检索结果-内蒙古大学图书馆

entropy Optimized Deep Feature Compression

IEEE SIGNAL PROCESSING LETTERS 2021年 28卷 324-328页

作者： Niu, Benben Cao, Xiaoran Wei, Ziwei He, Yun Tsinghua Univ Dept Elect Engn Beijing 100084 Peoples R China Tsinghua Univ Beijing Natl Res Ctr Informat Sci & Technol Beijing 100084 Peoples R China

This letter focuses on the compression of deep features. With the rapid expansion of deep feature data in various CNN-based analysis and processing tasks, the demand for efficient compression continues to increase. Product quantization (PQ) is widely used in the compact expression of features. In the quantization process, feature vectors are mapped into fixed-length codes based on a pre-trained codebook. However, PQ is not specifically designed for data compression, and the fixed-length codes are not suitable for further compression such as entropy coding. In this letter, we propose an entropy-optimized compression scheme for deep features. By introducing entropy into the loss function in the training process of quantization, the quantization and entropy coding modules are jointly optimized to minimize the total coding cost. We evaluate the proposed methods in retrieval tasks. Compared with fixed-length coding, the proposed scheme can be generally combined with PQ and its extended method and can achieve a better compression performance consistently.

关键词： Quantization (signal) Indexes entropy coding Task analysis entropy Measurement Signal processing algorithms entropy coding feature vector joint optimization product quantization

来源：评论

学校读者我要写书评

暂无评论

Aligned Intra Prediction and Hyper Scale Decoder Under Multistage Context Model for JPEG AI

引用

IEEE SIGNAL PROCESSING LETTERS 2024年 31卷 1545-1549页

作者： Li, Shuai Gao, Yanbo Li, Chuankun Yuan, Hui Shandong Univ Sch Control Sci & Engn Jinan 250100 Peoples R China Shandong Univ Sch Software Jinan 250100 Peoples R China North Univ China State Key Lab Dynam Testing Technol Taiyuan 030051 Peoples R China North Univ China Sch Informat & Commun Engn Taiyuan 030051 Peoples R China

Learning-based image compression has raised increasing interests in the last few years. Currently, Joint Photographic Experts Group (JPEG) is working on the standardization of learning-based image compression as JPEG AI. It adopts a deep neural network based encoder-decoder architecture with hyperprior based probability formulation for entropy coding. JPEG AI currently contains two coding profiles: Base Operating Point (BaseOP) and High Operating Point (HighOP). Among the various techniques developed in JPEG AI, Multistage Context Model (MCM) was adopted as the context model to perform intra prediction in HighOP. It transforms the spatially progressive context prediction into sub-image feature prediction among channels via feature down-shuffling. However, in this prediction process, sub-image features are not spatially aligned to each other, and directly using the neighboring sub-image features cannot provide accurate prediction. Moreover, the distributions of residual features generated by MCM are also not consistent with that of the hyper scale decoder, which is used to construct the probability model in the entropy coding of residual features, leading to suboptimal residual coding. To address the above problems, we propose an Aligned Intra Prediction (AIP) and Aligned Hyper Scale Decoder (AHSD) under MCM for JPEG AI coding. AIP aligns the reference sub-image features to the to-be-predicted feature in MCM. AHSD further generates hyper scale features with matched distributions to the residual features. Experimental results demonstrate that the proposed method improves the coding performance by 1.3% in terms of BD-rate saving over the JPEG AI reference software.

