检索结果-内蒙古大学图书馆

learning-based image compression With Parameter-Adaptive Rate-Constrained Loss

IEEE SIGNAL PROCESSING LETTERS 2024年 31卷 1099-1103页

作者： Guerin Jr, Nilson D. da Silva, Renam Castro Macchiavello, Bruno Univ Brasilia Dept Comp Sci BR-70910900 Brasilia Brazil Univ Brasilia Fac UnB Gama BR-72444240 Gama Leste Brazil

In recent years, the crucial task of image compression has been addressed by end-to-end neural network methods. However, achieving fine-grained rate control in this new paradigm has presented challenges. In our previous work, we explored mismatches in rate estimation during target-rate-oriented training and proposed heuristics involving costly parameter searches as a solution. This work proposes a lightweight approach, which dynamically adapts loss parameters to mitigate rate estimation issues, ensuring precise target rate attainment. Inspired by Reinforcement learning, our method exhibits performance comparable to preceding approaches on the Kodak dataset in terms of PSNR. Additionally, it reduces computational training costs.

关键词： Convolutional neural network learning-based image compression rate control variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Semantic-oriented learning-based image compression by Only-Train-Once quantized autoencoders

引用

SIGNAL image AND VIDEO PROCESSING 2023年第1期17卷 285-293页

作者： Sebai, D. Shah, A. Ulah Univ Manouba Natl Sch Comp Sci Cristal Lab Manouba Tunisia Univ Tun Hussein Onn Fac Comp Sci & Informat Technol Parit Raja Johor Malaysia

Accessibility to big training datasets together with current advances in computing power has emerged interest in the leverage of deep learning to address image compression. This needs to train and deploy separate networks for rate adaptation, which is impractical and extensive in terms of memory cost and power consumption, especially for broad bitrate ranges. To deal with such limitation, the variable-rate compression methods use the Lagrange multiplier to control the Rate/Distortion trade-offs in order not to require retraining of the neural network for each rate. However, they do not make an optimized bit allocation for the eye-catching foreground details, and do not consider the different degree of attention that the human eye has to each area of the image. Thus, other deep learning-based image compression approaches, which could outperform the above ones, are replied on the use of additional information. In this paper, we present a loss-conditional autoencoder tailored to the specific task of semantic image understanding to achieve higher visual quality in lossy variable-rate compression. Our framework is a neural network-based scheme able to automatically optimize coding parameters with multi-term perceptual loss function based on semantic-important structural SIMilarity index. To ensure the rate adaptation, we suggest modulating the compression network on the bitwidth of its activations by quantizing them according to several bitwidth values. Experiments are presented on the JPEG AI dataset in which our method achieves competitive and higher visual quality for the same compressed size, when compared to conventional codecs and related work.

关键词： learning-based image compression Variable-rate compression Loss-conditional autoencoder Only-Train-Once Quantized autoencoders Multi-term loss function

来源：评论

学校读者我要写书评

暂无评论

FOURIER SERIES AND LAPLACIAN NOISE-based QUANTIZATION ERROR COMPENSATION FOR END-TO-END learning-based image compression 30

FOURIER SERIES AND LAPLACIAN NOISE-BASED QUANTIZATION ERROR ...

引用

30th IEEE International Conference on image Processing (ICIP)

作者： Jiang, Shiqi Yuan, Hui Li, Shuai Mao, Xiaolong Shandong Univ Sch Software Jinan Shandong Peoples R China Shandong Univ Sch Control Sci & Engn Jinan Shandong Peoples R China

ISBN: (纸本)9781728198354

Quantization is a core operation in lossy image compression. In the end-to-end learning-based image compression framework, quantization is conducted by a rounding operation during test, while it is replaced by additive uniform noise during training, leading to a mismatched problem between train and test. To address this problem, we propose a quantization error compensation method for the end-to-end learning-based image compression framework. The method uses Fourier series to approximate the periodic changes of the quantization error, and adds Laplacian noise to the quantized latent during test. The proposed method can be flexibly combined with different end-to-end learning-based image compression methods. Experimental results show that higher coding efficiency can be achieved by adding the proposed method with the state-of-the-art methods.

关键词： learning-based image compression quantization error compensation fourier series laplacian noise

来源：评论

学校读者我要写书评

暂无评论

On the impact of learning-based image compression on computer vision tasks 47

On the impact of learning-based image compression on compute...

