervised Salient Object Detection with Spectral Cluster Votingcited by 56
  30. 2021Large-Scale Unsupervised Object Discoverycited by 54
  31. 2020Object Segmentation Without Labels with Large-Scale Generative Modelscited by 52
  32. 2018Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspectivecited by 50
  33. 2021Finding an Unsupervised Image Segmenter in Each of Your Deep Generative Modelscited by 44
  34. 2022Towards Open-Set Object Detection and Discoverycited by 44
  35. 2018Learning to Segment via Cut-and-Pastecited by 42
  36. 2019Unsupervised Image Matching and Object Discovery as Optimizationcited by 42
  37. 2021TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentationcited by 38
  38. 2017LR-GAN: Layered Recursive Generative Adversarial Networks for Image Generationcited by 36

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 12; 2024: 3; 2025: 4; 2026: 1.

20 papers.

Sort:

By area:

  1. 2023Diffusion Models for Open-Vocabulary Segmentationcited by 63
  2. 2023CLIP-DIY: CLIP Dense Inference Yields Open-Vocabulary Semantic Segmentation For-Freecited by 39
  3. 2023u-LLaVA: Unifying Multi-Modal Tasks via Large Language Modelcited by 24
  4. 2025Does Object Binding Naturally Emerge in Large Pretrained Vision Transformers?cited by 19
  5. 2023Unsupervised Object Localization in the Era of Self-Supervised ViTs: A Surveycited by 16
  6. 2023Betrayed by Attention: A Simple yet Effective Approach for Self-supervised Video Object Segmentationcited by 10
  7. 2023Understanding Self-Supervised Features for Learning Unsupervised Instance Segmentationcited by 7
  8. 2025Instance-Level Moving Object Segmentation from a Single Image with Eventscited by 6
  9. 2023SEMPART: Self-supervised Multi-resolution Partitioning of Image Semanticscited by 4
  10. 2023Aerial Image Object Detection With Vision Transformer Detector (ViTDet)cited by 3
  11. 2023Box-based Refinement for Weakly Supervised and Unsupervised Localization Taskscited by 3
  12. 2023Towards End-to-End Unsupervised Saliency Detection with Self-Supervised Top-Down Contextcited by 2
8 more
  1. 2025FlowCut: Unsupervised Video Instance Segmentation via Temporal Mask Matchingcited by 2
  2. 2023A Lightweight Clustering Framework for Unsupervised Semantic Segmentationcited by 1
  3. 2024Monocular Per-Object Distance Estimation with Masked Object Modelingcited by 1
  4. 2023Divided Attention: Unsupervised Multi-Object Discovery with Contextually Separated Slotscited by 0
  5. 2024Rethinking Saliency-Guided Weakly-Supervised Semantic Segmentationcited by 0
  6. 2024Joint-Embedding Predictive Architecture for Self-Supervised Learning of Mask Classification Architecturecited by 0
  7. 2025Object-Centric Cropping for Visual Few-Shot Classificationcited by 0
  8. 2026Self-supervised Automatic Mattingcited by 0