关键词： Decoding Transform coding Image coding Convolution Artificial intelligence Image reconstruction entropy coding Image compression JPEG AI multistage context model (MCM) hyper scale decoder

来源：评论

学校读者我要写书评

暂无评论

Efficient, low-complexity image coding with a set-partitioning embedded block coder

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2004年第11期14卷 1219-1235页

作者： Pearlman, WA Islam, A Nagaraj, N Said, A Rensselaer Polytech Inst Dept Elect Comp & Syst Engn Troy NY 12180 USA Nokia Inc Irvington TX 75039 USA GE John F Welch Technol Ctr Bangalore 560066 Karnataka India Hewlett Packard Labs Palo Alto CA 94304 USA

We propose an embedded, block-based, image wavelet transform coding algorithm of low complexity. It uses a recursive set-partitioning procedure to sort subsets of wavelet coefficients by maximum magnitude with respect to thresholds that are integer powers of two. It exploits two fundamental characteristics of an image transform-the well-defined hierarchical structure, and energy clustering in frequency and in space. The two partition strategies allow for versatile and efficient coding of several image transform structures, including dyadic, blocks inside subbands, wavelet packets, and discrete cosine transform (DCT). We describe the use of this coding algorithm in several implementations, including reversible (lossless) coding and its adaptation for color images, and show extensive comparisons with other state-of-the-art coders, such as set partitioning in hierarchical trees (SPIHT) and JPEG2000. We conclude that this algorithm, in addition to being very flexible, retains all the desirable features of these algorithms and is highly competitive to them in compression efficiency.

关键词： color image coding embedded coding entropy coding hierarchical coding image coding lossless coding wavelet coding

来源：评论

学校读者我要写书评

暂无评论

Image compression with learned lifting-based DWT and learned tree-based entropy models

引用

MULTIMEDIA SYSTEMS 2023年第6期29卷 3369-3384页

作者： Sahin, Ugur Berk Kamisli, Fatih Middle East Tech Univ Elect & Elect Engn TR-06800 Ankara Turkiye ASELSAN Ankara Turkiye

This paper explores learned image compression based on traditional and learned discrete wavelet transform (DWT) architectures and learned entropy models for coding DWT subband coefficients. A learned DWT is obtained through the lifting scheme with learned nonlinear predict and update filters. Several learned entropy models, with varying computational complexities, are explored to exploit inter- and intra-DWT subband coefficient dependencies, akin to traditional EZW, SPIHT, or EBCOT algorithms. Experimental results show that when the explored learned entropy models are combined with traditional wavelet filters, such as the CDF 9/7 filters, compression performance that far exceeds that of JPEG2000 can be achieved. When the learned entropy models are combined with the learned DWT, compression performance increases further. The computations in the learned DWT and all entropy models, except one, can be simply parallelized, and thus, the systems provide practical encoding and decoding times on GPUs, unlike other DWT-based learned compression systems in the literature.

关键词： Neural networks Image coding Transform coding Wavelet transforms entropy coding JPEG2000

来源：评论

学校读者我要写书评

暂无评论

Joint source-channel turbo decoding of entropy-coded sources

引用

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS 2001年第9期19卷 1680-1696页

作者： Guyader, A Fabre, E Guillemot, C Robert, M INRIA IRISA F-35042 Rennes France

We analyze the dependencies between the variables involved in the source and channel coding chain. This analysis is carried out in the framework of Bayesian networks, which provide both an intuitive representation for the global model of the coding chain and a way of deriving joint (soft) decoding algorithms. Three sources of dependencies are involved in the chain: 1) the source model, a Markov chain of symbols;2) the source coder model, based on a variable length code (VLC), for example a Huffman code;and 3) the channel coder, based on a convolutional error correcting code. Joint decoding relying on the hidden Markov model (HMM) of the global coding chain is intractable, except in trivial cases. We advocate instead an iterative procedure inspired from serial turbo codes, in which the three models of the coding chain are used alternately. This idea of using separately each factor of a big product model inside an iterative procedure usually requires the presence of an interleaver between successive components. We show that only one interleaver is necessary here, placed between the source coder and the channel coder. The decoding scheme we propose can be viewed as a turbo algorithm using alternately the intersymbol correlation due to the Markov source and the redundancy introduced by the channel code. The intermediary element, the source coder model, is used as a translator of soft information from the bit clock to the symbol clock.

