English
Related papers

Related papers: Unified Multivariate Gaussian Mixture for Efficien…

200 papers

We propose a novel algorithm for quantizing continuous latent representations in trained models. Our approach applies to deep probabilistic models, such as variational autoencoders (VAEs), and enables both data and model compression. Unlike…

Image and Video Processing · Electrical Eng. & Systems 2020-09-09 Yibo Yang , Robert Bamler , Stephan Mandt

Many common types of data can be represented as functions that map coordinates to signal values, such as pixel locations to RGB values in the case of an image. Based on this view, data can be compressed by overfitting a compact neural…

Machine Learning · Computer Science 2023-10-31 Zongyu Guo , Gergely Flamich , Jiajun He , Zhibo Chen , José Miguel Hernández-Lobato

Variational autoencoders often assume isotropic Gaussian priors and mean-field posteriors, hence do not exploit structure in scenarios where we may expect similarity or consistency across latent variables. Gaussian process variational…

Machine Learning · Statistics 2020-11-17 Metod Jazbec , Michael Pearce , Vincent Fortuin

We present a novel systematic theoretical framework to analyze the rate-distortion (R-D) limits of learned image compression. While recent neural codecs have achieved remarkable empirical results, their distance from the…

Information Theory · Computer Science 2026-01-15 Changshuo Wang , Zijian Liang , Kai Niu , Ping Zhang

This paper studies the problem of estimating the covariance of a collection of vectors using only highly compressed measurements of each vector. An estimator based on back-projections of these compressive samples is proposed and analyzed. A…

Machine Learning · Statistics 2019-01-16 Martin Azizyan , Akshay Krishnamurthy , Aarti Singh

Perceptual optimization is widely recognized as essential for neural compression, yet balancing the rate-distortion-perception tradeoff remains challenging. This difficulty is especially pronounced in video compression, where frame-wise…

Image and Video Processing · Electrical Eng. & Systems 2025-10-14 Zongyu Guo , Zhaoyang Jia , Jiahao Li , Xiaoyi Zhang , Bin Li , Yan Lu

Deep learning models have significantly improved the visual quality and accuracy on compressive sensing recovery. In this paper, we propose an algorithm for signal reconstruction from compressed measurements with image priors captured by a…

Machine Learning · Computer Science 2020-03-20 Shaojie Xu , Sihan Zeng , Justin Romberg

This paper proposes using a Gaussian mixture model as a prior, for solving two image inverse problems, namely image deblurring and compressive imaging. We capitalize on the fact that variable splitting algorithms, like ADMM, are able to…

Computer Vision and Pattern Recognition · Computer Science 2016-05-24 Afonso M. Teodoro , José M. Bioucas-Dias , Mário A. T. Figueiredo

This paper explores image caption generation using conditional variational auto-encoders (CVAEs). Standard CVAEs with a fixed Gaussian prior yield descriptions with too little variability. Instead, we propose two models that explicitly…

Computer Vision and Pattern Recognition · Computer Science 2017-11-21 Liwei Wang , Alexander G. Schwing , Svetlana Lazebnik

The extensive adoption of Deep Neural Networks has led to their increased utilization in challenging scientific visualization tasks. Recent advancements in building compressed data models using implicit neural representations have shown…

Machine Learning · Computer Science 2025-10-20 Abhay Kumar Dwivedi , Shanu Saklani , Soumya Dutta

Non-linear latent variable models have become increasingly popular in a variety of applications. However, there has been little study on theoretical properties of these models. In this article, we study rates of posterior contraction in…

Statistics Theory · Mathematics 2017-01-27 Shuang Zhou , Debdeep Pati , Anirban Bhattacharya , David Dunson

Sparse representation leads to an efficient way to approximately recover a signal by the linear composition of a few bases from a learnt dictionary, based on which various successful applications have been achieved. However, in the scenario…

Computer Vision and Pattern Recognition · Computer Science 2018-05-04 Xiang Zhang , Jiarui Sun , Siwei Ma , Zhouchen Lin , Jian Zhang , Shiqi Wang , Wen Gao

Graphical models are commonly used tools for modeling multivariate random variables. While there exist many convenient multivariate distributions such as Gaussian distribution for continuous data, mixed data with the presence of discrete…

Machine Learning · Statistics 2014-04-30 Jianqing Fan , Han Liu , Yang Ning , Hui Zou

Models with a large number of latent variables are often used to fully utilize the information in big or complex data. However, they can be difficult to estimate using standard approaches, and variational inference methods are a popular…

Methodology · Statistics 2021-04-20 Rubén Loaiza-Maya , Michael Stanley Smith , David J. Nott , Peter J. Danaher

We study linear models under heavy-tailed priors from a probabilistic viewpoint. Instead of computing a single sparse most probable (MAP) solution as in standard deterministic approaches, the focus in the Bayesian compressed sensing…

Computer Vision and Pattern Recognition · Computer Science 2014-03-05 George Papandreou , Alan Yuille

We propose a unified compression framework that uses generative adversarial networks (GAN) to compress image and speech signals. The compressed signal is represented by a latent vector fed into a generator network which is trained to…

Signal Processing · Electrical Eng. & Systems 2019-12-10 Bowen Liu , Ang Cao , Hun-seok Kim

Despite progress in training neural networks for lossy image compression, current approaches fail to maintain both perceptual quality and abstract features at very low bitrates. Encouraged by recent success in learning discrete…

Machine Learning · Computer Science 2020-10-19 Will Williams , Sam Ringer , Tom Ash , John Hughes , David MacLeod , Jamie Dougherty

We present the first unified framework for rate-distortion-optimized compression and segmentation of 3D Gaussian Splatting (3DGS). While 3DGS has proven effective for both real-time rendering and semantic scene understanding, prior works…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Yu-Jen Tseng , Chia-Hao Kao , Jing-Zhong Chen , Alessandro Gnutti , Shao-Yuan Lo , Yen-Yu Lin , Wen-Hsiao Peng

Variational autoencoders (VAEs) are a powerful class of deep generative latent variable model for unsupervised representation learning on high-dimensional data. To ensure computational tractability, VAEs are often implemented with a…

Machine Learning · Computer Science 2020-06-09 Alex Campbell , Pietro Liò

This paper proposes a new high dimensional regression method by merging Gaussian process regression into a variational autoencoder framework. In contrast to other regression methods, the proposed method focuses on the case where output…

Computer Vision and Pattern Recognition · Computer Science 2019-08-13 YoungJoon Yoo , Sangdoo Yun , Hyung Jin Chang , Yiannis Demiris , Jin Young Choi