检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

3 篇 会议

馆藏范围

3 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

3 篇 工学
- 3 篇 电气工程
- 3 篇 计算机科学与技术...
- 1 篇 软件工程
1 篇 医学
- 1 篇 临床医学

主题

3 篇 rate-distortion-...
2 篇 deep learning
2 篇 auto-encoder
1 篇 trellis-coded qu...
1 篇 deep-learning
1 篇 trellis-coded-qu...
1 篇 high efficiency ...
1 篇 versatile video ...
1 篇 image compressio...
1 篇 quantization

机构

2 篇 free univ berlin...
2 篇 tech univ berlin...
1 篇 heinrich hertz i...
1 篇 fraunhofer inst ...
1 篇 fraunhofer inst ...

作者

3 篇 wiegand thomas
3 篇 schwarz heiko
3 篇 pfaff jonathan
3 篇 marpe detlev
2 篇 schaefer michael
1 篇 borzechowski flo...
1 篇 pientka sophie
1 篇 schafer michael
1 篇 suhring karsten

语言

3 篇 英文

检索条件"主题词=Rate-Distortion-Optimization"

共 3 条记录，以下是1-10 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

rate-distortion-optimization FOR DEEP IMAGE COMPRESSION

RATE-DISTORTION-OPTIMIZATION FOR DEEP IMAGE COMPRESSION

引用

IEEE International Conference on Image Processing (ICIP)

作者： Schaefer, Michael Pientka, Sophie Pfaff, Jonathan Schwarz, Heiko Marpe, Detlev Wiegand, Thomas Fraunhofer Inst Telecommun Video Commun & Applicat Dept Heinrich Hertz Inst Einsteinufer 37 D-10587 Berlin Germany

ISBN: (纸本)9781665441155

Given the capabilities of massive GPU hardware, there has been a surge of using artificial neural networks (ANN) for still image compression. These compression systems usually consist of convolutional layers and can be considered as non-linear transform coding. Notably, these ANNs are based on an end-to-end approach where the encoder determines a compressed version of the image as features. In contrast to this, existing image and video codecs employ a block-based architecture with signal-dependent encoder optimizations. A basic requirement for designing such optimizations is estimating the impact of the quantization error on the resulting bitrate and distortion. As for non-linear, multi-layered neural networks, this is a difficult problem. This paper presents a performant auto-encoder architecture for still image compression, which represents the compressed features at multiple scales. Then, we demonstrate how an algorithm, which tests multiple feature candidates, can reduce the Lagrangian cost and optimize compression efficiency. The algorithm avoids multiple network executions by pre-estimating the impact of the quantization on the distortion by a higher-order polynomial.

关键词： High Efficiency Video Coding (HEVC) Versatile Video Coding (VVC) Deep Learning Auto-Encoder rate-distortion-optimization

来源：评论

学校读者我要写书评

暂无评论

TRELLIS-CODED QUANTIZATION FOR END-TO-END LEARNED IMAGE COMPRESSION 29

TRELLIS-CODED QUANTIZATION FOR END-TO-END LEARNED IMAGE COMP...

引用

IEEE International Conference on Image Processing (ICIP)

作者： Suhring, Karsten Schafer, Michael Pfaff, Jonathan Schwarz, Heiko Marpe, Detlev Wiegand, Thomas Fraunhofer Inst Telecommun Heinrich Hertz Inst Berlin Germany Free Univ Berlin Inst Comp Sci Berlin Germany Tech Univ Berlin Dept Telecommun Syst Berlin Germany

ISBN: (数字)9781665496209

ISBN: (纸本)9781665496209

The performance of variational auto-encoders (VAE) for image compression has steadily grown in recent years, thus becoming competitive with advanced visual data compression technologies. These neural networks transform the source image into a latent space with a channel-wise representation. In most works, the latents are scalar quantized before being entropy coded. On the other hand, vector quantizers generally achieve denser packings of high-dimensional data regardless of the source distribution. Hence, low-complexity variants of these quantizers are implemented in the compression standards JPEG 2000 and Versatile Video Coding. In this paper we demonstrate coding gains by using trellis-coded quantization (TCQ) over scalar quantization. For the optimization of the networks with regard to TCQ, we employ a specific noisy representation of the features during the training stage. For variable-rate VAEs, we obtained 7.7% average BD-rate savings on the Kodak images by using TCQ over scalar quantization. When different networks per target bitrate are optimized, we report a relative coding gain of 2.4% due to TCQ.

关键词： Deep Learning Auto-Encoder rate-distortion-optimization Trellis-Coded Quantization

来源：评论

学校读者我要写书评

暂无评论

OPTIMIZING LEARNED IMAGE COMPRESSION ON SCALAR AND ENTROPY-CONSTRAINT QUANTIZATION 31

OPTIMIZING LEARNED IMAGE COMPRESSION ON SCALAR AND ENTROPY-C...

引用

2024 International Conference on Image Processing

作者： Borzechowski, Florian Schaefer, Michael Schwarz, Heiko Pfaff, Jonathan Marpe, Detlev Wiegand, Thomas Heinrich Hertz Inst Nachrichtentech Berlin GmbH Fraunhofer Inst Telecommun Berlin Germany Free Univ Berlin Inst Comp Sci Berlin Germany Tech Univ Berlin Dept Telecommun Syst Berlin Germany

ISBN: (纸本)9798350349405;9798350349399

The continuous improvements on image compression with variational autoencoders have lead to learned codecs competitive with conventional approaches in terms of rate-distortion efficiency. Nonetheless, taking the quantization into account during the training process remains a problem, since it produces zero derivatives almost everywhere and needs to be replaced with a differentiable approximation which allows end-to-end optimization. Though there are different methods for approximating the quantization, none of them model the quantization noise correctly and thus, result in suboptimal networks. Hence, we propose an additional finetuning training step: After conventional end-to-end training, parts of the network are retrained on quantized latents obtained at the inference stage. For entropy-constraint quantizers like Trellis-Coded Quantization, the impact of the quantizer is particularly difficult to approximate by rounding or adding noise as the quantized latents are interdependently chosen through a trellis search based on both the entropy model and a distortion measure. We show that retraining on correctly quantized data consistently yields additional coding gain for both uniform scalar and especially for entropy-constraint quantization, without increasing inference complexity. For the Kodak test set, we obtain average savings between 1% and 2%, and for the TecNick test set up to 2.2% in terms of Bjontegaard-Delta bitrate.

关键词： Deep-Learning Image Compression Quantization rate-distortion-optimization Trellis-Coded-Quantization

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共1页 << < 1 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：