检索结果-内蒙古大学图书馆

Saliency Segmentation Oriented deep image compression With Novel Bit Allocation

IEEE TRANSACTIONS ON image PROCESSING 2025年 34卷 16-29页

作者： Li, Yuan Gao, Wei Li, Ge Ma, Siwei Peking Univ Shenzhen Grad Sch Sch Elect & Comp Engn Guangdong Prov Key Lab Ultra High Definit Immers M Shenzhen 518055 Peoples R China Peng Cheng Lab Shenzhen 518066 Peoples R China Peking Univ Natl Engn Res Ctr Visual Technol Sch Comp Sci Beijing 100871 Peoples R China

image compression distortion can cause performance degradation of machine analysis tasks, therefore recent years have witnessed fast progress in developing deep image compression methods optimized for machine perception. However, the investigation still lacks for saliency segmentation. First, in this paper we propose a deep compression network increasing local signal fidelity of important image pixels for saliency segmentation, which is different from existing methods utilizing the analysis network loss for backward propagation. By this means, these two types of networks can be decoupled to improve the compatibility of proposed compression method for diverse saliency segmentation networks. Second, pixel-level bit weights are modeled with probability distribution in the proposed bit allocation method. The ascending cosine roll-down (ACRD) function allocates bits to those important pixels, which fits the essence that saliency segmentation can be regarded as the pixel-level bi-classification task. Third, the compression network is trained without the help of saliency segmentation, where latent representations are decomposed into base and enhancement channels. Base channels are retained in the whole image, while enhancement channels are utilized only for important pixels, and therefore more bits can benefit saliency segmentation via enhancement channels. Extensive experimental results demonstrate that the proposed method can save an average of 10.34% bitrate compared with the state-of-the-art deep image compression method, where the rate-accuracy (R-A) performances are evaluated on sixteen downstream saliency segmentation networks with five conventional SOD datasets. The code will be available at: https://***/OpenAICoding/SaliencyIC and https://***/AkeLiLi/SaliencyIC.

关键词： image coding image segmentation Bit rate Object segmentation Distortion image reconstruction Entropy Training Semantics Degradation deep image compression saliency segmentation novel bit allocation pixel-level image fidelity enhancement

来源：评论

学校读者我要写书评

暂无评论

Quantization-Based Adaptive deep image compression Using Semantic Information

引用

IEEE ACCESS 2023年 11卷 118061-118077页

作者： Lei, Zhongyue Hong, Xuemin Shi, Jianghong Su, Minxian Lin, Chaoheng Xia, Wei Xiamen Univ Sch Informat Xiamen 361005 Peoples R China Xiamen Satellite Positioning Applicat Co Ltd Xiamen 361008 Peoples R China Xiamen Beidou Key Lab Appl Technol Xiamen 361008 Peoples R China Fujian Centerm Informat Co Ltd Fuzhou 350028 Peoples R China

deep image coding (DIC) for hybrid application contexts has recently attracted significant research interest because of its potential to support both human and machine visual tasks. Since the regions of interest (ROI) are different for different application contexts, it is important to design an adaptive image coding mechanism in practical DIC. In this paper, we propose the first quantization-based adaptive DIC framework for hybrid contexts of image reconstruction and classification. This framework can be applied to upgrade existing fixed-rate DIC models into adaptive DIC for hybrid contexts. It consists of two key modules: a semantics-based ROI mask generation module and a module for generating ROI gain and inverse gain matrices. These matrices are used to control the quantization accuracy of different latent vector elements, thereby achieving encoding at different rates while prioritizing the reconstruction quality of the ROI. Moreover, we propose a five-stage training method for the quantization-based adaptive DIC model to optimize the rate-distortion-classification-perception (RDCP) tradeoff. Experiments over a wide rate range show that our method achieves superior RDCP tradeoff performance. Compared to the benchmark scheme BM-CHENG, the proposed algorithm improves the classification accuracy by an average of 15%. The average relative improvements on various metrics, such as natural image quality evaluator (NIQE), learned perceptual image patch similarity (LPIPS), and feature similarity index measure (FSIM), are about 22%, 47%, and 1%, respectively. The proposed algorithm is a promising candidate for fast adaptive coding with low-complexity constraints.

