mlsanityData to 14 Oct 2026

Exploring the Role of the Bottleneck in Slot-Based Models Through Covariance Regularization

arXiv 2306.02577 ↗First posted 5 Jun 2023cs.CV cs.AI cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

In this project we attempt to make slot-based models with an image reconstruction objective competitive with those that use a feature reconstruction objective on real world datasets. We propose a loss-based approach to constricting the bottleneck of slot-based models, allowing larger-capacity encoder networks to be used with Slot Attention without producing degenerate stripe-shaped masks. We find that our proposed method offers an improvement over the baseline Slot Attention model but does not reach the performance of dinosaur on the COCO2017 dataset. Throughout this project, we confirm the superiority of a feature reconstruction objective over an image reconstruction objective and explore the role of the architectural bottleneck in slot-based models.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 21 of its 23 references that are in the map. First posted on arXiv 5 Jun 2023.

Builds on

21 of 23 references.

References · 21

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  3. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  4. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  5. 2021VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learningcited by 1,057
  6. 2020Object-Centric Learning with Slot Attentioncited by 876
  7. 2020Inductive Biases for Deep Learning of Higher-Level Cognitioncited by 275
  8. 2021Conditional Object-Centric Learning from Videocited by 248
  9. 2020On the Binding Problem in Artificial Neural Networkscited by 233
  10. 2022Bridging the Gap to Real-World Object-Centric Learningcited by 220
  11. 2019Contrastive Learning of Structured World Modelscited by 209
  12. 2022SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videoscited by 166
9 more
  1. 2021Illiterate DALL-E Learns to Composecited by 147
  2. 2022Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videoscited by 139
  3. 2021ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentationcited by 93
  4. 2021Generalization and Robustness Implications in Object-Centric Learningcited by 81
  5. 2023Invariant Slot Attention: Object Discovery with Slot-Centric Reference Framescited by 51
  6. 2019A Perspective on Objects and Systematic Generalization in Model-Based RLcited by 14
  7. 2022Inductive Biases for Object-Centric Representations in the Presence of Complex Texturescited by 13
  8. 2020Slot Contrastive Networks: A Contrastive Approach for Representing Objectscited by 9
  9. 2022Towards Unsupervised Visual Reasoning: Do Off-The-Shelf Features Know How to Reason?cited by 1

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1; 2025: 1.

3 papers.

  1. 2023SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformerscited by 49
  2. 2024Attention Normalization Impacts Cardinality Generalization in Slot Attentioncited by 2
  3. 2025ContextFusion and Bootstrap: An Effective Approach to Improve Slot Attention-Based Object-Centric Learningcited by 0