paper-with-me

Papers

Integer Discrete Flows and Lossless Compression

2019-05-17 · NeurIPS 2019 12 · Emiel Hoogeboom, Jorn W. T. Peters, Rianne van den Berg, Max Welling

Lossless compression methods shorten the expected representation size of data without loss of information, using a statistical model. Flow-based models are attractive in this setting because they admit exact likelihood optimization, which is equivalent to minimizing the expected number of bits per message. However, conventional flows assume continuous data, which may lead to reconstruction errors when quantized for compression. For that reason, we introduce a flow-based generative model for ordinal discrete data called Integer Discrete Flow (IDF): a bijective integer map that can learn rich transformations on high-dimensional data. As building blocks for IDFs, we introduce a flexible transformation layer called integer discrete coupling. Our experiments show that IDFs are competitive with other flow-based generative models. Furthermore, we demonstrate that IDF based compression achieves state-of-the-art lossless compression rates on CIFAR10, ImageNet32, and ImageNet64. To the best of our knowledge, this is the first lossless compression method that uses invertible neural networks.

📄 PDF Abstract BibTeX arXiv:1905.07376

Code (2)

jornpeters/integer_discrete_flows 공식 구현 pytorch
tuatruog/astrocompress pytorch

Similar Papers 제목 키워드 기반

IDF++: Analyzing and Improving Integer Discrete Flows for Lossless Compression

2020-06-22 · ICLR 2021 1 · Rianne van den Berg, Alexey A. Gritsenko, Mostafa Dehghani, Casper Kaae Sønderby 외

In this paper we analyse and improve integer discrete flows for lossless compression. Integer discrete flows are a recently proposed class of models that learn invertible transformations for integer-valued random variabl…

Quantization

Fast Lossless Neural Compression with Integer-Only Discrete Flows

2022-06-17 · Siyu Wang, Jianfei Chen, Chongxuan Li, Jun Zhu 외

By applying entropy codecs with learned data distributions, neural compressors have significantly outperformed traditional codecs in terms of compression ratio. However, the high inference latency of neural networks hind…

Quantization

iVPF: Numerical Invertible Volume Preserving Flow for Efficient Lossless Compression

2021-03-30 · CVPR 2021 1 · Shifeng Zhang, Chen Zhang, Ning Kang, Zhenguo Li

It is nontrivial to store rapidly growing big data nowadays, which demands high-performance lossless compression techniques. Likelihood-based generative models have witnessed their success on lossless compression, where …

iVPF: Numerical Invertible Volume Preserving Flow for Efficient Lossless Compression

2021-09-05 · CVPR 2021 9 · Changsu Cao, Jiaqi Hu, Wengang Zhang, Xusheng Xu 외

It is nontrivial to store rapidly growing big data nowadays, which demands high-performance lossless compression techniques. Likelihood-based generative models have witnessed their success on lossless compression, where …

Discrete Denoising Flows

2021-07-24 · ICML Workshop INNF 2021 7 · Alexandra Lindt, Emiel Hoogeboom

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 likel…

Denoising