mlsanityData to 14 Oct 2026

Neural Systematic Binder

arXiv 2211.01177 ↗First posted 2 Nov 2022cs.CV cs.AI cs.LGcited by 37

Not on the map. Why?

Abstract (arXiv)

The key to high-level cognition is believed to be the ability to systematically manipulate and compose knowledge pieces. While token-like structured knowledge representations are naturally provided in text, it is elusive how to obtain them for unstructured modalities such as scene images. In this paper, we propose a neural mechanism called Neural Systematic Binder or SysBinder for constructing a novel structured representation called Block-Slot Representation. In Block-Slot Representation, object-centric representations known as slots are constructed by composing a set of independent factor representations called blocks, to facilitate systematic generalization. SysBinder obtains this structure in an unsupervised way by alternatingly applying two different binding principles: spatial binding for spatial modularity across the full scene and factor binding for factor modularity within an object. SysBinder is a simple, deterministic, and general-purpose layer that can be applied as a drop-in module in any arbitrary neural network and on any modality. In experiments, we find that SysBinder provides significantly better factor disentanglement within the slots than the conventional object-centric methods, including, for the first time, in visually complex scene images such as CLEVR-Tex. Furthermore, we demonstrate factor-level systematicity in controlled scene generation by decoding unseen factor combinations.

Key facts. Cited by 37 papers in the map (data through 14 Oct 2026). Builds on 75 of its 93 references that are in the map. First posted on arXiv 2 Nov 2022.

Builds on

75 of 93 references.

References · 75

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  3. 2017Neural Discrete Representation Learningcited by 4,712
  4. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  5. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  6. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  7. 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,457
  8. 2015Spatial Transformer Networkscited by 1,429
  9. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 941
  10. 2020Object-Centric Learning with Slot Attentioncited by 876
  11. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 860
  12. 2018Disentangling by Factorisingcited by 616
38 more
  1. 2019MONet: Unsupervised Scene Decomposition and Representationcited by 392
  2. 2019Multi-Object Representation Learning with Iterative Variational Inferencecited by 360
  3. 2021Conditional Object-Centric Learning from Videocited by 248
  4. 2017Variational Inference of Disentangled Latent Concepts from Unlabeled Observationscited by 241
  5. 2020On the Binding Problem in Artificial Neural Networkscited by 233
  6. 2019GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representationscited by 227
  7. 2019Recurrent Independent Mechanismscited by 219
  8. 2016Attend, Infer, Repeat: Fast Scene Understanding with Generative Modelscited by 209
  9. 2020SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decompositioncited by 190
  10. 2022Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cutcited by 167
  11. 2022SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videoscited by 166
  12. 2021Illiterate DALL-E Learns to Composecited by 147
  13. 2022Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videoscited by 139
  14. 2018Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objectscited by 128
  15. 2017Neural Expectation Maximizationcited by 123
  16. 2019Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEscited by 117
  17. 2019Entity Abstraction in Visual Model-Based Reinforcement Learningcited by 110
  18. 2021GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinementcited by 109
  19. 2019SCALOR: Generative World Models with Scalable Object Representationscited by 108
  20. 2018Learning Deep Disentangled Embeddings with the F-Statistic Losscited by 101
  21. 2018Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactionscited by 100
  22. 2021ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentationcited by 93
  23. 2022Object Scene Representation Transformercited by 90
  24. 2021Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentationcited by 88
  25. 2019Measuring Compositionality in Representation Learningcited by 84
  26. 2021Generalization and Robustness Implications in Object-Centric Learningcited by 81
  27. 2022Object discovery and representation networkscited by 80
  28. 2021Neural Production Systems: Learning Rule-Governed Visual Dynamicscited by 75
  29. 2020Improving Generative Imagination in Object-Centric World Modelscited by 71
  30. 2021Unsupervised Learning of Compositional Energy Conceptscited by 71
  31. 2022Self-Supervised Visual Representation Learning with Semantic Groupingcited by 70
  32. 2016Tagger: Deep Unsupervised Perceptual Groupingcited by 69
  33. 2021SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decompositioncited by 69
  34. 2020Unsupervised Shape and Pose Disentanglement for 3D Meshescited by 61
  35. 2019COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Explorationcited by 57
  36. 2020Generative Neurosymbolic Machinescited by 57
  37. 2020Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systemscited by 48
  38. 2022Object Representations as Fixed Points: Training Iterative Refinement Algorithms with Implicit Differentiationcited by 46