引用

Conference on Applications of Digital image Processing XLVII

作者： Akamatsu, Shunsuke Testolina, Michela Upenik, Evgeniy Ebrahimi, Touradj Waseda Univ Adv Multimedia Syst Lab Shillman Hall 4013-14-9 OkuboShinjuku Ku Tokyo 1690072 Japan Ecole Polytech Fed Lausanne EPFL Multimedia Signal Proc Grp MMSPG CH-1015 Lausanne Switzerland

ISBN: (纸本)9781510679344;9781510679351

The image compression field is witnessing a shift in paradigm thanks to the rise of neural network-based models. In this context, the JPEG committee is in the process of standardizing the first learning-based image compression standard, known as JPEG AI. While most of the research to date has focused on image coding for humans, JPEG AI plans to address both human and machine vision by presenting several non-normative decoders addressing multiple image processing and computer vision tasks in addition to standard reconstruction. While the impact of conventional image compression on computer vision tasks has already been addressed, no study has been conducted to assess the impact of learning-based image compression on such tasks. In this paper, the impact of learning-based image compression, including JPEG AI, on computer vision tasks is reviewed and discussed, mainly focusing on the image classification task along with object detection and segmentation. This study reviews the impact of image compression with JPEG AI on various computer vision models. It shows the superiority of JPEG AI over other conventional and learning-based compression models.

关键词： JPEG AI learning-based image compression computer vision image classification object detection

来源：评论

学校读者我要写书评

暂无评论

Asymmetric Learned image compression With Multi-Scale Residual Block, Importance Scaling, and Post-Quantization Filtering

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2023年第8期33卷 4309-4321页

作者： Fu, Haisheng Liang, Feng Liang, Jie Li, Binglin Zhang, Guohe Han, Jingning Xi An Jiao Tong Univ Sch Microelect Xian 710049 Peoples R China Simon Fraser Univ Sch Engn Sci Burnaby BC V5A 1S6 Canada Google Inc Mountain View CA 95054 USA

Recently, deep learning-based image compression has made significant progresses, and has achieved better rate-distortion (R-D) performance than the latest traditional method, H.266/VVC, in both MS-SSIM metric and the more challenging PSNR metric. However, a major problem is that the complexities of many leading learned schemes are too high. In this paper, we propose an efficient and effective image coding framework, which achieves similar R-D performance with lower complexity than the state of the art. First, we develop an improved multi-scale residual block (MSRB) that can expand the receptive field and capture global information more efficiently, which further reduces the spatial correlation of the latent representations. Second, an importance scaling network is introduced to directly scale the latents to achieve content-adaptive bit allocation without sending side information, which is more flexible than previous importance map methods. Third, we apply a post-quantization filter (PQF) to reduce the quantization error, motivated by the Sample Adaptive Offset (SAO) filter in video coding. Moreover, our experiments show that the performance of the system is less sensitive to the complexity of the decoder. Therefore, we design an asymmetric paradigm, in which the encoder employs three stages of MSRBs to improve the learning capacity, whereas the decoder only uses one stage of MSRB, which reduces the decoder complexity and still yields satisfactory performance. Experimental results show that compared to the state-of-the-art method, the encoding and decoding time of the proposed method are about 17 times faster, and the R-D performance is only reduced by about 1% on both Kodak and Tecnick-40 datasets, which is still better than H.266/VVC(4:4:4) and other leading learning-based methods. Our source code is publicly available at https://***/fengyurenpingsheng.

关键词： learning-based image compression multi-scale residual block importance scaling post-quantization filter entropy coding

来源：评论

学校读者我要写书评

暂无评论

ANFIC: image compression Using Augmented Normalizing Flows

IEEE OPEN JOURNAL OF CIRCUITS AND SYSTEMS

引用

IEEE OPEN JOURNAL OF CIRCUITS AND SYSTEMS 2021年 2卷 613-626页

作者： Ho, Yung-Han Chan, Chih-Chun Peng, Wen-Hsiao Hang, Hsueh-Ming Domanski, Marek Natl Yang Ming Chiao Tung Univ Dept Comp Sci Hsinchu 300 Taiwan Natl Yang Ming Chiao Tung Univ Dept Elect Engn Hsinchu 300 Taiwan Poznan Univ Tech Inst Multimedia Telecommun PL-60965 Poznan Poland

This paper introduces an end-to-end learned image compression system, termed ANFIC, based on Augmented Normalizing Flows (ANF). ANF is a new type of flow model, which stacks multiple variational autoencoders (VAE) for greater model expressiveness. The VAE-based image compression has gone mainstream, showing promising compression performance. Our work presents the first attempt to leverage VAE-based compression in a flow-based framework. ANFIC advances further compression efficiency by stacking and extending hierarchically multiple VAE's. The invertibility of ANF, together with our training strategies, enables ANFIC to support a wide range of quality levels without changing the encoding and decoding networks. Extensive experimental results show that in terms of PSNR-RGB, ANFIC performs comparably to or better than the state-of-the-art learned image compression. Moreover, it performs close to VVC intra coding, from low-rate compression up to perceptually lossless compression. In particular, ANFIC achieves the state-of-the-art performance, when extended with conditional convolution for variable rate compression with a single model. The source code of ANFIC can be found at https://***/dororojames/ANFIC.

