mlsanityData to 7 Oct 2026

Identifiable Object-Centric Representation Learning via Probabilistic Slot Attention

arXiv 2406.07141 ↗First posted 11 Jun 2024cs.LG cs.AIcited by 9

Not on the map. Why?

Abstract (arXiv)

Learning modular object-centric representations is crucial for systematic generalization. Existing methods show promising object-binding capabilities empirically, but theoretical identifiability guarantees remain relatively underdeveloped. Understanding when object-centric representations can theoretically be identified is crucial for scaling slot-based methods to high-dimensional images with correctness guarantees. To that end, we propose a probabilistic slot-attention algorithm that imposes an aggregate mixture prior over object-centric slot representations, thereby providing slot identifiability guarantees without supervision, up to an equivalence relation. We provide empirical verification of our theoretical identifiability result using both simple 2-dimensional data and high-resolution imaging datasets.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 51 of its 79 references that are in the map. First posted on arXiv 11 Jun 2024.

Builds on

51 of 79 references.

References · 51

  1. 2017Attention Is All You Needcited by 59,932
  2. 2017Neural Discrete Representation Learningcited by 4,650
  3. 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,445
  4. 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
  5. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
  6. 2020Object-Centric Learning with Slot Attentioncited by 865
  7. 2018Disentangling by Factorisingcited by 614
  8. 2019Variational Autoencoders and Nonlinear ICA: A Unifying Frameworkcited by 494
  9. 2019MONet: Unsupervised Scene Decomposition and Representationcited by 388
  10. 2019Multi-Object Representation Learning with Iterative Variational Inferencecited by 359
  11. 2021Self-Supervised Learning with Data Augmentations Provably Isolates Content from Stylecited by 308
  12. 2018Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive Learningcited by 278
38 more
  1. 2016Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICAcited by 270
  2. 2017VAE with a VampPriorcited by 247
  3. 2021Conditional Object-Centric Learning from Videocited by 247
  4. 2020Weakly-Supervised Disentanglement Without Compromisescited by 237
  5. 2020On the Binding Problem in Artificial Neural Networkscited by 230
  6. 2019GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representationscited by 227
  7. 2021Contrastive Learning Inverts the Data Generating Processcited by 220
  8. 2016Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoderscited by 219
  9. 2022Bridging the Gap to Real-World Object-Centric Learningcited by 219
  10. 2020SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decompositioncited by 190
  11. 2018Tell Me Where to Look: Guided Attention Inference Networkcited by 168
  12. 2022SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videoscited by 165
  13. 2021Illiterate DALL-E Learns to Composecited by 147
  14. 2022Weakly supervised causal representation learningcited by 140
  15. 2022Interventional Causal Representation Learningcited by 140
  16. 2022Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videoscited by 139
  17. 2021How to represent part-whole hierarchies in a neural networkcited by 123
  18. 2015Deep Convolutional Inverse Graphics Networkcited by 121
  19. 2019Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEscited by 116
  20. 2021GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinementcited by 109
  21. 2018Iterative Amortized Inferencecited by 93
  22. 2023Multi-View Causal Representation Learning with Partial Observabilitycited by 72
  23. 2022Identifiability of deep generative models without auxiliary informationcited by 70
  24. 2022Weakly Supervised Representation Learning with Sparse Perturbationscited by 64
  25. 2023Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolationcited by 56
  26. 2022Function Classes for Identifiable Nonlinear Independent Component Analysiscited by 53
  27. 2023SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformerscited by 49
  28. 2022Object Representations as Fixed Points: Training Iterative Refinement Algorithms with Implicit Differentiationcited by 46
  29. 2023Provably Learning Object-Centric Representationscited by 45
  30. 2022From Statistical to Causal Learningcited by 40
  31. 2024Nonparametric Partial Disentanglement via Mechanism Sparsity: Sparse Actions, Interventions and Sparse Temporal Dependenciescited by 39
  32. 2019Capsule Routing via Variational Bayescited by 32
  33. 2023Rotating Features for Object Discoverycited by 29
  34. 2021Multi-Facet Clustering Variational Autoencoderscited by 28
  35. 2021I Don't Need u: Identifiable Non-Linear ICA Without Side Informationcited by 21
  36. 2023Object-centric architectures enable efficient causal representation learningcited by 21
  37. 2023Slot-VAE: Object-Centric Scene Generation with Slot Attentioncited by 20
  38. 2023Grounded Object Centric Learningcited by 17

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 6; 2026: 2.

9 papers.

  1. 2024Interaction Asymmetry: A General Principle for Learning Composable Abstractionscited by 19
  2. 2025MetaSlot: Break Through the Fixed Number of Slots in Object-Centric Learningcited by 11
  3. 2025Slot-BERT: Self-supervised Object Discovery in Surgical Videocited by 4
  4. 2025unMORE: Unsupervised Multi-Object Segmentation via Center-Boundary Reasoningcited by 4
  5. 2025Diverse Influence Component Analysis: A Geometric Approach to Nonlinear Mixture Identifiabilitycited by 4
  6. 2025Neurosymbolic Object-Centric Learning with Distant Supervisioncited by 2
  7. 2025Transparent Visual Reasoning via Object-Centric Agent Collaborationcited by 0
  8. 2026Entity-Centric World Models: Interaction-Aware Masking for Causal Video Predictioncited by 0
  9. 2026Not all solutions are created equal: An analytical dissociation of functional and representational similarity in deep linear neural networkscited by 0