检索结果-内蒙古大学图书馆

IAACS: Image aesthetic assessment through color composition and space formation

virtual reality & Intelligent Hardware 2023年第1期5卷 42-56页

作者： Bailin YANG Changrui ZHU Frederick WBLI Tianxiang WEI Xiaohui LIANG Qingxu WANG School of Computer and Information Engineering Zhejiang Gongshang UniversityHangzhou 310018China Department of Computer Science University of DurhamDH13LEUnited Kingdom College of Intelligence and Computing Tianjin UniversityTianjin 300072China State Key Laboratory of Virtual Reality Technology and Systems Beihang UniversityBeijing 100191China

Background Determining how an image is visually appealing is a complicated and subjective task. This motivates the use of a machine-learning model to evaluate image aesthetics automatically by matching the aesthetics of the general public. Although deep learning methods have successfully learned good visual features from images,correctly assessing the aesthetic quality of an image remains a challenge for deep learning. Methods To address this, we propose a novel multiview convolutional neural network to assess image aesthetics assessment through color composition and space formation(IAACS). Specifically, from different views of an image––including its key color components and their contributions, the image space formation, and the image itself––our network extracts the corresponding features through our proposed feature extraction module(FET) and the Image Net weight-based classification model. Result By fusing the extracted features, our network produces an accurate prediction score distribution for image aesthetics. The experimental results show that we have achieved superior performance.

关键词： Image aesthetic assessment Color composition Space formation Deep learning

来源：评论

学校读者我要写书评

暂无评论

Decoupling General and Personalized Knowledge in Federated Learning via Additive and Low-rank Decomposition 24

Decoupling General and Personalized Knowledge in Federated L...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Wu, Xinghao Liu, Xuefeng Niu, Jianwei Wang, Haolin Tang, Shaojie Zhu, Guogang Su, Hao State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Zhongguancun Laboratory Beijing China Department of Management Science and Systems University at Buffalo BuffaloNY United States School of Computer Science and Engineering Beihang University Beijing China

ISBN: (纸本)9798400706868

To address data heterogeneity, the key strategy of Personalized Federated Learning (PFL) is to decouple general knowledge (shared among clients) and client-specific knowledge, as the latter can have a negative impact on collaboration if not removed. Existing PFL methods primarily adopt a parameter partitioning approach, where the parameters of a model are designated as one of two types: parameters shared with other clients to extract general knowledge and parameters retained locally to learn client-specific knowledge. However, as these two types of parameters are put together like a jigsaw puzzle into a single model during the training process, each parameter may simultaneously absorb both general and client-specific knowledge, thus struggling to separate the two types of knowledge effectively. In this paper, we introduce FedDecomp, a simple but effective PFL paradigm that employs parameter additive decomposition to address this issue. Instead of assigning each parameter of a model as either a shared or personalized one, FedDecomp decomposes each parameter into the sum of two parameters: a shared one and a personalized one, thus achieving a more thorough decoupling of shared and personalized knowledge compared to the parameter partitioning method. In addition, as we find that retaining local knowledge of specific clients requires much lower model capacity compared with general knowledge across all clients, we let the matrix containing personalized parameters be low rank during the training process. Moreover, a new alternating training strategy is proposed to further improve the performance. Experimental results across multiple datasets and varying degrees of data heterogeneity demonstrate that FedDecomp outperforms state-of-the-art methods up to 4.9%. The code is available at https://***/XinghaoWu/FedDecomp © 2024 ACM.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Federated Learning for EEG Emotion Recognition

Adaptive Federated Learning for EEG Emotion Recognition

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Calvin Chan Qingqing Zheng Chengjian Xu Qiong Wang Pheng Ann Heng Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Department of Computer Science and Engineering The Chinese University of Hong Kong

