mlsanityData to 7 Oct 2026

Neural Expectation Maximization

arXiv 1708.03498 ↗First posted 11 Aug 2017cs.LG cs.NE stat.MLcited by 123

Not on the map. Why?

Abstract (arXiv)

Many real world tasks such as reasoning and physical interaction require identification and manipulation of conceptual entities. A first step towards solving these tasks is the automated discovery of distributed symbol-like representations. In this paper, we explicitly formalize this problem as inference in a spatial mixture model where each component is parametrized by a neural network. Based on the Expectation Maximization framework we then derive a differentiable clustering method that simultaneously learns how to group and represent individual entities. We evaluate our method on the (sequential) perceptual grouping task and find that it is able to accurately recover the constituent objects. We demonstrate that the learned representations are useful for next-step prediction.

Key facts. Cited by 123 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Aug 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 36; 2022: 28; 2023: 30; 2024: 17; 2025: 6; 2026: 6.

123 papers.

Sort:

By area:

  1. 2021Conditional Object-Centric Learning from Videocited by 247
  2. 2022SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videoscited by 165
  3. 2021Illiterate DALL-E Learns to Composecited by 147
  4. 2022Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videoscited by 139
  5. 2021Generative Adversarial Transformerscited by 120
  6. 2021GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinementcited by 109
  7. 2021Unsupervised Discovery of Object Radiance Fieldscited by 100
  8. 2021ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentationcited by 93
  9. 2023Object-Centric Slot Diffusioncited by 90
  10. 2021Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentationcited by 88
  11. 2023SlotDiffusion: Object-Centric Generative Modeling with Diffusion Modelscited by 85
  12. 2021Generalization and Robustness Implications in Object-Centric Learningcited by 81
38 more
  1. 2023Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similaritiescited by 78
  2. 2021Is Attention Better Than Matrix Decomposition?cited by 75
  3. 2021Unsupervised Learning of Compositional Energy Conceptscited by 71
  4. 2021MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Predictioncited by 61
  5. 2022Improving Object-centric Learning with Query Optimizationcited by 60
  6. 2023Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolationcited by 56
  7. 2023Invariant Slot Attention: Object Discovery with Slot-Centric Reference Framescited by 51
  8. 2021Unsupervised Layered Image Decomposition into Object Prototypescited by 50
  9. 2023Self-supervised Object-Centric Learning for Videoscited by 49
  10. 2022Object Representations as Fixed Points: Training Iterative Refinement Algorithms with Implicit Differentiationcited by 46
  11. 2023Provably Learning Object-Centric Representationscited by 45
  12. 2022Complex-Valued Autoencoders for Object Discoverycited by 40
  13. 2021Learning Object-Centric Representations of Multi-Object Scenes from Multiple Viewscited by 37
  14. 2022Neural Systematic Bindercited by 37
  15. 2021Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representationscited by 36
  16. 2021Single Image Depth Estimation: An Overviewcited by 35
  17. 2022PartAfford: Part-level Affordance Discovery from 3D Objectscited by 35
  18. 2022EM-driven unsupervised learning for efficient motion segmentationcited by 33
  19. 2022VAEL: Bridging Variational Autoencoders and Probabilistic Logic Programmingcited by 31
  20. 2021Unsupervised Object Learning via Common Fatecited by 29
  21. 2023Rotating Features for Object Discoverycited by 29
  22. 2022Unsupervised Discovery and Composition of Object Light Fieldscited 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. 2022Modularity-Aware Graph Autoencoders for Joint Community Detection and Link Predictioncited by 22
  27. 2023Causal Triplet: An Open Challenge for Intervention-centric Causal Representation Learningcited by 22
  28. 2023Towards Unsupervised Object Detection From LiDAR Point Cloudscited by 22
  29. 2021Structured World Belief for Reinforcement Learning in POMDPcited by 21
  30. 2023Slot-VAE: Object-Centric Scene Generation with Slot Attentioncited by 20
  31. 2022Neural Groundplans: Persistent Neural Scene Representations from a Single Imagecited by 17
  32. 2023Shepherding Slots to Objects: Towards Stable and Robust Object-Centric Learningcited by 17
  33. 2024Slot State Space Modelscited by 17
  34. 2021Self-supervised Reinforcement Learning with Independently Controllable Subgoalscited by 16
  35. 2022Promising or Elusive? Unsupervised Object Segmentation from Real-world Single Imagescited by 16
  36. 2023Contrastive Training of Complex-Valued Autoencoders for Object Discoverycited by 16
  37. 2023Object-Centric Multiple Object Trackingcited by 15
  38. 2022Unsupervised Learning of Temporal Abstractions with Slot-based Transformerscited by 14

50 most cited of 123 All 123 (JSON)