mlsanityData to 7 Oct 2026

Differentiable Particle Filters through Conditional Normalizing Flow

arXiv 2107.00488 ↗First posted 1 Jul 2021cs.AI cs.LGcited by 15

Not on the map. Why?

Abstract (arXiv)

Differentiable particle filters provide a flexible mechanism to adaptively train dynamic and measurement models by learning from observed data. However, most existing differentiable particle filters are within the bootstrap particle filtering framework and fail to incorporate the information from latest observations to construct better proposals. In this paper, we utilize conditional normalizing flows to construct proposal distributions for differentiable particle filters, enriching the distribution families that the proposal distributions can represent. In addition, normalizing flows are incorporated in the construction of the dynamic model, resulting in a more expressive dynamic model. We demonstrate the performance of the proposed conditional normalizing flow-based differentiable particle filters in a visual tracking task.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 15 of its 23 references that are in the map. First posted on arXiv 1 Jul 2021.

Builds on

15 of 23 references.

References · 15

  1. 2013Auto-Encoding Variational Bayescited by 3,980
  2. 2016Density estimation using Real NVPcited by 2,029
  3. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  4. 2019Learning Likelihoods with Conditional Normalizing Flowscited by 170
  5. 2019Noise Flow: Noise Modeling with Conditional Normalizing Flowscited by 108
  6. 2018Particle Filter Networks with Application to Visual Localizationcited by 64
  7. 2021Differentiable Particle Filtering via Entropy-Regularized Optimal Transportcited by 59
  8. 2018Differentiable Particle Filters: End-to-End Learning with Algorithmic Priorscited by 58
  9. 2014On Particle Methods for Parameter Estimation in State-Space Modelscited by 47
  10. 2016Backprop KF: Learning Discriminative Deterministic State Estimatorscited by 47
  11. 2019Particle Filter Recurrent Neural Networkscited by 36
  12. 2021Differentiable SLAM-net: Learning Particle SLAM for Visual Navigationcited by 34
3 more
  1. 2020How to Train Your Differentiable Filtercited by 23
  2. 2021Differentiable Factor Graph Optimization for Learning Smootherscited by 17
  3. 2020End-To-End Semi-supervised Learning for Differentiable Particle Filterscited by 12

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 1; 2023: 6; 2024: 4; 2025: 3.

15 papers.

Sort:

By area:

  1. 2023An overview of differentiable particle filters for data-adaptive sequential Bayesian inferencecited by 23
  2. 2024Normalizing Flow-based Differentiable Particle Filterscited by 10
  3. 2021Efficient Learning of the Parameters of Non-Linear Models using Differentiable Resampling in Particle Filterscited by 9
  4. 2023Unsupervised Learning of Sampling Distributions for Particle Filterscited by 8
  5. 2022Conditional Measurement Density Estimation in Sequential Monte Carlo via Normalizing Flowcited by 6
  6. 2023Sparse Graphical Linear Dynamical Systemscited by 4
  7. 2023Exact nonlinear state estimationcited by 4
  8. 2025Steering Deep Non-Linear Spatially Selective Filters for Weakly Guided Extraction of Moving Speakers in Dynamic Scenarioscited by 4
  9. 2025Flow-based Bayesian filtering for high-dimensional nonlinear stochastic dynamical systemscited by 3
  10. 2023Differentiable Bootstrap Particle Filters for Regime-Switching Modelscited by 2
  11. 2023Learning Differentiable Particle Filter on the Flycited by 2
  12. 2024Revisiting semi-supervised training objectives for differentiable particle filterscited by 2
3 more
  1. 2025DnD Filter: Differentiable State Estimation for Dynamic Systems using Diffusion Modelscited by 1
  2. 2024Inverse Particle Filtercited by 0
  3. 2024Learning Flock: Enhancing Sets of Particles for Multi~Sub-State Particle Filtering with Neural Augmentationcited by 0