mlsanityData to 7 Oct 2026

Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions

arXiv 1802.10353 ↗First posted 28 Feb 2018cs.LG cs.AI cs.NEcited by 100

Not on the map. Why?

Abstract (arXiv)

Common-sense physical reasoning is an essential ingredient for any intelligent agent operating in the real-world. For example, it can be used to simulate the environment, or to infer the state of parts of the world that are currently unobserved. In order to match real-world conditions this causal knowledge must be learned without access to supervised data. To address this problem we present a novel method that learns to discover objects and model their physical interactions from raw visual images in a purely unsupervised fashion. It incorporates prior knowledge about the compositional nature of human perception to factor interactions between object-pairs and learn efficiently. On videos of bouncing balls we show the superior modelling capabilities of our method compared to other unsupervised neural approaches that do not incorporate such prior knowledge. We demonstrate its ability to handle occlusion and show that it can extrapolate learned knowledge to scenes with different numbers of objects.

Key facts. Cited by 100 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 43; 2022: 21; 2023: 21; 2024: 10; 2025: 4; 2026: 1.

100 papers.

Sort:

By area:

  1. 2021Conditional Object-Centric Learning from Videocited by 247
  2. 2021Towards Causal Representation Learningcited by 207
  3. 2021PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learningcited by 181
  4. 2022SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videoscited by 165
  5. 2022SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Modelscited by 146
  6. 2022Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videoscited by 139
  7. 2021GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinementcited by 109
  8. 2021Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentationcited by 88
  9. 2023SlotDiffusion: Object-Centric Generative Modeling with Diffusion Modelscited by 85
  10. 2021Coordination Among Neural Modules Through a Shared Global Workspacecited by 83
  11. 2021Generalization and Robustness Implications in Object-Centric Learningcited by 81
  12. 2023Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similaritiescited by 78
38 more
  1. 2021Neural Production Systems: Learning Rule-Governed Visual Dynamicscited by 75
  2. 2021Is Attention Better Than Matrix Decomposition?cited by 75
  3. 2021Unsupervised Learning of Compositional Energy Conceptscited by 71
  4. 2021Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learningcited by 53
  5. 2022Iso-Dream: Isolating and Leveraging Noncontrollable Visual Dynamics in World Modelscited by 53
  6. 2023Invariant Slot Attention: Object Discovery with Slot-Centric Reference Framescited by 51
  7. 2021Unsupervised Layered Image Decomposition into Object Prototypescited by 50
  8. 2022Object Representations as Fixed Points: Training Iterative Refinement Algorithms with Implicit Differentiationcited by 46
  9. 2023Provably Learning Object-Centric Representationscited by 45
  10. 2021iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesiscited by 42
  11. 2021Discrete-Valued Neural Communicationcited by 39
  12. 2021Understanding Object Dynamics for Interactive Image-to-Video Synthesiscited by 38
  13. 2022Learning to Accelerate Partial Differential Equations via Latent Global Evolutioncited by 38
  14. 2022Neural Systematic Bindercited by 37
  15. 2021Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representationscited by 36
  16. 2021RAIN: Reinforced Hybrid Attention Inference Network for Motion Forecastingcited by 36
  17. 2022PartAfford: Part-level Affordance Discovery from 3D Objectscited by 35
  18. 2022VAEL: Bridging Variational Autoencoders and Probabilistic Logic Programmingcited by 31
  19. 2024Temporally Consistent Object-Centric Learning by Contrasting Slotscited by 30
  20. 2021Unsupervised Object Learning via Common Fatecited by 29
  21. 2021Conditional Neural Relational Inference for Interacting Systemscited by 28
  22. 2022Dynamic-Group-Aware Networks for Multi-Agent Trajectory Prediction with Relational Reasoningcited by 28
  23. 2022Compositional Scene Representation Learning via Reconstruction: A Surveycited by 27
  24. 2021Unsupervised Foreground Extraction via Deep Region Competitioncited by 26
  25. 2021Generative Video Transformer: Can Objects be the Words?cited by 24
  26. 2021Dynamic Inference with Neural Interpreterscited by 24
  27. 2023Towards Unsupervised Object Detection From LiDAR Point Cloudscited by 22
  28. 2021Structured World Belief for Reinforcement Learning in POMDPcited by 21
  29. 2021Capturing the objects of vision with neural networkscited by 21
  30. 2023Object-centric architectures enable efficient causal representation learningcited by 21
  31. 2021Unsupervised Object-Based Transition Models for 3D Partially Observable Environmentscited by 19
  32. 2022Unsupervised Multi-object Segmentation by Predicting Probable Motion Patternscited by 19
  33. 2023Systematic Visual Reasoning through Object-Centric Relational Abstractioncited by 19
  34. 2023Shepherding Slots to Objects: Towards Stable and Robust Object-Centric Learningcited by 17
  35. 2024Slot State Space Modelscited by 17
  36. 2021Self-supervised Reinforcement Learning with Independently Controllable Subgoalscited by 16
  37. 2023Contrastive Training of Complex-Valued Autoencoders for Object Discoverycited by 16
  38. 2023Neural Relational Inference with Fast Modular Meta-learningcited by 16

50 most cited of 100 All 100 (JSON)