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Emotion classification based on electroencephalogram (EEG) signals has drawn huge attention in affective brain computer interface (BCI). Recently, plenty of deep learning approaches have been proposed to improve the performance of EEG emotion recognition, especially the application of domain adaptation methods to tackle the challenge of large individual differences of EEG signals from subject to subject. However, these conventional transfer learning methods would result in information leakage during the sharing of domain data to enhance the accuracy of the target tasks. Therefore, in this paper, we proposed a distributed deep learning method, named adaptive federated learning (AdaFL) for EEG emotion recognition. In AdaFL, a server collaboratively learns a global model by adaptively aggregating the local models according to their importance in several communication rounds. In particular, an importance function is developed to evaluate each client, which would determine to select a subset of optimal clients for subsequent global model aggregation. The function is a simple transformation of the training loss and the sample size of the local models. Then, the resulting importance scores of selected clients are further converted into aggregation coefficients to measure the weights of the local models for global model aggregation. The distinct advantage of AdaFL is that the cross-subject information could be well utilized and the information leakage risk could be significantly reduced. To validate the efficacy of the proposed AdaFL, we conduct extensive experiments on two real EEG emotion datasets, i.e., SEED and DEAP. The experimental results show that the proposed AdaFL has achieved 94.95 ± 0.40% and 91.06 ± 0.29% average classification accuracy on the SEED and DEAP datasets, respectively, which reflects the superiority of our method over the state-of-the-art approaches.

关键词： Training Deep learning Adaptation models Emotion recognition Accuracy Federated learning Brain modeling

来源：评论

学校读者我要写书评

暂无评论

Why Go Full? Elevating Federated Learning Through Partial Network Updates 38

Why Go Full? Elevating Federated Learning Through Partial Ne...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Wang, Haolin Liu, Xuefeng Niu, Jianwei Guo, Wenkai Tang, Shaojie State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Center for AI Business Innovation Department of Management Science and Systems University at Buffalo BuffaloNY United States Zhongguancun Laboratory Beijing China

Federated learning is a distributed machine learning paradigm designed to protect user data privacy, which has been successfully implemented across various scenarios. In traditional federated learning, the entire parameter set of local models is updated and averaged in each training round. Although this full network update method maximizes knowledge acquisition and sharing for each model layer, it prevents the layers of the global model from cooperating effectively to complete the tasks of each client, a challenge we refer to as layer mismatch. This mismatch problem recurs after every parameter averaging, consequently slowing down model convergence and degrading overall performance. To address the layer mismatch issue, we introduce the FedPart method, which restricts model updates to either a single layer or a few layers during each communication round. Furthermore, to maintain the efficiency of knowledge acquisition and sharing, we develop several strategies to select trainable layers in each round, including sequential updating and multi-round cycle training. Our theoretical analysis and experimental results show that the FedPart method significantly outperforms traditional full-network update strategies, achieving faster convergence, greater accuracy, and reduced communication and computational overhead. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Spatial-Spectral Decoupling Fusion Framework for Visible and Near-Infrared Images 5

A Spatial-Spectral Decoupling Fusion Framework for Visible a...

引用

5th ACM International Conference on Multimedia in Asia, MMAsia 2023

作者： Tang, Zhenglin Hu, Hai-Miao Beijing Key Laboratory of Digital Media School of Computer Science and Engineering Beihang University Beijing China Hangzhou Innovation Institute of Beihang University Hangzhou China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China

ISBN: (纸本)9798400702051

The visible and near-infrared image fusion aims to generate an image that integrates complementary information from images captured in different spectral bands. However, existing fusion methods either only focus on the fusion of spatial information, or fuse spatial and spectral information without decoupling, resulting in undesirable effects such as halo artifacts, information loss, and inferior visual quality. To address these issues, we propose a Spatial-Spectral Decoupling Fusion (SSDF) framework that can effectively fuse the spatial and spectral information of visible and near-infrared images. The SSDF framework decomposes the image pairs into two main branches: the Spatial Feature Enhancement (SFE) branch and the Spectral Characteristic Preservation (SCP) branch. The SFE branch enhances the salient details in the fused image by exploiting the contrast between spatial features and generating region-based fusion weights, while the SCP branch preserves the intrinsic spectral characteristics of the scene by fusing the reflectance characteristics of visible and near-infrared images. The final image is obtained by combining the spatial and spectral information. We conduct extensive experiments to show that our SSDF method can achieve superior fusion performance in subjective visual quality and objective metrics compared with state-of-the-art methods. © 2023 Copyright held by the owner/author(s).

