mlsanityData to 13 Oct 2026

Multi-Resolution Continuous Normalizing Flows

arXiv 2106.08462 ↗First posted 15 Jun 2021cs.CV cs.LG eess.IVcited by 4

Not on the map. Why?

Abstract (arXiv)

Recent work has shown that Neural Ordinary Differential Equations (ODEs) can serve as generative models of images using the perspective of Continuous Normalizing Flows (CNFs). Such models offer exact likelihood calculation, and invertible generation/density estimation. In this work we introduce a Multi-Resolution variant of such models (MRCNF), by characterizing the conditional distribution over the additional information required to generate a fine image that is consistent with the coarse image. We introduce a transformation between resolutions that allows for no change in the log likelihood. We show that this approach yields comparable likelihood values for various image datasets, with improved performance at higher resolutions, with fewer parameters, using only 1 GPU. Further, we examine the out-of-distribution properties of (Multi-Resolution) Continuous Normalizing Flows, and find that they are similar to those of other likelihood-based generative models.

Key facts. Cited by 4 papers in the map (data through 13 Oct 2026). Builds on 68 of its 106 references that are in the map. First posted on arXiv 15 Jun 2021.

Builds on

68 of 106 references.

References · 68

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,952
  2. 2020Denoising Diffusion Implicit Modelscited by 9,718
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,028
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,023
  5. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,849
  6. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,077
  7. 2018Neural Ordinary Differential Equationscited by 3,750
  8. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,585
  9. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,975
  10. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,619
  11. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,371
  12. 2015Variational Inference with Normalizing Flowscited by 2,163
38 more
  1. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,051
  2. 2016Density estimation using Real NVPcited by 2,033
  3. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,542
  4. 2019Generating Long Sequences with Sparse Transformerscited by 1,538
  5. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,475
  6. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,381
  7. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,327
  8. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,317
  9. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,039
  10. 2018Deep Anomaly Detection with Outlier Exposurecited by 941
  11. 2016Conditional Image Generation with PixelCNN Decoderscited by 861
  12. 2016Pixel Recurrent Neural Networkscited by 815
  13. 2018Image Transformercited by 771
  14. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 638
  15. 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 637
  16. 2019Neural Spline Flowscited by 590
  17. 2018FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Modelscited by 588
  18. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 464
  19. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  20. 2015Adversarial Autoencoderscited by 364
  21. 2018Invertible Residual Networkscited by 364
  22. 2019Axial Attention in Multidimensional Transformerscited by 356
  23. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
  24. 2015A note on the evaluation of generative modelscited by 291
  25. 2019Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Designcited by 260
  26. 2019Residual Flows for Invertible Generative Modelingcited by 257
  27. 2020How to train your neural ODE: the world of Jacobian and kinetic regularizationcited by 228
  28. 2020Why Normalizing Flows Fail to Detect Out-of-Distribution Datacited by 220
  29. 2015Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networkscited by 214
  30. 2019Input complexity and out-of-distribution detection with likelihood-based generative modelscited by 186
  31. 2018Stochastic Adversarial Video Predictioncited by 173
  32. 2020OT-Flow: Fast and Accurate Continuous Normalizing Flows via Optimal Transportcited by 143
  33. 2017PixelSNAIL: An Improved Autoregressive Generative Modelcited by 137
  34. 2017PacGAN: The power of two samples in generative adversarial networkscited by 104
  35. 2020Adversarial score matching and improved sampling for image generationcited by 95
  36. 2019Integer Discrete Flows and Lossless Compressioncited by 83
  37. 2019On Robustness of Neural Ordinary Differential Equationscited by 83
  38. 2020Learning Differential Equations that are Easy to Solvecited by 81

50 most cited of 68 All 68 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 1; 2025: 1.

4 papers.

  1. 2022Comparing the latent space of generative modelscited by 11
  2. 2025Lecture Notes on Normalizing Flows for Lattice Quantum Field Theoriescited by 4
  3. 2023Probabilistic and Semantic Descriptions of Image Manifolds and Their Applicationscited by 3
  4. 2024Multi-Lattice Sampling of Quantum Field Theories via Neural Operator-based Flowscited by 1