Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression

• URL: http://arxiv.org/abs/2203.10897v1
• Date: Mon, 21 Mar 2022 11:44:17 GMT
• Title: Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression
• Authors: Xiaosu Zhu, Jingkuan Song, Lianli Gao, Feng Zheng, Heng Tao Shen
• Abstract summary: latent variables with priors and hyperpriors is an essential problem in variational image compression. We find inter-correlations and intra-correlations exist when observing latent variables in a vectorized perspective. Our model has better rate-distortion performance and an impressive $3.18times$ compression speed up.
• Score: 151.3826781154146
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Modeling latent variables with priors and hyperpriors is an essential problem in variational image compression. Formally, trade-off between rate and distortion is handled well if priors and hyperpriors precisely describe latent variables. Current practices only adopt univariate priors and process each variable individually. However, we find inter-correlations and intra-correlations exist when observing latent variables in a vectorized perspective. These findings reveal visual redundancies to improve rate-distortion performance and parallel processing ability to speed up compression. This encourages us to propose a novel vectorized prior. Specifically, a multivariate Gaussian mixture is proposed with means and covariances to be estimated. Then, a novel probabilistic vector quantization is utilized to effectively approximate means, and remaining covariances are further induced to a unified mixture and solved by cascaded estimation without context models involved. Furthermore, codebooks involved in quantization are extended to multi-codebooks for complexity reduction, which formulates an efficient compression procedure. Extensive experiments on benchmark datasets against state-of-the-art indicate our model has better rate-distortion performance and an impressive $3.18\times$ compression speed up, giving us the ability to perform real-time, high-quality variational image compression in practice. Our source code is publicly available at \url{https://github.com/xiaosu-zhu/McQuic}.

Related papers

• Fast constrained sampling in pre-trained diffusion models [77.21486516041391]
  Diffusion models have dominated the field of large, generative image models. We propose an algorithm for fast-constrained sampling in large pre-trained diffusion models.
  arXiv  Detail & Related papers  (2024-10-24T14:52:38Z)
• Variable-Rate Learned Image Compression with Multi-Objective Optimization and Quantization-Reconstruction Offsets [8.670873561640903]
  This paper follows the traditional approach to vary a single quantization step size to perform uniform quantization of all latent tensor elements. Three modifications are proposed to improve the variable rate compression performance. The achieved variable rate compression results indicate negligible or minimal compression performance loss compared to training multiple models.
  arXiv  Detail & Related papers  (2024-02-29T07:45:02Z)
• Activations and Gradients Compression for Model-Parallel Training [85.99744701008802]
  We study how simultaneous compression of activations and gradients in model-parallel distributed training setup affects convergence. We find that gradients require milder compression rates than activations. Experiments also show that models trained with TopK perform well only when compression is also applied during inference.
  arXiv  Detail & Related papers  (2024-01-15T15:54:54Z)
• Retraining-free Model Quantization via One-Shot Weight-Coupling Learning [41.299675080384]
  Mixed-precision quantization (MPQ) is advocated to compress the model effectively by allocating heterogeneous bit-width for layers. MPQ is typically organized into a searching-retraining two-stage process. In this paper, we devise a one-shot training-searching paradigm for mixed-precision model compression.
  arXiv  Detail & Related papers  (2024-01-03T05:26:57Z)
• Compound Batch Normalization for Long-tailed Image Classification [77.42829178064807]
  We propose a compound batch normalization method based on a Gaussian mixture. It can model the feature space more comprehensively and reduce the dominance of head classes. The proposed method outperforms existing methods on long-tailed image classification.
  arXiv  Detail & Related papers  (2022-12-02T07:31:39Z)
• Post-Training Quantization for Cross-Platform Learned Image Compression [15.67527732099067]
  It has been witnessed that learned image compression has outperformed conventional image coding techniques. One of the most critical issues that need to be considered is the non-deterministic calculation. We propose to solve this problem by introducing well-developed post-training quantization.
  arXiv  Detail & Related papers  (2022-02-15T15:41:12Z)
• Implicit Neural Representations for Image Compression [103.78615661013623]
  Implicit Neural Representations (INRs) have gained attention as a novel and effective representation for various data types. We propose the first comprehensive compression pipeline based on INRs including quantization, quantization-aware retraining and entropy coding. We find that our approach to source compression with INRs vastly outperforms similar prior work.
  arXiv  Detail & Related papers  (2021-12-08T13:02:53Z)
• Compressing gradients by exploiting temporal correlation in momentum-SGD [17.995905582226463]
  We analyze compression methods that exploit temporal correlation in systems with and without error-feedback. Experiments with the ImageNet dataset demonstrate that our proposed methods offer significant reduction in the rate of communication. We prove the convergence of SGD under an expected error assumption by establishing a bound for the minimum gradient norm.
  arXiv  Detail & Related papers  (2021-08-17T18:04:06Z)
• Asymmetric Gained Deep Image Compression With Continuous Rate Adaptation [12.009880944927069]
  We propose a continuously rate adjustable learned image compression framework, Asymmetric Gained Variational Autoencoder (AG-VAE) AG-VAE utilizes a pair of gain units to achieve discrete rate adaptation in one single model with a negligible additional computation. Our method achieves comparable quantitative performance with SOTA learned image compression methods and better qualitative performance than classical image codecs.
  arXiv  Detail & Related papers  (2020-03-04T11:42:05Z)
• On Biased Compression for Distributed Learning [55.89300593805943]
  We show for the first time that biased compressors can lead to linear convergence rates both in the single node and distributed settings. We propose several new biased compressors with promising theoretical guarantees and practical performance.
  arXiv  Detail & Related papers  (2020-02-27T19:52:24Z)

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.