关键词： deep image compression semantic importance adaptive coding hybrid contexts

来源：评论

学校读者我要写书评

暂无评论

Progressive deep image compression for Hybrid Contexts of image Classification and Reconstruction

引用

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS 2023年第1期41卷 72-89页

作者： Lei, Zhongyue Duan, Peng Hong, Xuemin Mota, Joao F. C. Shi, Jianghong Wang, Cheng-Xiang Xiamen Univ Sch Informat Xiamen 361000 Peoples R China Heriot Watt Univ Sch Engn & Phys Sci Edinburgh EH14 4AS Midlothian Scotland Southeast Univ Sch Informat Sci & Engn Natl Mobile Commun Res Lab Nanjing 210096 Jiangsu Peoples R China Purple Mt Labs Nanjing 211111 Peoples R China

Progressive deep image compression (DIC) with hybrid contexts is an under-investigated problem that aims to jointly maximize the utility of a compressed image for multiple contexts or tasks under variable rates. In this paper, we consider the contexts of image reconstruction and classification. We propose a DIC framework, called residual-enhanced mask-based progressive generative coding (RMPGC), designed for explicit control of the performance within the rate-distortion-classification-perception (RDCP) trade-off. Three independent mechanisms are introduced to yield a semantically structured latent representation that can support parameterized control of rate and context adaptation. Experimental results show that the proposed RMPGC outperforms a benchmark DIC scheme using the same generative adversarial nets (GANs) backbone in all six metrics related to classification, distortion, and perception. Moreover, RMPGC is a flexible framework that can be applied to different neural network backbones. Some typical implementations are given and shown to outperform the classic BPG codec and four state-of-the-art DIC schemes in classification and perception metrics, with a slight degradation in distortion metrics. Our proposal of a nonlinear-neural-coded and richly structured latent space makes the proposed DIC scheme well suited for image compression in wireless communications, multi-user broadcasting, and multi-tasking applications.

关键词： deep image compression progressive compression generative image compression image semantics

来源：评论

学校读者我要写书评

暂无评论

HIERARCHICAL FEATURE AGGREGATION NETWORK FOR deep image compression 47

HIERARCHICAL FEATURE AGGREGATION NETWORK FOR DEEP IMAGE COMP...

引用

47th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Li, Wenfeng Du, Zongcai He, Hao Tang, Jie Wu, Gangshan Nanjing Univ State Key Lab Novel Software Technol Nanjing Peoples R China

ISBN: (纸本)9781665405409

Existing CNN-based methods for image compression extract features through serially connected high-to-low (encoder) or low-to-high (decoder) resolution stages, leading to insufficient utilization of hierarchical features. To solve this problem, we present a hierarchical feature aggregation network (HFAN) for generating more informative latent representations. In detail, we propose two strategies, namely inter-stage feature aggregation and intra-stage feature aggregation. The inter-stage feature aggregation integrates multiscale information thereby producing more contextual features. The intra-stage aggregation fuses features within the same stage to enrich representations of one specific resolution. Besides, we incorporate a lightweight pixel-wise attention mechanism to further enhance the discriminative ability of our network. Extensive experiments demonstrate that our HFAN achieves superior performance over state-of-the-art methods without a hyperprior variational autoencoder.

关键词： deep image compression feature aggregation attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Rate-Distortion Optimized Encoding for deep image compression

IEEE OPEN JOURNAL OF CIRCUITS AND SYSTEMS

引用

IEEE OPEN JOURNAL OF CIRCUITS AND SYSTEMS 2021年 2卷 633-647页

作者： Schafer, Michael Pientka, Sophie Pfaff, Jonathan Schwarz, Heiko Marpe, Detlev Wiegand, Thomas Heinrich Hertz Inst Nachrichtentech Berlin GmbH Fraunhofer Inst Telecommun Video Commun & Applicat Dept D-10587 Berlin Germany Heinrich Hertz Inst Nachrichtentech Berlin GmbH Fraunhofer Inst Telecommun D-10587 Berlin Germany Free Univ Berlin Dept Math & Comp Sci D-14195 Berlin Germany Berlin Inst Technol Dept Elect Engn & Comp Sci D-10623 Berlin Germany