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Refining Boundary Sample Space for Differentiable Rendering 16

Refining Boundary Sample Space for Differentiable Rendering

引用

2024 16th International Conference on Graphics and Image Processing, ICGIP 2024

作者： Gao, Ruicheng Qi, Yue State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China Jingdezhen Research Institute Beihang University Jingdezhen333000 China Qingdao Research Institute Beihang University Qingdao266104 China

ISBN: (数字)9781510688780

ISBN: (纸本)9781510688773

The objective of physics-based differentiable rendering (PBDR) is to propagate gradients between scene parameters and the intensities of image pixels in a manner that is physically correct. The gradients obtained can be applied in optimization algorithms for the reconstruction of 3D geometry or materials, or they can be further propagated into neural network to learn neural representations of the scene. However, applying automatic differentiation techniques directly to the primary rendering process will result in biased gradients, as the rendering integral contains moving high-dimensional discontinuities. Based on how these discontinuities are managed-either implicitly or explicitly-existing PBDR methods can be categorized into two groups: reparameterization methods and boundary sampling methods. Boundary sampling methods need to construct paths that have one segment tangent to the geometry being differentiated in order to estimate a boundary integral to address the discontinuities explicitly. Such paths are usually constructed by sampling the tangent segment first and then extending it to complete the paths for subsequent processing. Fortunately, the number of dimensions in the space composed of such tangent segments is only three. In scenes comprised solely of triangle meshes, the first dimension is used to parameterize all the edges on the mesh, which determines a point on the tangent segment. The remaining two dimensions are used to parameterize the direction of the tangent segment. However, state-of-the-art boundary sampling methods parameterize the first dimension uniformly, which is inefficient because only a small portion of the edges contributes to the boundary integral, resulting in wasted parameter space. In this paper, we parameterize the first dimension by considering both edge length and contributions, thereby allocating more parameter space to important edges. Experiments demonstrate that our methods achieve lower variance gradients in the forward dif

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

From Global to Local: An Adaptive Environmental Illumination Estimation for Non-uniform Scattering 5

From Global to Local: An Adaptive Environmental Illumination...

引用

5th ACM International Conference on Multimedia in Asia, MMAsia 2023

作者： Liu, Huaizhuo Hu, Hai-Miao Beijing Key Laboratory of Digital Media School of Computer Science and Engineering Beihang University Beijing China Hangzhou Innovation Institute of Beihang University Hangzhou China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China

ISBN: (纸本)9798400702051

The atmospheric scattering model is one of the most widely used model to describe the optical imaging processing of hazy images. However, the global atmospheric light used in the traditional atmospheric scattering model has limitations in describing images with varying local environmental illumination. In this paper, by extending the global atmospheric light to the local illumination, a non-uniform scattering model is proposed, which can better describe real scenes under non-uniform environmental illumination. Based on this model, an adaptive local illumination estimation for hazy image is proposed, which can adapt to the local differences of environment illumination. The experimental results demonstrate that the proposed algorithm can outperform the state-of-the-art algorithms in terms of not only the non-uniform scattering removal but also the adaptability. © 2023 Copyright held by the owner/author(s).

关键词： atmospheric scattering model global atmospheric light local environment illumination non-uniform scattering removal

来源：评论

学校读者我要写书评

暂无评论

Towards Practical Facial Video-based Remote Heart Rate Estimation via Cross Domain rPPG Adaptation 23

Towards Practical Facial Video-based Remote Heart Rate Estim...

引用

Proceedings of the 2023 10th International Conference on Biomedical and Bioinformatics Engineering

作者： Ze Yang Haofei Wang Feng Lu Qinping Zhao the State Key Laboratory of Virtual Reality Technology and Systems and the School of Computer Science and Engineering at Beihang University China Peng Cheng Laboratory China the State Key Laboratory of Virtual Reality Technology and Systems and the School of Computer Science and Engineering at Beihang University China and Peng Cheng Laboratory China

