检索结果-内蒙古大学图书馆

IEEE International Symposium on Circuits and systems

作者： Wei Zhou Zhibo Chen CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

Image quality assessment (IQA) aims to estimate human perception based image visual quality. Although existing deep neural networks (DNNs) have shown significant effectiveness for tackling the IQA problem, it still needs to improve the DNN-based quality assessment models by exploiting efficient multi-scale features. In this paper, motivated by the human visual system (HVS) combining multi-scale features for perception, we propose to use pyramid features learning to build a DNN with hierarchical multi-scale features for distorted image quality prediction. Our model is based on both residual maps and distorted images in luminance domain, where the proposed network contains spatial pyramid pooling and feature pyramid from the network structure. Our proposed network is optimized in a deep end-to-end supervision manner. To validate the effectiveness of the proposed method, extensive experiments are conducted on four widely-used image quality assessment databases, demonstrating the superiority of our algorithm.

关键词： Image quality Visualization Databases Visual systems Streaming media Quality assessment Video recording

来源：评论

学校读者我要写书评

暂无评论

Efficient Integer-Arithmetic-Only Convolutional Networks with Bounded ReLU

Efficient Integer-Arithmetic-Only Convolutional Networks wit...

引用

IEEE International Symposium on Circuits and systems (ISCAS)

作者： Hengrui Zhao Dong Liu Houqiang Li CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei China

To facilitate large-scale deployment of convolutional networks, integer-arithmetic-only inference has been demonstrated effective, which not only reduces computational cost but also ensures cross-platform consistency. However, previous studies on integer networks usually report a decline in the inference accuracy, given the same number of parameters as floating-point-number (FPN) networks. In this paper, we propose to finetune and quantize a well-trained FPN convolutional network to obtain an integer convolutional network. Our key idea is to adjust the upper bound of a bounded rectified linear unit (ReLU), which replaces the normal ReLU and effectively controls the dynamic range of activations. Based on the tradeoff between learning ability and quantization error of networks, we managed to preserve full accuracy after quantization and obtain efficient integer networks. Our experiments on ResNet for image classification demonstrate that our 8-bit integer networks achieve state-of-the-art performance compared with Google's TensorFlow and NVIDIA's TensorRT. Moreover, we experiment on VDSR for image super-resolution and on VRCNN for compression artifact reduction, both of which serve regression tasks that natively require high inference accuracy. Besides ensuring the equivalent performance as the corresponding FPN networks, our integer networks have only 1/4 memory cost and run 2× faster on GPUs.

关键词： Upper bound Quantization (signal) Image coding Superresolution Dynamic range Task analysis Image classification

来源：评论

学校读者我要写书评

暂无评论

Rpsa: Riemannian Principal Skewness Analysis

SSRN

引用

SSRN 2023年

作者： Geng, Xiurui Gao, Jingyu Aerospace Information Research Institute Chinese Academy of Sciences Beijing100864 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100049 China Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Chinese Academy of Sciences Beijing100864 China

By transforming the determination of the principal skewness direction of data into the solution of the eigenpair (eigenvalue and eigenvector) of its coskewness tensor, the principal skewness analysis (PSA) has been introduced into the blind source separation (BSS) community. Different from the eigenpair problem of a matrix which has been extensively and thoroughly studied, the solution of the eigenpairs of a coskewness tensor is a recently emerging research topic and can only be obtained by means of optimization at present. Generally, the iteration direction and the iteration step size are the two most critical factors in optimization methods. As the iteration direction, the conventional gradient has been widely used to solve the eigenpairs of a coskewness tensor in the existing methods. However, in this paper, we have found that compared with the conventional gradient, Riemannian gradient as the search direction is more conducive to avoid the current eigenvector converging to the ones that have been obtained. In addition, in order to obtain the rest locally maximal eigenpairs of a coskewness tensor, a new step-size adjustment strategy is also designed in this study. Experiments on simulated and real data demonstrate the effectiveness and superiority of the presented method. © 2023, The Authors. All rights reserved.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

K-Wise Multi-Graph Matching

SSRN

引用

SSRN 2023年

作者： Zhu, Xinwen Zhu, Liangliang Geng, Xiurui Aerospace Information Research Institute Chinese Academy of Sciences Beijing100864 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100049 China Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Chinese Academy of Sciences Beijing100864 China

