mlsanityData to 7 Oct 2026

Discrete Denoising Flows

arXiv 2107.11625 ↗First posted 24 Jul 2021cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Discrete flow-based models are a recently proposed class of generative models that learn invertible transformations for discrete random variables. Since they do not require data dequantization and maximize an exact likelihood objective, they can be used in a straight-forward manner for lossless compression. In this paper, we introduce a new discrete flow-based model for categorical random variables: Discrete Denoising Flows (DDFs). In contrast with other discrete flow-based models, our model can be locally trained without introducing gradient bias. We show that DDFs outperform Discrete Flows on modeling a toy example, binary MNIST and Cityscapes segmentation maps, measured in log-likelihood.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 18 of its 21 references that are in the map. First posted on arXiv 24 Jul 2021.

Builds on

18 of 21 references.

References · 18

  1. 2016Densely Connected Convolutional Networkscited by 6,691
  2. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  3. 2013Auto-Encoding Variational Bayescited by 3,980
  4. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  5. 2015Variational Inference with Normalizing Flowscited by 2,161
  6. 2016Density estimation using Real NVPcited by 2,029
  7. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  8. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  9. 2016Conditional Image Generation with PixelCNN Decoderscited by 859
  10. 2018Practical Full Resolution Learned Lossless Image Compressioncited by 93
  11. 2019Practical Lossless Compression with Latent Variables using Bits Back Codingcited by 85
  12. 2019Integer Discrete Flows and Lossless Compressioncited by 82
6 more
  1. 2019Discrete Flows: Invertible Generative Models of Discrete Datacited by 68
  2. 2019Bit-Swap: Recursive Bits-Back Coding for Lossless Compression with Hierarchical Latent Variablescited by 51
  3. 2019HiLLoC: Lossless Image Compression with Hierarchical Latent Variable Modelscited by 36
  4. 2020IDF++: Analyzing and Improving Integer Discrete Flows for Lossless Compressioncited by 35
  5. 2019Compression with Flows via Local Bits-Back Codingcited by 34
  6. 2020General Invertible Transformations for Flow-based Generative Modelingcited by 4

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 0; 2024: 1.

2 papers.

  1. 2022Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioningcited by 362
  2. 2024Discrete Modeling via Boundary Conditional Diffusion Processescited by 0