关键词： Bayesian network data compression entropy coding iterative decoding joint source-channel decoding probabilistic inference soft decoding turbo code variable length code

来源：评论

学校读者我要写书评

暂无评论

Learned Image Compression With Gaussian-Laplacian-Logistic Mixture Model and Concatenated Residual Modules

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2023年 32卷 2063-2076页

作者： Fu, Haisheng Liang, Feng Lin, Jianping Li, Bing Akbari, Mohammad Liang, Jie Zhang, Guohe Liu, Dong Tu, Chengjie Han, Jingning Xi An Jiao Tong Univ Sch Microelect Xian 710049 Peoples R China Univ Sci & Technol China CAS Key Lab Technol Geospatial Informat Proc & App Hefei 230027 Peoples R China Simon Fraser Univ Sch Engn Sci Burnaby BC V5A 1S6 Canada Tencent Technol Shenzhen 518052 Peoples R China Google Inc Mountain View CA 94043 USA

Recently deep learning-based image compression methods have achieved significant achievements and gradually outperformed traditional approaches including the latest standard Versatile Video coding (VVC) in both PSNR and MS-SSIM metrics. Two key components of learned image compression are the entropy model of the latent representations and the encoding/decoding network architectures. Various models have been proposed, such as autoregressive, softmax, logistic mixture, Gaussian mixture, and Laplacian. Existing schemes only use one of these models. However, due to the vast diversity of images, it is not optimal to use one model for all images, even different regions within one image. In this paper, we propose a more flexible discretized Gaussian-Laplacian-Logistic mixture model (GLLMM) for the latent representations, which can adapt to different contents in different images and different regions of one image more accurately and efficiently, given the same complexity. Besides, in the encoding/decoding network design part, we propose a concatenated residual blocks (CRB), where multiple residual blocks are serially connected with additional shortcut connections. The CRB can improve the learning ability of the network, which can further improve the compression performance. Experimental results using the Kodak, Tecnick-100 and Tecnick-40 datasets show that the proposed scheme outperforms all the leading learning-based methods and existing compression standards including VVC intra coding (4:4:4 and 4:2:0) in terms of the PSNR and MS-SSIM. The source code is available at https://***/fengyurenpingsheng.

关键词： Image coding entropy entropy coding Decoding Correlation Context modeling Complexity theory Deep learning-based image compression entropy coding Gaussian mixture model residual network

来源：评论

学校读者我要写书评

暂无评论

ADAPTIVE entropy-CODED PREDICTIVE VECTOR QUANTIZATION OF IMAGES

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 1992年第3期40卷 633-644页

作者： MODESTINO, JW KIM, YH Electrical Computer and Systems Engineering Department Rensselaer Polytechnic Institute Troy NY USA

We consider 2-D predictive vector quantization (PVQ) of images subject to an entropy constraint and demonstrate the substantial performance improvements over existing unconstrained approaches. Furthermore, we describe a simple adaptive buffer-instrumented implementation of this 2-D entropy-coded PVQ scheme which can accommodate the associated variable-length entropy coding while completely eliminating buffer overflow/underflow problems at the expense of only a slight degradation in performance. This scheme, called 2-D PVQ/AECQ, is shown to result in excellent rate-distortion performance and impressive quality reconstructions on real-world images. Indeed, the real-world coding results shown here demonstrate little distortion at rates as low as 0.5 b/pixel.

关键词： Vector quantization Rate-distortion Image coding Books Statistics Pixel entropy coding Degradation Image reconstruction Encoding

来源：评论

学校读者我要写书评

暂无评论

Learned Lossless Image Compression Through Interpolation With Low Complexity

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2023年第12期33卷 7832-7841页

作者： Kamisli, Fatih Middle East Tech Univ Dept Elect & Elect Engn TR-06800 Ankara Turkiye

