mlsanityData to 14 Oct 2026

Conditional Permutation Invariant Flows

arXiv 2206.09021 ↗First posted 17 Jun 2022stat.ML cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

We present a novel, conditional generative probabilistic model of set-valued data with a tractable log density. This model is a continuous normalizing flow governed by permutation equivariant dynamics. These dynamics are driven by a learnable per-set-element term and pairwise interactions, both parametrized by deep neural networks. We illustrate the utility of this model via applications including (1) complex traffic scene generation conditioned on visually specified map information, and (2) object bounding box generation conditioned directly on images. We train our model by maximizing the expected likelihood of labeled conditional data under our flow, with the aid of a penalty that ensures the dynamics are smooth and hence efficiently solvable. Our method significantly outperforms non-permutation invariant baselines in terms of log likelihood and domain-specific metrics (offroad, collision, and combined infractions), yielding realistic samples that are difficult to distinguish from real data.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 39 of its 50 references that are in the map. First posted on arXiv 17 Jun 2022.

Builds on

39 of 50 references.

References · 39

  1. 2017Attention Is All You Needcited by 60,361
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  4. 2020End-to-End Object Detection with Transformerscited by 7,414
  5. 2022Generative Adversarial Networkscited by 5,627
  6. 2013Auto-Encoding Variational Bayescited by 4,053
  7. 2018Neural Ordinary Differential Equationscited by 3,779
  8. 2015Variational Inference with Normalizing Flowscited by 2,170
  9. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
  10. 2016Density estimation using Real NVPcited by 2,042
  11. 2020Linformer: Self-Attention with Linear Complexitycited by 1,474
  12. 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,457
27 more
  1. 2017Deep Setscited by 1,421
  2. 2016Group Equivariant Convolutional Networkscited by 1,165
  3. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,148
  4. 2018Attention-based Deep Multiple Instance Learningcited by 1,095
  5. 2020Object-Centric Learning with Slot Attentioncited by 876
  6. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 754
  7. 2019MONet: Unsupervised Scene Decomposition and Representationcited by 392
  8. 2019Multi-Object Representation Learning with Iterative Variational Inferencecited by 360
  9. 2018Neural Relational Inference for Interacting Systemscited by 339
  10. 2017Relation Networks for Object Detectioncited by 305
  11. 2020Permutation Invariant Graph Generation via Score-Based Generative Modelingcited by 270
  12. 2020Equivariant Flows: Exact Likelihood Generative Learning for Symmetric Densitiescited by 250
  13. 2019INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTION Dataset in Interactive Driving Scenarios with Semantic Mapscited by 231
  14. 2020How to train your neural ODE: the world of Jacobian and kinetic regularizationcited by 228
  15. 2021A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groupscited by 187
  16. 2019Learning Likelihoods with Conditional Normalizing Flowscited by 172
  17. 2021E(n) Equivariant Normalizing Flowscited by 165
  18. 2018Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networkscited by 132
  19. 2019Graph Normalizing Flowscited by 104
  20. 2021SceneGen: Learning to Generate Realistic Traffic Scenescited by 84
  21. 2020Learning Differential Equations that are Easy to Solvecited by 81
  22. 2019Deep Set Prediction Networkscited by 71
  23. 2019FSPool: Learning Set Representations with Featurewise Sort Poolingcited by 53
  24. 2021PointFlow: Flowing Semantics Through Points for Aerial Image Segmentationcited by 29
  25. 2020Scalable Normalizing Flows for Permutation Invariant Densitiescited by 22
  26. 2014Transformation Properties of Learned Visual Representationscited by 18
  27. 2019Neural Networks with Cheap Differential Operatorscited by 18

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 2; 2025: 0; 2026: 1.

6 papers.

  1. 2023Equivariant flow matchingcited by 135
  2. 2024On permutation-invariant neural networkscited by 10
  3. 2023Don't be so negative! Score-based Generative Modeling with Oracle-assisted Guidancecited by 6
  4. 2024TorchDriveEnv: A Reinforcement Learning Benchmark for Autonomous Driving with Reactive, Realistic, and Diverse Non-Playable Characterscited by 6
  5. 2023Realistically distributing object placements in synthetic training data improves the performance of vision-based object detection modelscited by 1
  6. 2026Mirror Learningcited by 0