mlsanityData to 7 Oct 2026

Bridging the Gap to Real-World Object-Centric Learning

arXiv 2209.14860 ↗First posted 29 Sep 2022cs.CV cs.LGcited by 219

Not on the map. Why?

Abstract (arXiv)

Humans naturally decompose their environment into entities at the appropriate level of abstraction to act in the world. Allowing machine learning algorithms to derive this decomposition in an unsupervised way has become an important line of research. However, current methods are restricted to simulated data or require additional information in the form of motion or depth in order to successfully discover objects. In this work, we overcome this limitation by showing that reconstructing features from models trained in a self-supervised manner is a sufficient training signal for object-centric representations to arise in a fully unsupervised way. Our approach, DINOSAUR, significantly out-performs existing image-based object-centric learning models on simulated data and is the first unsupervised object-centric model that scales to real-world datasets such as COCO and PASCAL VOC. DINOSAUR is conceptually simple and shows competitive performance compared to more involved pipelines from the computer vision literature.

Key facts. Cited by 219 papers in the map (data through 7 Oct 2026). Builds on 73 of its 99 references that are in the map. First posted on arXiv 29 Sep 2022.

Builds on

73 of 99 references.

References · 73

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  6. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  7. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  8. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  9. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  10. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  11. 2017Neural Discrete Representation Learningcited by 4,650
  12. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
38 more
  1. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  2. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,610
  3. 2020On Layer Normalization in the Transformer Architecturecited by 906
  4. 2020Object-Centric Learning with Slot Attentioncited by 865
  5. 2016COCO-Stuff: Thing and Stuff Classes in Contextcited by 858
  6. 2022A Generalist Agentcited by 802
  7. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 784
  8. 2021Perceiver IO: A General Architecture for Structured Inputs & Outputscited by 616
  9. 2022GroupViT: Semantic Segmentation Emerges from Text Supervisioncited by 529
  10. 2018Invariant Information Clustering for Unsupervised Image Classification and Segmentationcited by 454
  11. 2019MONet: Unsupervised Scene Decomposition and Representationcited by 388
  12. 2022Kubric: A scalable dataset generatorcited by 373
  13. 2019Multi-Object Representation Learning with Iterative Variational Inferencecited by 359
  14. 2021Deep ViT Features as Dense Visual Descriptorscited by 327
  15. 2022Masked Siamese Networks for Label-Efficient Learningcited by 301
  16. 2021Conditional Object-Centric Learning from Videocited by 247
  17. 2022Unsupervised Semantic Segmentation by Distilling Feature Correspondencescited by 241
  18. 2020On the Binding Problem in Artificial Neural Networkscited by 230
  19. 2019GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representationscited by 227
  20. 2021Localizing Objects with Self-Supervised Transformers and no Labelscited by 227
  21. 2016Generating Images with Perceptual Similarity Metrics based on Deep Networkscited by 221
  22. 2019Recurrent Independent Mechanismscited by 219
  23. 2016Attend, Infer, Repeat: Fast Scene Understanding with Generative Modelscited by 209
  24. 2021Towards Causal Representation Learningcited by 207
  25. 2020SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decompositioncited by 190
  26. 2021Unsupervised Semantic Segmentation by Contrasting Object Mask Proposalscited by 190
  27. 2022Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cutcited by 166
  28. 2022SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videoscited by 165
  29. 2021PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clusteringcited by 163
  30. 2022Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localizationcited by 150
  31. 2021Illiterate DALL-E Learns to Composecited by 147
  32. 2022Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videoscited by 139
  33. 2018Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objectscited by 128
  34. 2017Augmented Reality Meets Computer Vision : Efficient Data Generation for Urban Driving Scenescited by 122
  35. 2019Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEscited by 116
  36. 2019Entity Abstraction in Visual Model-Based Reinforcement Learningcited by 110
  37. 2021GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinementcited by 109
  38. 2019SCALOR: Generative World Models with Scalable Object Representationscited by 108

50 most cited of 73 All 73 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 46; 2024: 57; 2025: 53; 2026: 60.

219 papers.

