mlsanityData to 14 Oct 2026

Multi-Object Representation Learning with Iterative Variational Inference

arXiv 1903.00450 ↗First posted 1 Mar 2019cs.LG cs.CV stat.MLcited by 360

Not on the map. Why?

Cited by 22 in World models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Human perception is structured around objects which form the basis for our higher-level cognition and impressive systematic generalization abilities. Yet most work on representation learning focuses on feature learning without even considering multiple objects, or treats segmentation as an (often supervised) preprocessing step. Instead, we argue for the importance of learning to segment and represent objects jointly. We demonstrate that, starting from the simple assumption that a scene is composed of multiple entities, it is possible to learn to segment images into interpretable objects with disentangled representations. Our method learns -- without supervision -- to inpaint occluded parts, and extrapolates to scenes with more objects and to unseen objects with novel feature combinations. We also show that, due to the use of iterative variational inference, our system is able to learn multi-modal posteriors for ambiguous inputs and extends naturally to sequences.

Key facts. Cited by 360 papers in the map (data through 14 Oct 2026). First posted on arXiv 1 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2019: 1; 2020: 0; 2021: 70; 2022: 72; 2023: 72; 2024: 58; 2025: 40; 2026: 47.

360 papers.

Sort:

By area:

  1. 2022Kubric: A scalable dataset generatorcited by 381
  2. 2021Conditional Object-Centric Learning from Videocited by 248
  3. 2021Localizing Objects with Self-Supervised Transformers and no Labelscited by 230
  4. 2022Bridging the Gap to Real-World Object-Centric Learningcited by 220
  5. 2021Towards Causal Representation Learningcited by 209
  6. 2021PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learningcited by 182
  7. 2021Multi-Task Reinforcement Learning with Context-based Representationscited by 174
  8. 2022SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videoscited by 166
  9. 2022Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localizationcited by 150
  10. 2023Denoising Diffusion Samplerscited by 149
  11. 2021Self-supervised Video Object Segmentation by Motion Groupingcited by 147
  12. 2021Illiterate DALL-E Learns to Composecited by 147
38 more
  1. 2022Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videoscited by 139
  2. 2021Generative Adversarial Transformerscited by 120
  3. 2021GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinementcited by 109
  4. 2021Unsupervised Discovery of Object Radiance Fieldscited by 101
  5. 2021ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentationcited by 93
  6. 2022Object Scene Representation Transformercited by 90
  7. 2023Object-Centric Slot Diffusioncited by 90
  8. 2021Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentationcited by 88
  9. 2022Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learningcited by 86
  10. 2023SlotDiffusion: Object-Centric Generative Modeling with Diffusion Modelscited by 85
  11. 2021Generalization and Robustness Implications in Object-Centric Learningcited by 81
  12. 2022Object discovery and representation networkscited by 80
  13. 2021SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Datacited by 78
  14. 2022Adversarial Masking for Self-Supervised Learningcited by 78
  15. 2023Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similaritiescited by 78
  16. 2021Neural Production Systems: Learning Rule-Governed Visual Dynamicscited by 75
  17. 2021Greedy Hierarchical Variational Autoencoders for Large-Scale Video Predictioncited by 75
  18. 2021Unsupervised Learning of Compositional Energy Conceptscited by 71
  19. 2022Self-Supervised Visual Representation Learning with Semantic Groupingcited by 70
  20. 2021SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decompositioncited by 69
  21. 2023Compositional Generalization from First Principlescited by 64
  22. 2022Learning Multi-Object Dynamics with Compositional Neural Radiance Fieldscited by 63
  23. 2022Segmenting Moving Objects via an Object-Centric Layered Representationcited by 63
  24. 2022Improving Object-centric Learning with Query Optimizationcited by 60
  25. 2021SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editingcited by 58
  26. 2023Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolationcited by 58
  27. 2021Unsupervised Part Discovery from Contrastive Reconstructioncited by 57
  28. 2021Large-Scale Unsupervised Object Discoverycited by 54
  29. 2022Discovering Object Masks with Transformers for Unsupervised Semantic Segmentationcited by 54
  30. 2022Unsupervised Semantic Segmentation with Self-supervised Object-centric Representationscited by 54
  31. 2022Iso-Dream: Isolating and Leveraging Noncontrollable Visual Dynamics in World Modelscited by 53
  32. 2023Invariant Slot Attention: Object Discovery with Slot-Centric Reference Framescited by 51
  33. 2021Unsupervised Layered Image Decomposition into Object Prototypescited by 50
  34. 2023An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learningcited by 49
  35. 2023Self-supervised Object-Centric Learning for Videoscited by 49
  36. 2023SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformerscited by 49
  37. 2022Object Representations as Fixed Points: Training Iterative Refinement Algorithms with Implicit Differentiationcited by 46
  38. 2023Provably Learning Object-Centric Representationscited by 45

50 most cited of 360 All 360 (JSON)