ISBN: (纸本)9798400708343

Remote photoplethysmography (rPPG) is a non-contact technology that can estimate heart rate using facial video and holds significant potential for health monitoring. Despite the latest deep learning-based rPPG approaches can predict high-quality rPPG signal under similar scenarios, these methods often suffer from degraded performance when encountering variations in subjects, environments, or illumination conditions in target domains. To address this challenge, we propose an uncertainty-guided self-training approach that leverages model uncertainty and periodic priors to enhance generalization across different domains without requiring labels in the target domain. We iteratively update the model using pseudo-labels generated from its own predictions on unlabelled data in the target domain, with varying confidence levels informed by the model’s uncertainty estimation. To achieve this, we modify a standard Convolutional Neural Network (CNN) into a Bayesian Neural Network (BNN) for uncertainty estimation, which guides the assignment of pseudo-labels with varying confidence levels. By employing the adversarially learned periodic priors of rPPG signals shared across domains as regularization terms, we further stabilize the model adaptation process. We evaluate the proposed method on two public datasets (PURE and UBFC-rPPG) across five cross-domain tasks. Experimental results demonstrate improved performance over the baselines, with gains ranging from 60.5% to 97.2%, outperforming existing methods in generalization performance for rPPG-based heart rate measurement.

关键词： heart rate estimation remote photoplethysmography unsupervised domain adaptation

来源：评论

学校读者我要写书评

暂无评论

Pedestrian Attribute Recognition as Label-balanced Multi-label Learning 41

Pedestrian Attribute Recognition as Label-balanced Multi-lab...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Zhou, Yibo Hu, Hai-Miao Xiang, Yirong Zhang, Xiaokang Wu, Haotian Beijing Key Laboratory of Digital Media School of Computer Science and Engineering Beihang University Beijing100191 China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China Hangzhou Innovation Institute of Beihang University Hangzhou310051 China The University of Manchester United Kingdom

Rooting in the scarcity of most attributes, realistic pedestrian attribute datasets exhibit unduly skewed data distribution, from which two types of model failures are delivered: (1) label imbalance: model predictions lean greatly towards the side of majority labels;(2) semantics imbalance: model is easily overfitted on the under-represented attributes due to their insufficient semantic *** render perfect label balancing, we propose a novel framework that successfully decouples label-balanced data re-sampling from the curse of attributes co-occurrence, i.e., we equalize the sampling prior of an attribute while not biasing that of the co-occurred *** diversify the attributes semantics and mitigate the feature noise, we propose a Bayesian feature augmentation method to introduce true in-distribution *** both imbalances jointly, our work achieves best accuracy on various popular benchmarks, and importantly, with minimal computational budget. Copyright 2024 by the author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Power of Age-based Reward in Fresh Information Acquisition 42

The Power of Age-based Reward in Fresh Information Acquisiti...

引用

42nd IEEE International Conference on computer Communications, INFOCOM 2023

作者： Wang, Zhiyuan Meng, Qingkai Zhang, Shan Luo, Hongbin Beihang University School of Computer Science and Engineering Beijing China Beihang University State Key Laboratory of Virtual Reality Technology and Systems China Beihang University Institute of Artificial Intelligence Beijing China State Key Laboratory of Software Development Environment China

ISBN: (纸本)9798350334142

Many Internet platforms collect fresh information of various points of interest (PoIs) relying on users who happen to be nearby the PoIs. The platform will offer reward to incentivize users and compensate their costs incurred from information acquisition. In practice, the user cost (and its distribution) is hidden to the platform, thus it is challenging to determine the optimal reward. In this paper, we investigate how the platform dynamically rewards the users, aiming to jointly reduce the age of information (AoI) and the operational expenditure (OpEx). Due to the hidden cost distribution, this is an online non-convex learning problem with partial feedback. To overcome the challenge, we first design an age-based rewarding scheme, which decouples the OpEx from the unknown cost distribution and enables the platform to accurately control its OpEx. We then take advantage of the age-based rewarding scheme and propose an exponentially discretizing and learning (EDAL) policy for platform operation. We prove that the EDAL policy performs asymptotically as well as the optimal decision (derived based on the cost distribution). Simulation results show that the age-based rewarding scheme protects the platform's OpEx from the influence of the user characteristics, and verify the asymptotic optimality of the EDAL policy. © 2023 IEEE.

关键词： Simulation platform

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：