mlsanityData to 7 Oct 2026

Differentiable Mathematical Programming for Object-Centric Representation Learning

arXiv 2210.02159 ↗First posted 5 Oct 2022cs.LG cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

We propose topology-aware feature partitioning into k disjoint partitions for given scene features as a method for object-centric representation learning. To this end, we propose to use minimum s-t graph cuts as a partitioning method which is represented as a linear program. The method is topologically aware since it explicitly encodes neighborhood relationships in the image graph. To solve the graph cuts our solution relies on an efficient, scalable, and differentiable quadratic programming approximation. Optimizations specific to cut problems allow us to solve the quadratic programs and compute their gradients significantly more efficiently compared with the general quadratic programming approach. Our results show that our approach is scalable and outperforms existing methods on object discovery tasks with textured scenes and objects.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 28 of its 44 references that are in the map. First posted on arXiv 5 Oct 2022.

Builds on

28 of 44 references.

References · 28

  1. 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,445
  2. 2020Object-Centric Learning with Slot Attentioncited by 865
  3. 2017OptNet: Differentiable Optimization as a Layer in Neural Networkscited by 588
  4. 2017Learning Sparse Neural Networks through L0 Regularizationcited by 571
  5. 2019MONet: Unsupervised Scene Decomposition and Representationcited by 388
  6. 2022Kubric: A scalable dataset generatorcited by 373
  7. 2019Multi-Object Representation Learning with Iterative Variational Inferencecited by 359
  8. 2021Conditional Object-Centric Learning from Videocited by 247
  9. 2019GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representationscited by 227
  10. 2018Melding the Data-Decisions Pipeline: Decision-Focused Learning for Combinatorial Optimizationcited by 220
  11. 2020SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decompositioncited by 190
  12. 2022SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videoscited by 165
16 more
  1. 2017OSQP: An Operator Splitting Solver for Quadratic Programscited by 156
  2. 2019Stochastic Optimization of Sorting Networks via Continuous Relaxationscited by 111
  3. 2021GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinementcited by 109
  4. 2018Neural Nearest Neighbors Networkscited by 98
  5. 2021ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentationcited by 93
  6. 2021Generalization and Robustness Implications in Object-Centric Learningcited by 81
  7. 2019Reparameterizable Subset Sampling via Continuous Relaxationscited by 69
  8. 2021SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decompositioncited by 69
  9. 2020How do Decisions Emerge across Layers in Neural Models? Interpretation with Differentiable Maskingcited by 63
  10. 2020Generative Neurosymbolic Machinescited by 57
  11. 2021Unsupervised Layered Image Decomposition into Object Prototypescited by 50
  12. 2022Complex-Valued Autoencoders for Object Discoverycited by 40
  13. 2021Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representationscited by 36
  14. 2021MarioNette: Self-Supervised Sprite Learningcited by 35
  15. 2013Neuronal Synchrony in Complex-Valued Deep Networkscited by 28
  16. 2018On the Differentiability of the Solution to Convex Optimization Problemscited by 23

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 1; 2025: 1; 2026: 1.

6 papers.

  1. 2023Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similaritiescited by 78
  2. 2023Unlocking Slot Attention by Changing Optimal Transport Costscited by 16
  3. 2024Mechanistic Neural Networks for Scientific Machine Learningcited by 16
  4. 2023Reusable Slotwise Mechanismscited by 4
  5. 2025MatrixNet: Learning over symmetry groups using learned group representationscited by 2
  6. 2026ORGAN: Object-Centric Representation Learning using Cycle Consistent Generative Adversarial Networkscited by 0