iFlow: Numerically Invertible Flows for Efficient Lossless Compression via a Uniform Coder

• URL: http://arxiv.org/abs/2111.00965v1
• Date: Mon, 1 Nov 2021 14:15:58 GMT
• Title: iFlow: Numerically Invertible Flows for Efficient Lossless Compression via a Uniform Coder
• Authors: Shifeng Zhang, Ning Kang, Tom Ryder and Zhenguo Li
• Abstract summary: iFlow is a new method for achieving efficient lossless compression. iFlow achieves state-of-the-art compression ratios and is $5times$ quicker than other high-performance schemes.
• Score: 38.297114268193
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: It was estimated that the world produced $59 ZB$ ($5.9 \times 10^{13} GB$) of data in 2020, resulting in the enormous costs of both data storage and transmission. Fortunately, recent advances in deep generative models have spearheaded a new class of so-called "neural compression" algorithms, which significantly outperform traditional codecs in terms of compression ratio. Unfortunately, the application of neural compression garners little commercial interest due to its limited bandwidth; therefore, developing highly efficient frameworks is of critical practical importance. In this paper, we discuss lossless compression using normalizing flows which have demonstrated a great capacity for achieving high compression ratios. As such, we introduce iFlow, a new method for achieving efficient lossless compression. We first propose Modular Scale Transform (MST) and a novel family of numerically invertible flow transformations based on MST. Then we introduce the Uniform Base Conversion System (UBCS), a fast uniform-distribution codec incorporated into iFlow, enabling efficient compression. iFlow achieves state-of-the-art compression ratios and is $5\times$ quicker than other high-performance schemes. Furthermore, the techniques presented in this paper can be used to accelerate coding time for a broad class of flow-based algorithms.

Related papers

• Ultra Dual-Path Compression For Joint Echo Cancellation And Noise Suppression [38.09558772881095]
  Under fixed compression ratios, dual-path compression combining both the time and frequency methods will give further performance improvement. Proposed models show competitive performance compared with fast FullSubNet and DeepNetFilter.
  arXiv  Detail & Related papers  (2023-08-21T21:36:56Z)
• DiffRate : Differentiable Compression Rate for Efficient Vision Transformers [98.33906104846386]
  Token compression aims to speed up large-scale vision transformers (e.g. ViTs) by pruning (dropping) or merging tokens. DiffRate is a novel token compression method that has several appealing properties prior arts do not have.
  arXiv  Detail & Related papers  (2023-05-29T10:15:19Z)
• Unrolled Compressed Blind-Deconvolution [77.88847247301682]
  sparse multichannel blind deconvolution (S-MBD) arises frequently in many engineering applications such as radar/sonar/ultrasound imaging. We propose a compression method that enables blind recovery from much fewer measurements with respect to the full received signal in time.
  arXiv  Detail & Related papers  (2022-09-28T15:16:58Z)
• Deep Lossy Plus Residual Coding for Lossless and Near-lossless Image Compression [85.93207826513192]
  We propose a unified and powerful deep lossy plus residual (DLPR) coding framework for both lossless and near-lossless image compression. We solve the joint lossy and residual compression problem in the approach of VAEs. In the near-lossless mode, we quantize the original residuals to satisfy a given $ell_infty$ error bound.
  arXiv  Detail & Related papers  (2022-09-11T12:11:56Z)
• Lossless Compression with Probabilistic Circuits [42.377045986733776]
  Probabilistic Circuits (PCs) are a class of neural networks involving $|p|$ computational units. We derive efficient encoding and decoding schemes that both have time complexity $mathcalO (log(D) cdot |p|)$, where a naive scheme would have linear costs in $D$ and $|p|$. By scaling up the traditional PC structure learning pipeline, we achieved state-of-the-art results on image datasets such as MNIST.
  arXiv  Detail & Related papers  (2021-11-23T03:30:22Z)
• ANFIC: Image Compression Using Augmented Normalizing Flows [16.161901495436233]
  This paper introduces an end-to-end learned image compression system, termed ANFIC, based on Augmented Normalizing Flows (ANF) In terms of PSNR-RGB, ANFIC performs comparably to or better than the state-of-the-art learned image compression. In particular, ANFIC achieves the state-of-the-art performance, when extended with conditional convolution for variable rate compression with a single model.
  arXiv  Detail & Related papers  (2021-07-18T15:02:31Z)
• Towards Compact CNNs via Collaborative Compression [166.86915086497433]
  We propose a Collaborative Compression scheme, which joints channel pruning and tensor decomposition to compress CNN models. We achieve 52.9% FLOPs reduction by removing 48.4% parameters on ResNet-50 with only a Top-1 accuracy drop of 0.56% on ImageNet 2012.
  arXiv  Detail & Related papers  (2021-05-24T12:07:38Z)
• iVPF: Numerical Invertible Volume Preserving Flow for Efficient Lossless Compression [21.983560104199622]
  It is nontrivial to store rapidly growing big data nowadays, which demands high-performance compression techniques. We propose Numerical Invertible Volume Preserving Flow (iVPF) computation which is derived from the general volume preserving flows. Experiments on various datasets show that the algorithm based on iVPF achieves state-of-the-art compression ratio over lightweight compression algorithms.
  arXiv  Detail & Related papers  (2021-03-30T09:50:58Z)
• PowerGossip: Practical Low-Rank Communication Compression in Decentralized Deep Learning [62.440827696638664]
  We introduce a simple algorithm that directly compresses the model differences between neighboring workers. Inspired by the PowerSGD for centralized deep learning, this algorithm uses power steps to maximize the information transferred per bit.
  arXiv  Detail & Related papers  (2020-08-04T09:14:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.