50 most cited of 75 All 75 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 11; 2024: 17; 2025: 6; 2026: 3.

37 papers.

Sort:

By area:

  1. 2023Object-Centric Slot Diffusioncited by 90
  2. 2023SlotDiffusion: Object-Centric Generative Modeling with Diffusion Modelscited by 85
  3. 2023An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learningcited by 49
  4. 2023SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformerscited by 49
  5. 2024Neural Assets: 3D-Aware Multi-Object Scene Synthesis with Image Diffusion Modelscited by 30
  6. 2023Rotating Features for Object Discoverycited by 29
  7. 2023Object-centric architectures enable efficient causal representation learningcited by 21
  8. 2023Slot-VAE: Object-Centric Scene Generation with Slot Attentioncited by 20
  9. 2024Interaction Asymmetry: A General Principle for Learning Composable Abstractionscited by 20
  10. 2024Slot State Space Modelscited by 17
  11. 2026Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modelingcited by 15
  12. 2024Neural Concept Bindercited by 14
25 more
  1. 2024A Complexity-Based Theory of Compositionalitycited by 13
  2. 2024Unsupervised Concept Discovery Mitigates Spurious Correlationscited by 11
  3. 2025Vector-Quantized Vision Foundation Models for Object-Centric Learningcited by 11
  4. 2025MetaSlot: Break Through the Fixed Number of Slots in Object-Centric Learningcited by 11
  5. 2024Neural Language of Thought Modelscited by 9
  6. 2024Recurrent Complex-Weighted Autoencoders for Unsupervised Object Discoverycited by 8
  7. 2023Concept-Centric Transformers: Enhancing Model Interpretability through Object-Centric Concept Learning within a Shared Global Workspacecited by 7
  8. 2024Multi-Scale Fusion for Object Representationcited by 7
  9. 2023Imagine the Unseen World: A Benchmark for Systematic Generalization in Visual World Modelscited by 6
  10. 2024Bootstrapping Top-down Information for Self-modulating Slot Attentioncited by 6
  11. 2024Binding Dynamics in Rotating Featurescited by 5
  12. 2024Grouped Discrete Representation for Object-Centric Learningcited by 5
  13. 2024Explicitly Disentangled Representations in Object-Centric Learningcited by 4
  14. 2025Dreamweaver: Learning Compositional World Models from Pixelscited by 4
  15. 2023Discrete, compositional, and symbolic representations through attractor dynamicscited by 2
  16. 2023Leveraging Image Augmentation for Object Manipulation: Towards Interpretable Controllability in Object-Centric Learningcited by 2
  17. 2024Attention-based Iterative Decomposition for Tensor Product Representationcited by 2
  18. 2024Grouped Discrete Representation Guides Object-Centric Learningcited by 2
  19. 2024Successes and Limitations of Object-centric Models at Compositional Generalisationcited by 2
  20. 2025Neural USD: An object-centric framework for iterative editing and controlcited by 2
  21. 2026DiCo: Disentangled Concept Representation for Text-to-image Person Re-identificationcited by 2
  22. 2024Learning Disentangled Representation in Object-Centric Models for Visual Dynamics Prediction via Transformerscited by 1
  23. 2025Disentangled Representation Learning via Modular Compositional Biascited by 1
  24. 2025Multi-Part Object Representations via Graph Structures and Co-Part Discoverycited by 0
  25. 2026Disentanglement with Holographic Reduced Representationscited by 0