关键词： Training Degradation image coding Codes Convolution Stacking Network architecture learning-based image compression flow-based image compression augmented normalizing flows perceptually lossless image compression variable rate image compression

来源：评论

学校读者我要写书评

暂无评论

Device Interoperability for Learned image compression with Weights and Activations Quantization

Device Interoperability for Learned Image Compression with W...

引用

Picture Coding Symposium (PCS)

作者： Koyuncu, Esin Solovyev, Timofey Alshina, Elena Kaup, Andre Friedrich Alexander Univ Erlangen Nurnberg Multimedia Commun & Signal Proc Erlangen Germany Huawei Technol Audiovisual Lab Munich Res Ctr Munich Germany

ISBN: (纸本)9781665492577

learning-based image compression has improved to a level where it can outperform traditional image codecs such as HEVC and VVC in terms of coding performance. In addition to good compression performance, device interoperability is essential for a compression codec to be deployed, i.e., encoding and decoding on different CPUs or GPUs should be error-free and with negligible performance reduction. In this paper, we present a method to solve the device interoperability problem of a state-of-the-art image compression network. We implement quantization to entropy networks which output entropy parameters. We suggest a simple method which can ensure cross-platform encoding and decoding, and can be implemented quickly with minor performance deviation, of 0.3% BD-rate, from floating point model results.

关键词： learning-based image compression device interoperability neural network quantization

来源：评论

学校读者我要写书评

暂无评论

A new end-to-end image compression system based on convolutional neural networks 42

A new end-to-end image compression system based on convoluti...

引用

Conference on Applications of Digital image Processing XLII

作者： Akyazi, Pinar Ebrahimi, Touradj Ecole Polytech Fed Lausanne Multimedia Signal Proc Grp MMSPG CH-1015 Lausanne Switzerland

ISBN: (数字)9781510629684

ISBN: (纸本)9781510629684

In this paper, two new end-to-end image compression architectures based on convolutional neural networks are presented. The proposed networks employ 2D wavelet decomposition as a preprocessing step before training and extract features for compression from wavelet coefficients. Training is performed end-to-end and multiple models operating at different rate points are generated by using a regularizer in the loss function. Results show that the proposed methods outperform JPEG compression, reduce blocking and blurring artifacts, and preserve more details in the images especially at low bitrates.

关键词： learning-based image compression low-rate image compression deep convolutional neural networks discrete wavelet transform

来源：评论

学校读者我要写书评

暂无评论

EFFICIENT LEARNED image compression WITH SELECTIVE KERNEL RESIDUAL MODULE AND CHANNEL-WISE CAUSAL CONTEXT MODEL 49

EFFICIENT LEARNED IMAGE COMPRESSION WITH SELECTIVE KERNEL RE...

引用

49th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Fu, Haisheng Liang, Feng Liang, Jie Fang, Zhenman Zhang, Guohe Han, Jingning Xi An Jiao Tong Univ Xian Peoples R China Simon Fraser Univ Burnaby BC Canada Google LLC Mountain View CA USA

ISBN: (纸本)9798350344868;9798350344851

Recently, learning-based image compression approaches have achieved superior performance over classical image compression methods. However, their complexities remain quite high. In this paper, we propose two efficient modules to reduce the complexity. First, we introduce a selective kernel residual module into the core network, which effectively expands the receptive field and captures global information. Second, we present an improved channel-wise causal context model, designed to not only reduce encoding and decoding time but also ensure rate-distortion performance. Experimental results demonstrate that our proposed method achieves better trade-off than recent leading learned image compression methods, and also outperforms the latest H.266/VVC (4:4:4) in terms of PSNR and MS-SSIM metrics.

关键词： learning-based image compression Selective kernel residual module Channel-wise causal context model

来源：评论

学校读者我要写书评

暂无评论

MULTISCALE AUGMENTED NORMALIZING FLOWS FOR image compression 49

MULTISCALE AUGMENTED NORMALIZING FLOWS FOR IMAGE COMPRESSION

引用

49th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Windsheimer, Marc Brand, Fabian Kaup, Andre Friedrich Alexander Univ Erlangen Nurnberg Multimedia Commun & Signal Proc Cauerstr 7 D-91058 Erlangen Germany

ISBN: (纸本)9798350344868;9798350344851

Most learning-based image compression methods lack efficiency for high image quality due to their non-invertible design. The decoding function of the frequently applied compressive autoencoder architecture is only an approximated inverse of the encoding transform. This issue can be resolved by using invertible latent variable models, which allow a perfect reconstruction if no quantization is performed. Furthermore, many traditional image and video coders apply dynamic block partitioning to vary the compression of certain image regions depending on their content. Inspired by this approach, hierarchical latent spaces have been applied to learning-based compression networks. In this paper, we present a novel concept, which adapts the hierarchical latent space for augmented normalizing flows, an invertible latent variable model. Our best performing model achieves significant rate savings of more than 7% over comparable single-scale models.

关键词： learning-based image compression augmented normalizing flows hierarchical image compression rate distortion optimization end-to-end 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：