Multi-graph matching, which aims to find the correspondences of multiple graphs, is an extension of conventional two-graph matching. There are mainly two categories of multi-graph matching methods, i.e., the pairwise-based methods and the tensor-based methods. Both of them try to find the correspondences between graphs by maximizing the values of the similarities between the corresponding features, e.g., nodes, edges, and so on. The difference is that for a set of features from different graphs to be matched, the pairwise-based methods consider the similarities of every two features, while the tensor-based methods directly consider the whole similarity among them. Therefore, the measurement of similarities in the tensor-based methods is usually much more flexible than that in the pairwise-based methods. However, the time and space complexities of the tensor-based methods grow geometrically as the number of graphs to be matched increases. In this paper, through a comprehensive investigation, we propose a k-wise multi-graph matching method which includes the aforementioned two kinds of methods as special cases. Generally, by choosing different value of k, it could be found that the proposed algorithm can strike a balance between flexible similarity measurement and low computational complexity. In addition, a factorization of k-wise global affinity matrix is proposed to save the computational cost of our method. Experiments with synthetic and real data demonstrate the superiority of our method. © 2023, The Authors. All rights reserved.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

360HRL: Hierarchical Reinforcement Learning Based Rate Adaptation for 360-Degree Video Streaming

360HRL: Hierarchical Reinforcement Learning Based Rate Adapt...

引用

IEEE Visual Communications and Image processing (VCIP)

作者： Jun Fu Chen Hou Zhibo Chen CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

ISBN: (纸本)9781728173221

Recently, reinforced adaptive bitrate (ABR) algorithms have achieved remarkable success in tile-based 360-degree video streaming. However, they heavily rely on accurate viewport prediction. To alleviate this issue, we propose a hierarchical reinforcement-learning (RL) based ABR algorithm, dubbed 360HRL. Specifically, 360HRL consists of a top agent and a bottom agent. The former is used to decide whether to download a new segment for continuous playback or re-download an old segment for correcting wrong bitrate decisions caused by inaccurate viewport estimation, and the latter is used to select bitrates for tiles in the chosen segment. In addition, 360HRL adopts a two-stage training methodology. In the first stage, the bottom agent is trained under the environment where the top agent always chooses to download a new segment. In the second stage, the bottom agent is fixed and the top agent is optimized with the help of a heuristic decision rule. Experimental results demonstrate that 360HRL outperforms existing RL-based ABR algorithms across a broad of network conditions and quality of experience (QoE) objectives.

关键词： Training Visual communication Image processing Bit rate Estimation Reinforcement learning Streaming media

来源：评论

学校读者我要写书评

暂无评论

Analyzing Time Complexity of Practical Learned Image Compression Models

Analyzing Time Complexity of Practical Learned Image Compres...

引用

IEEE Visual Communications and Image processing (VCIP)

作者： Xiaohan Pan Zongyu Guo Zhibo Chen CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

ISBN: (纸本)9781728173221

We have witnessed the rapid development of learned image compression (LIC). The latest LIC models have outperformed almost all traditional image compression standards in terms of rate-distortion (RD) performance. However, the time complexity of LIC model is still underdiscovered, limiting the practical applications in industry. Even with the acceleration of GPU, LIC models still struggle with long coding time, especially on the decoder side. In this paper, we analyze and test a few prevailing and representative LIC models, and compare their complexity with traditional codecs including H.265/HEVC intra and H.266/VVC intra. We provide a comprehensive analysis on every module in the LIC models, and investigate how bitrate changes affect coding time. We observe that the time complexity bottleneck mainly exists in entropy coding and context modelling. Although this paper pay more attention to experimental statistics, our analysis reveals some insights for further acceleration of LIC model, such as model modification for parallel computing, model pruning and a more parallel context model.

关键词： Analytical models Image coding Codecs Visual communication Computational modeling Rate-distortion Decoding

来源：评论

学校读者我要写书评

暂无评论

Electromagnetic Simulation Aided SAR Target Classification Via Deep Domain Adaptation

Electromagnetic Simulation Aided SAR Target Classification V...

引用

2021 CIE International Conference on Radar, Radar 2021

作者： Lv, Xiaoling Qiu, Xiaolan Yu, Wenming Aerospace Information Research Institute Chinese Academy of Sciences School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing China Suzhou Aerospace Information Research Institute Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Suzhou China Southeast University State Key Laboratory of Millimeter Waves Nanjing China

ISBN: (纸本)9781665498142

Convolutional neural networks (CNNs) have made tremendous success in optical images classification recently. However, in synthetic aperture radar (SAR) target classification, it is difficult to annotate a large amount of real SAR images to train CNNs. Sufficient annotated images can be easily obtained through simulation, but the disparity between the simulated images and the real images makes them difficult to directly apply to the real images classification. In this paper, we propose a model that integrates multi-kernel maximum mean discrepancy (MK-MMD) and domain-adversarial training to alleviate this problem. Simulated SAR images with annotation and unlabeled real SAR images are used to train our model. First, we use domain-adversarial training to prompt the model to extract domain-invariant features. Then, the MK-MMD between the hidden representations of simulated images and real images is reduced to narrow domain discrepancy. Experimental results on the real SAR dataset demonstrate that our method effectively solves the domain shift problem and improves the classification accuracy. © 2021 IEEE.