deep-learned variational auto-encoders (VAE) have shown remarkable capabilities for lossy image compression. These neural networks typically employ non-linear convolutional layers for finding a compressible representation of the input image. Advanced techniques such as vector quantization, context-adaptive arithmetic coding and variable-rate compression have been implemented in these auto-encoders. Notably, these networks rely on an end-to-end approach, which fundamentally differs from hybrid, block-based video coding systems. Therefore, signal-dependent encoder optimizations have not been thoroughly investigated for VAEs yet. However, rate-distortion optimized encoding heavily determines the compression performance of state-of-the-art video codecs. Designing such optimizations for non-linear, multi-layered networks requires to understand the relationship between the quantization, the bit allocation of the features and the distortion. Therefore, this paper examines the rate-distortion performance of a variable-rate VAE. In particular, one demonstrates that the trained encoder network typically finds features with a near-optimal bit allocation across the channels. Furthermore, one approximates the relationship between distortion and quantization by a higher-order polynomial, whose coefficients can be robustly estimated. Based on these considerations, the authors investigate an encoding algorithm for the Lagrange optimization, which significantly improves the coding efficiency.

关键词： Video coding image coding Vector quantization Nonlinear distortion Bit rate Rate-distortion Signal processing algorithms deep image compression variational auto-encoders rate-distortion optimized encoding non-linear transform coding

来源：评论

学校读者我要写书评

暂无评论

deep image compression with multi-stage representation*

引用

JOURNAL OF VISUAL COMMUNICATION AND image REPRESENTATION 2021年 79卷 103226-103226页

作者： Wang, Zixi Ding, Guiguang Han, Jungong Li, Fan Xi An Jiao Tong Univ Sch Informat & Commun Engn Xian 710049 Peoples R China Tsinghua Univ Sch Software Beijing 100084 Peoples R China Aberystwyth Univ Comp Sci Dept Aberystwyth SY23 3FL Dyfed Wales

While deep learning-based image compression methods have shown impressive coding performance, most existing methods are still in the mire of two limitations: (1) unpredictable compression efficiency gain when adopting convolutional neural networks with different depths, and (2) lack of an accurate model to estimate the entropy during the training process. To address these two problems, in this paper, a deep multi-stage representation based image compression (MSRIC) method is proposed. Owing to this architecture, the detail information of shallow stages and the compact information of deep stages can be utilized for image reconstruction. Furthermore, a data-dependent channel-wised factorized probability model (DCFPM) is adopted to increase the accuracy of entropy estimation. Experimental results indicate that the proposed method guarantees better perceptual performance at a wide range of bit-rates. Also, ablation studies are carried out to validate the above mentioned technologies.

关键词： deep image compression Multi-stage representation Data-dependent probability model Convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

A Study of deep image compression for YUV420 Color Space 44

A Study of Deep Image Compression for YUV420 Color Space

引用

Conference Applications of Digital image Processing XLIV

作者： Ma, Changyue Wang, Zhao Liao, Ru-Ling Ye, Yan Alibaba Grp 4 Wangjing East Garden Beijing Peoples R China Alibaba Grp 525 Almanor Ave Sunnyvale CA USA

ISBN: (数字)9781510645233

ISBN: (纸本)9781510645233;9781510645226

Currently, most deep image compression methods are designed to compress images in RGB color space. However, there are also many images in YUV420 color space and the video coding standards such as H.265/HEVC and H.266/VVC support compression of images in YUV420 color space with their respective Main Still Picture profiles. In this paper, we first study how to adjust the deep compression frameworks designed for images in RGB color space to compress images in YUV420 color space. Then, we study the coding performance impact when we adjust the training distortion weight for YUV channels and compare the experimental results with HEVC and VVC all intra configuration. The proposed approaches are applicable in both image compression and intra coding in video compression.

