mlsanityData to 14 Oct 2026

Object-Centric Learning with Slot Attention

arXiv 2006.15055 ↗First posted 26 Jun 2020cs.LG cs.CV stat.MLcited by 876

Not on the map. Why?

Cited by 53 in World models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Learning object-centric representations of complex scenes is a promising step towards enabling efficient abstract reasoning from low-level perceptual features. Yet, most deep learning approaches learn distributed representations that do not capture the compositional properties of natural scenes. In this paper, we present the Slot Attention module, an architectural component that interfaces with perceptual representations such as the output of a convolutional neural network and produces a set of task-dependent abstract representations which we call slots. These slots are exchangeable and can bind to any object in the input by specializing through a competitive procedure over multiple rounds of attention. We empirically demonstrate that Slot Attention can extract object-centric representations that enable generalization to unseen compositions when trained on unsupervised object discovery and supervised property prediction tasks.

Key facts. Cited by 876 papers in the map (data through 14 Oct 2026). First posted on arXiv 26 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 99; 2022: 130; 2023: 165; 2024: 156; 2025: 145; 2026: 181.

876 papers.

Sort:

By area:

  1. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,071
  2. 2021Perceiver: General Perception with Iterative Attentioncited by 1,104
  3. 2021Multiscale Vision Transformerscited by 897
  4. 2023Vision Transformers Need Registerscited by 871
  5. 2021Perceiver IO: A General Architecture for Structured Inputs & Outputscited by 629
  6. 2022Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulationcited by 551
  7. 2022GroupViT: Semantic Segmentation Emerges from Text Supervisioncited by 531
  8. 2021ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biasescited by 484
  9. 2022Kubric: A scalable dataset generatorcited by 381
  10. 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 367
  11. 2024ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulationcited by 315
  12. 2021Understanding Robustness of Transformers for Image Classificationcited by 249
38 more
  1. 2021Conditional Object-Centric Learning from Videocited by 248
  2. 2021Localizing Objects with Self-Supervised Transformers and no Labelscited by 230
  3. 2021Keeping Your Eye on the Ball: Trajectory Attention in Video Transformerscited by 224
  4. 2022Bridging the Gap to Real-World Object-Centric Learningcited by 220
  5. 2021Towards Causal Representation Learningcited by 209
  6. 2022Scalable Adaptive Computation for Iterative Generationcited by 195
  7. 2021Multi-Task Reinforcement Learning with Context-based Representationscited by 174
  8. 2022SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videoscited by 166
  9. 2022Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localizationcited by 150
  10. 2021Self-supervised Video Object Segmentation by Motion Groupingcited by 147
  11. 2021Illiterate DALL-E Learns to Composecited by 147
  12. 2022SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Modelscited by 147
  13. 2022Weakly supervised causal representation learningcited by 140
  14. 2022Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videoscited by 139
  15. 2022VIOLA: Imitation Learning for Vision-Based Manipulation with Object Proposal Priorscited by 136
  16. 2021How to represent part-whole hierarchies in a neural networkcited by 123
  17. 2021Generative Adversarial Transformerscited by 120
  18. 2021Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learningcited by 113
  19. 2022Disentangled Representation Learningcited by 112
  20. 2021GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinementcited by 109
  21. 2021LambdaNetworks: Modeling Long-Range Interactions Without Attentioncited by 107
  22. 2021Unsupervised Discovery of Object Radiance Fieldscited by 101
  23. 2023Learning Open-vocabulary Semantic Segmentation Models From Natural Language Supervisioncited by 99
  24. 2022Learning Dynamic Facial Radiance Fields for Few-Shot Talking Head Synthesiscited by 97
  25. 2021ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentationcited by 93
  26. 2023Weakly-Supervised Concealed Object Segmentation with SAM-based Pseudo Labeling and Multi-scale Feature Groupingcited by 92
  27. 2023Grounding Everything: Emerging Localization Properties in Vision-Language Transformerscited by 91
  28. 2022Object Scene Representation Transformercited by 90
  29. 2023Object-Centric Slot Diffusioncited by 90
  30. 2023RoboTAP: Tracking Arbitrary Points for Few-Shot Visual Imitationcited by 90
  31. 2021Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentationcited by 88
  32. 2023SlotDiffusion: Object-Centric Generative Modeling with Diffusion Modelscited by 85
  33. 2023Modular Deep Learningcited by 83
  34. 2022Perceptual Grouping in Contrastive Vision-Language Modelscited by 82
  35. 2021Generalization and Robustness Implications in Object-Centric Learningcited by 81
  36. 2022Object discovery and representation networkscited by 80
  37. 2023Knowing Where to Focus: Event-aware Transformer for Video Groundingcited by 79
  38. 2021SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Datacited by 78

50 most cited of 876 All 876 (JSON)