关键词： convolutional neural network (CNN) Synthetic aperture radar (SAR) target classification unsupervised domain adaptation (UDA)

来源：评论

学校读者我要写书评

暂无评论

Domain-class correlation decomposition for generalizable person re-identification

arXiv

引用

arXiv 2021年

作者： Yang, Kaiwen Tian, Xinmei CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

Domain generalization in person re-identification is a highly important meaningful and practical task in which a model trained with data from several source domains is expected to generalize well to unseen target domains. Domain adversarial learning is a promising domain generalization method that aims to remove domain information in the latent representation through adversarial training. However, in person re-identification, the domain and class are correlated, and we theoretically show that domain adversarial learning will lose certain information about class due to this domain-class correlation. Inspired by casual inference, we propose to perform interventions to the domain factor d, aiming to decompose the domain-class correlation. To achieve this goal, we proposed estimating the resulting representation z∗ caused by the intervention through first- and second-order statistical characteristic matching. Specifically, we build a memory bank to restore the statistical characteristics of each domain. Then, we use the newly generated samples {z∗, y, d∗} to compute the loss function. These samples are domain-class correlation decomposed;thus, we can learn a domain-invariant representation that can capture more class-related features. Extensive experiments show that our model outperforms the state-of-the-art methods on the large-scale domain generalization Re-ID benchmark. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Attribute Artifacts Removal for geometry-based Point Cloud Compression

arXiv

引用

arXiv 2021年

作者： Sheng, Xihua Li, Li Liu, Dong Xiong, Zhiwei CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

geometry-based point cloud compression (G-PCC) can achieve remarkable compression efficiency for point clouds. However, it still leads to serious attribute compression artifacts, especially under low bitrate scenarios. In this paper, we propose a Multi-Scale Graph Attention Network (MS-GAT) to remove the artifacts of point cloud attributes compressed by G-PCC. We first construct a graph based on point cloud geometry coordinates and then use the Chebyshev graph convolutions to extract features of point cloud attributes. Considering that one point may be correlated with points both near and far away from it, we propose a multi-scale scheme to capture the short- and long-range correlations between the current point and its neighboring and distant points. To address the problem that various points may have different degrees of artifacts caused by adaptive quantization, we introduce the quantization step per point as an extra input to the proposed network. We also incorporate a weighted graph attentional layer into the network to pay special attention to the points with more attribute artifacts. To the best of our knowledge, this is the first attribute artifacts removal method for G-PCC. We validate the effectiveness of our method over various point clouds. Objective comparison results show that our proposed method achieves an average of 9.74% BD-rate reduction compared with Predlift and 10.13% BD-rate reduction compared with RAHT. Subjective comparison results present that visual artifacts such as color shifting, blurring, and quantization noise are reduced. Copyright © 2021, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

aiWave: Volumetric Image Compression with 3-D Trained Affine Wavelet-like Transform

arXiv

引用

arXiv 2022年

作者： Xue, Dongmei Ma, Haichuan Li, Li Liu, Dong Xiong, Zhiwei The CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China The Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230088 China

Volumetric image compression has become an urgent task to effectively transmit and store images produced in biological research and clinical practice. At present, the most commonly used volumetric image compression methods are based on wavelet transform, such as JP3D. However, JP3D employs an ideal, separable, global, and fixed wavelet basis to convert input images from pixel domain to frequency domain, which seriously limits its performance. In this paper, we first design a 3-D trained wavelet-like transform to enable signal-dependent and non-separable transform. Then, an affine wavelet basis is introduced to capture the various local correlations in different regions of volumetric images. Furthermore, we embed the proposed wavelet-like transform to an end-to-end compression framework called aiWave to enable an adaptive compression scheme for various datasets. Last but not least, we introduce the weight sharing strategies of the affine wavelet-like transform according to the volumetric data characteristics in the axial direction to reduce the number of parameters. The experimental results show that: 1) when cooperating our trained 3-D affine wavelet-like transform with a simple factorized entropy coding module, aiWave performs better than JP3D and is comparable in terms of encoding and decoding complexities;2) when adding a context module to remove signal redundancy further, aiWave can achieve a much better performance than HEVC. Copyright © 2022, The Authors. All rights reserved.

关键词： 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：