关键词： deep image compression YUV420 color space YUV training distortion weight

来源：评论

学校读者我要写书评

暂无评论

deep semantic image compression via cooperative network pruning

引用

JOURNAL OF VISUAL COMMUNICATION AND image REPRESENTATION 2023年第1期95卷

作者： Luo, Sihui Fang, Gongfan Song, Mingli Ningbo Univ Ningbo Peoples R China Zhejiang Univ Hangzhou Peoples R China

Incorporating semantic analysis into image compression can significantly reduce the repetitive computation of fundamental semantic analysis in downstream applications such as semantic image retrieval. In this paper, we tackle the semantic image compression task, which embeds semantics in the compressed bitstream. An intuitive solution to this task is joint multi-task training, which generally results in the trade-off of one task to accommodate the other. We thus provide an alternative pilot solution: given a pair of pre-trained teacher networks that specialize in image compression and semantic inference respectively, we first fuse both models to acquire an ensemble model and then leverage cooperative network pruning and retraining to condense the knowledge. Various experiments on five benchmark datasets validate that the proposed method achieves on par and in many cases better performance than the teachers yet comes in a more compact size, and outperforms its multi-task learning and knowledge distillation counterparts.

关键词： deep image compression Network pruning Semantic perception

来源：评论

学校读者我要写书评

暂无评论

Variable Rate deep image compression With Modulated Autoencoder

引用

IEEE SIGNAL PROCESSING LETTERS 2020年第0期27卷 331-335页

作者： Yang, Fei Herranz, Luis van de Weijer, Joost Guitian, Jose A. Iglesias Lopez, Antonio M. Mozerov, Mikhail G. Univ Autonoma Barcelona Comp Vis Ctr E-08193 Barcelona Spain Northwestern Polytech Univ Key Lab Informat Fus Technol Xian 710072 Peoples R China Comp Vis Ctr Barcelona 08193 Spain Comp Sci Dept Barcelona 08193 Spain

Variable rate is a requirement for flexible and adaptable image and video compression. However, deep image compression methods (DIC) are optimized for a single fixed rate-distortion (R-D) tradeoff. While this can be addressed by training multiple models for different tradeoffs, the memory requirements increase proportionally to the number of models. Scaling the bottleneck representation of a shared autoencoder can provide variable rate compression with a single shared autoencoder. However, the R-D performance using this simple mechanism degrades in low bitrates, and also shrinks the effective range of bitrates. To address these limitations, we formulate the problem of variable R-D optimization for DIC, and propose modulated autoencoders (MAEs), where the representations of a shared autoencoder are adapted to the specific R-D tradeoff via a modulation network. Jointly training this modulated autoencoder and the modulation network provides an effective way to navigate the R-D operational curve. Our experiments show that the proposed method can achieve almost the same R-D performance of independent models with significantly fewer parameters.

关键词： deep image compression variable bitrate autoencoder modulated autoencoder

来源：评论

学校读者我要写书评

暂无评论

deep image compression WITH ITERATIVE NON-UNIFORM QUANTIZATION 25

DEEP IMAGE COMPRESSION WITH ITERATIVE NON-UNIFORM QUANTIZATI...

引用

25th IEEE International Conference on image Processing (ICIP)

作者： Cai, Jianrui Zhang, Lei Hong Kong Polytech Univ Dept Comp Hong Kong Peoples R China

ISBN: (纸本)9781479970612

image compression, which aims to represent an image with less storage space, is a classical problem in image processing. Recently, by training an encoder-quantizer-decoder network, deep convolutional neural networks (CNNs) have achieved promising results in image compression. As a non-differentiable part of the compression system, quantizer is hard to be updated during the network training. Most of existing deep image compression methods adopt a uniform rounding function as the quantizer, which however restricts the capability and flexibility of CNNs in compressing complex image structures. In this paper, we present an iterative non-uniform quantization scheme for deep image compression. More specifically, we alternatively optimize the quantizer and encoder-decoder. When the encoder-decoder is fixed, a non-uniform quantizer is optimized based on the distribution of representation features. The encoder-decoder network is then updated by fixing the quantizer. Extensive experiments demonstrate the superior PSNR index of the proposed method to existing deep compressors and JPEG2000.

关键词： deep image compression Iterative Non-Uniform Quantization

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：