Sort:

By area:

  1. 2022Disentangled Representation Learningcited by 111
  2. 2023Object-Centric Slot Diffusioncited by 90
  3. 2023SlotDiffusion: Object-Centric Generative Modeling with Diffusion Modelscited by 85
  4. 2023Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similaritiescited by 78
  5. 2023Multi-View Causal Representation Learning with Partial Observabilitycited by 72
  6. 2022Unsupervised Object Localization: Observing the Background to Discover Objectscited by 66
  7. 2023DiffusionSeg: Adapting Diffusion Towards Unsupervised Object Discoverycited by 53
  8. 2023Invariant Slot Attention: Object Discovery with Slot-Centric Reference Framescited by 51
  9. 2023Self-supervised Object-Centric Learning for Videoscited by 49
  10. 2023SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformerscited by 49
  11. 2023Provably Learning Object-Centric Representationscited by 45
  12. 2024Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imaginationcited by 45
38 more
  1. 2024EmerDiff: Emerging Pixel-level Semantic Knowledge in Diffusion Modelscited by 42
  2. 2023Provable Compositional Generalization for Object-Centric Learningcited by 41
  3. 2024In Defense of Lazy Visual Grounding for Open-Vocabulary Semantic Segmentationcited by 38
  4. 2024Artificial Kuramoto Oscillatory Neuronscited by 37
  5. 2023Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representationscited by 35
  6. 2024Adaptive Slot Attention: Object Discovery with Dynamic Slot Numbercited by 34
  7. 2024What is the Visual Cognition Gap between Humans and Multimodal LLMs?cited by 30
  8. 2024Temporally Consistent Object-Centric Learning by Contrasting Slotscited by 30
  9. 2023Rotating Features for Object Discoverycited by 29
  10. 2024EAGLE: Eigen Aggregation Learning for Object-Centric Unsupervised Semantic Segmentationcited by 27
  11. 2023Object Discovery from Motion-Guided Tokenscited by 25
  12. 2023Shatter and Gather: Learning Referring Image Segmentation with Text Supervisioncited by 25
  13. 2024Distilling Spectral Graph for Object-Context Aware Open-Vocabulary Semantic Segmentationcited by 23
  14. 2023Causal Triplet: An Open Challenge for Intervention-centric Causal Representation Learningcited by 22
  15. 2024Understanding Video Transformers via Universal Concept Discoverycited by 22
  16. 2023Object-centric architectures enable efficient causal representation learningcited by 21
  17. 2023Slot-VAE: Object-Centric Scene Generation with Slot Attentioncited by 20
  18. 2023Semantics Meets Temporal Correspondence: Self-supervised Object-centric Learning in Videoscited by 20
  19. 2023Systematic Visual Reasoning through Object-Centric Relational Abstractioncited by 19
  20. 2023Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Samplingcited by 19
  21. 2024Zero-Shot Object-Centric Representation Learningcited by 19
  22. 2024Interaction Asymmetry: A General Principle for Learning Composable Abstractionscited by 19
  23. 2025Does Object Binding Naturally Emerge in Large Pretrained Vision Transformers?cited by 19
  24. 2023DDLP: Unsupervised Object-Centric Video Prediction with Deep Dynamic Latent Particlescited by 18
  25. 2023Causal Unsupervised Semantic Segmentationcited by 18
  26. 2023SmooSeg: Smoothness Prior for Unsupervised Semantic Segmentationcited by 18
  27. 2022Boosting Object Representation Learning via Motion and Object Continuitycited by 17
  28. 2023Shepherding Slots to Objects: Towards Stable and Robust Object-Centric Learningcited by 17
  29. 2023Grounded Object Centric Learningcited by 17
  30. 2023CrIBo: Self-Supervised Learning via Cross-Image Object-Level Bootstrappingcited by 17
  31. 2024Slot State Space Modelscited by 17
  32. 2023Object-centric Learning with Cyclic Walks between Parts and Wholecited by 16
  33. 2023DORSal: Diffusion for Object-centric Representations of Scenes et alcited by 16
  34. 2023Unsupervised Object Localization in the Era of Self-Supervised ViTs: A Surveycited by 16
  35. 2025Object-Centric World Model for Language-Guided Manipulationcited by 16
  36. 2023Object-Centric Multiple Object Trackingcited by 15
  37. 2024Near, far: Patch-ordering enhances vision foundation models' scene understandingcited by 15
  38. 2024Exploring the Effectiveness of Object-Centric Representations in Visual Question Answering: Comparative Insights with Foundation Modelscited by 14

50 most cited of 219 All 219 (JSON)