With the increasing popularity of deep learning in image processing, many learned lossless image compression methods have been proposed recently. One group of algorithms are based on scale-based auto-regressive models and can provide competitive compression performance while also allowing easily parallelized computations and short encoding/decoding times. However, they use large neural networks and have high computational requirements. This paper presents an interpolation based learned lossless image compression method which falls in the scale-based auto-regressive models group. The method achieves compression performance better than or on par with the recent scale-based auto-regressive models, yet requires more than 10x less neural network parameters (0.19M) and encoding/decoding computation complexity. These achievements are due to the contributions/findings in the overall system and neural network architecture design, such as sharing interpolator neural networks across different scales, using separate neural networks for different parameters of the probability distribution model and performing the processing in the YCoCg-R color space instead of the RGB color space.

关键词： Image compression artificial neural networks entropy coding lossless compression

来源：评论

学校读者我要写书评

暂无评论

L_∞ constrained high-fidelity image compression via adaptive context modeling

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2000年第4期9卷 536-542页

作者： Wu, XL Bao, P Univ Western Ontario Dept Comp Sci London ON N6A 5B7 Canada Hong Kong Polytech Univ Dept Comp Hong Kong Hong Kong Peoples R China

In this paper, vee study high-fidelity image compression with a given tight L-infinity bound. We propose some practical adaptive context modeling techniques to correct prediction biases caused by quantizing prediction residues, a problem common to the existing DPCM-type predictive near-lossless image coders. By incorporating the proposed techniques into the near-lossless version of CALIC that is considered by many as state-of-the-art algorithm, me mere able to increase its PSNR by 1 dB or more and/or reduce its bit rate by 10% or more. More encouragingly, at bit rates around 1.25 bpp or higher, our method obtained competitive PSNR results against the best L-2-based wavelet coders, while obtaining much smaller L-infinity bound.

关键词： context modeling of images entropy coding near-lossless image compression predictive coding trellis quantization

来源：评论

学校读者我要写书评

暂无评论

Exploiting Intra-Slice and Inter-Slice Redundancy for Learning-Based Lossless Volumetric Image Compression

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2022年 31卷 1697-1707页

作者： Chen, Zhenghao Gu, Shuhang Lu, Guo Xu, Dong Univ Sydney Sch Elect & Informat Engn Sydney NSW 2006 Australia Beijing Inst Technol Sch Comp Sci & Technol Beijing 100811 Peoples R China

3D volumetric image processing has attracted increasing attention in the last decades, in which one major research area is to develop efficient lossless volumetric image compression techniques to better store and transmit such images with massive amount of information. In this work, we propose the first end-to-end optimized learning framework for losslessly compressing 3D volumetric data. Our approach builds upon a hierarchical compression scheme by additionally introducing the intra-slice auxiliary features and estimating the entropy model based on both intra-slice and inter-slice latent priors. Specifically, we first extract the hierarchical intra-slice auxiliary features through multi-scale feature extraction modules. Then, an Intra-slice and Inter-slice Conditional entropy coding module is proposed to fuse the intra-slice and inter-slice information from different scales as the context information. Based on such context information, we can predict the distributions for both intra-slice auxiliary features and the slice images. To further improve the lossless compression performance, we also introduce two new gating mechanisms called Intra-Gate and Inter-Gate to generate the optimal feature representations for better information fusion. Eventually, we can produce the bitstream for losslessly compressing volumetric images based on the estimated entropy model. Different from the existing lossless volumetric image codecs, our end-to-end optimized framework jointly learns both intra-slice auxiliary features at different scales for each slice and inter-slice latent features from previously encoded slices for better entropy estimation. The extensive experimental results indicate that our framework outperforms the state-of-the-art hand-crafted lossless volumetric image codecs (e.g., JP3D) and the learning-based lossless image compression method on four volumetric image benchmarks for losslessly compressing both 3D Medical Images and Hyper-Spectral Images.

关键词： Image coding Feature extraction entropy entropy coding Redundancy Three-dimensional displays Magnetic resonance imaging Volumetric image compression medical image compression hyper-spectral image compression

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：