mlsanityData to 7 Oct 2026

Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEs

arXiv 1901.07017 ↗First posted 21 Jan 2019cs.LG cs.CV stat.MLcited by 116

Not on the map. Why?

Abstract (arXiv)

We present a simple neural rendering architecture that helps variational autoencoders (VAEs) learn disentangled representations. Instead of the deconvolutional network typically used in the decoder of VAEs, we tile (broadcast) the latent vector across space, concatenate fixed X- and Y-"coordinate" channels, and apply a fully convolutional network with 1x1 stride. This provides an architectural prior for dissociating positional from non-positional features in the latent distribution of VAEs, yet without providing any explicit supervision to this effect. We show that this architecture, which we term the Spatial Broadcast decoder, improves disentangling, reconstruction accuracy, and generalization to held-out regions in data space. It provides a particularly dramatic benefit when applied to datasets with small objects. We also emphasize a method for visualizing learned latent spaces that helped us diagnose our models and may prove useful for others aiming to assess data representations. Finally, we show the Spatial Broadcast Decoder is complementary to state-of-the-art (SOTA) disentangling techniques and when incorporated improves their performance.

Key facts. Cited by 116 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Jan 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 1; 2020: 1; 2021: 21; 2022: 14; 2023: 26; 2024: 25; 2025: 19; 2026: 9.

116 papers.

Sort:

By area:

  1. 2021Conditional Object-Centric Learning from Videocited by 247
  2. 2022Bridging the Gap to Real-World Object-Centric Learningcited by 219
  3. 2021NEAT: Neural Attention Fields for End-to-End Autonomous Drivingcited by 174
  4. 2021Illiterate DALL-E Learns to Composecited by 147
  5. 2021GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinementcited by 109
  6. 2021ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentationcited by 93
  7. 2022Object Scene Representation Transformercited by 90
  8. 2023SlotDiffusion: Object-Centric Generative Modeling with Diffusion Modelscited by 85
  9. 2021Generalization and Robustness Implications in Object-Centric Learningcited by 81
  10. 2023SODA: Bottleneck Diffusion Models for Representation Learningcited by 76
  11. 2021SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decompositioncited by 69
  12. 2022Improving Object-centric Learning with Query Optimizationcited by 60
38 more
  1. 2023Invariant Slot Attention: Object Discovery with Slot-Centric Reference Framescited by 51
  2. 2021Unsupervised Layered Image Decomposition into Object Prototypescited by 50
  3. 2023Self-supervised Object-Centric Learning for Videoscited by 49
  4. 2022Object Representations as Fixed Points: Training Iterative Refinement Algorithms with Implicit Differentiationcited by 46
  5. 2021Learning Object-Centric Representations of Multi-Object Scenes from Multiple Viewscited by 37
  6. 2022Neural Systematic Bindercited by 37
  7. 2023Crossway Diffusion: Improving Diffusion-based Visuomotor Policy via Self-supervised Learningcited by 37
  8. 2021Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representationscited by 36
  9. 2024Temporally Consistent Object-Centric Learning by Contrasting Slotscited by 30
  10. 2021Learning to Give Checkable Answers with Prover-Verifier Gamescited by 29
  11. 2022Compositional Scene Representation Learning via Reconstruction: A Surveycited by 27
  12. 2021Towards Building A Group-based Unsupervised Representation Disentanglement Frameworkcited by 22
  13. 2023Slot-VAE: Object-Centric Scene Generation with Slot Attentioncited by 20
  14. 2023Learning to reason over visual objectscited by 19
  15. 2023Systematic Visual Reasoning through Object-Centric Relational Abstractioncited by 19
  16. 2024Interaction Asymmetry: A General Principle for Learning Composable Abstractionscited by 19
  17. 2021Local Disentanglement in Variational Auto-Encoders Using Jacobian L1 Regularizationcited by 17
  18. 2023Shepherding Slots to Objects: Towards Stable and Robust Object-Centric Learningcited by 17
  19. 2024Slot State Space Modelscited by 17
  20. 2023Contrastive Training of Complex-Valued Autoencoders for Object Discoverycited by 16
  21. 2023DORSal: Diffusion for Object-centric Representations of Scenes et alcited by 16
  22. 2025Object-Centric World Model for Language-Guided Manipulationcited by 16
  23. 2021Group Equivariant Subsamplingcited by 15
  24. 2024PLOT: Text-based Person Search with Part Slot Attention for Corresponding Part Discoverycited by 15
  25. 2022Unsupervised Learning of Temporal Abstractions with Slot-based Transformerscited by 14
  26. 2023Neurosymbolic Grounding for Compositional World Modelscited by 14
  27. 2024Exploring the Effectiveness of Object-Centric Representations in Visual Question Answering: Comparative Insights with Foundation Modelscited by 14
  28. 2021Reasoning-Modulated Representationscited by 13
  29. 2025Slot-Guided Adaptation of Pre-trained Diffusion Models for Object-Centric Learning and Compositional Generationcited by 13
  30. 2022Lost in Latent Space: Disentangled Models and the Challenge of Combinatorial Generalisationcited by 11
  31. 2023Object-Centric Learning with Slot Mixture Modulecited by 11
  32. 2025Vector-Quantized Vision Foundation Models for Object-Centric Learningcited by 11
  33. 2025MetaSlot: Break Through the Fixed Number of Slots in Object-Centric Learningcited by 11
  34. 2021Object-Centric Representation Learning with Generative Spatial-Temporal Factorizationcited by 10
  35. 2024Slot Abstractors: Toward Scalable Abstract Visual Reasoningcited by 10
  36. 2021Raven's Progressive Matrices Completion with Latent Gaussian Process Priorscited by 9
  37. 2022Test-time Adaptation with Slot-Centric Modelscited by 9
  38. 2024Neural Language of Thought Modelscited by 9

50 most cited of 116 All 116 (JSON)