iVPF: Numerical Invertible Volume Preserving Flow for Efficient Lossless Compression

By Shifeng Zhang, Chen Zhang, Ning Kang, Zhenguo Li. 2021

48 citations recorded by the source corpus.

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 flow based models are desirable in allowing exact data likelihood optimisation with bijective mappings. However, common continuous flows are in contradiction with the discreteness of coding schemes, which requires either 1) imposing strict constraints on flow models that degrades the performance or 2) coding numerous bijective mapping errors which reduces the efficiency. In this paper, we investigate volume preserving flows for lossless compression and show that a bijective mapping without error is possible. We propose Numerical Invertible Volume Preserving Flow (iVPF) which is derived from the general volume preserving flows. By introducing novel computation algorithms on flow models, an exact bijective mapping is achieved without any numerical error. We also propose a lossless compression algorithm based on iVPF. Experiments on various datasets show that the algorithm based on iVPF achieves state-of-the-art compression ratio over lightweight compression algorithms.

Subfields: Artificial Intelligence, Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Jun Zhu
2. Chongxuan Li
3. Jianfei Chen
4. Siyu Wang
5. Zhenguo Li
6. Shifeng Zhang
7. Ning Kang
8. Tom Ryder

In Computer Graphics and Computer-Aided Design

1. Jun Zhu

In Computer Vision and Pattern Recognition

1. Jun Zhu
2. Chongxuan Li
3. Zhenguo Li
4. Jianfei Chen
5. Siyu Wang
6. Shifeng Zhang
7. Ning Kang
8. Tom Ryder

Citations in the corpus

• Fast Lossless Neural Compression with Integer-Only Discrete Flows (2022, methodology): “LBB iVPF iFlow IDF IODF (Zhang et al., 2021c;b).”
• iFlow: Numerically Invertible Flows for Efficient Lossless Compression via a Uniform Coder (2021, methodology): “As such, transformations would require discretization, resulting in a loss of information [41, 3].”