检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Niu, Shuaicheng Wu, Jiaxiang Zhang, Yifan Chen, Yaofo Zheng, Shijian Zhao, Peilin Tan, Mingkui School of Software Engineering South China University of Technology China Key Laboratory of Big Data and Intelligent Robot Ministry of Education China Tencent AI Lab China National University of Singapore Singapore Pazhou Laboratory China

Test-time adaptation (TTA) seeks to tackle potential distribution shifts between training and testing data by adapting a given model w.r.t. any testing sample. This task is particularly important for deep models when the test environment changes frequently. Although some recent attempts have been made to handle this task, we still face two practical challenges: 1) existing methods have to perform backward computation for each test sample, resulting in unbearable prediction cost to many applications;2) while existing TTA solutions can significantly improve the test performance on out-of-distribution data, they often suffer from severe performance degradation on in-distribution data after TTA (known as catastrophic forgetting). In this paper, we point out that not all the test samples contribute equally to model adaptation, and high-entropy ones may lead to noisy gradients that could disrupt the model. Motivated by this, we propose an active sample selection criterion to identify reliable and non-redundant samples, on which the model is updated to minimize the entropy loss for test-time adaptation. Furthermore, to alleviate the forgetting issue, we introduce a Fisher regularizer to constrain important model parameters from drastic changes, where the Fisher importance is estimated from test samples with generated pseudo labels. Extensive experiments on CIFAR-10-C, ImageNet-C, and ImageNet-R verify the effectiveness of our proposed method. Code is available at https://***/mr-eggplant/EATA. Copyright © 2022, The Authors. All rights reserved.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

A Blockchain-Based Multi-Cloud Storage data Consistency Verification Scheme

A Blockchain-Based Multi-Cloud Storage Data Consistency Veri...

引用

IEEE International Conference on big data and Cloud Computing (BdCloud)

作者： Feiyu Wang Jian-tao Zhou Hao Wang Xu Guo College of Computer Science Inner Mongolia University Hohhot China Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Inner Mongolia Key Laboratory of Social Computing and Data Processing Inner Mongolia Engineering Laboratory for Big Data Analysis Technology Engineering Research Center of Ecological Big Data Ministry of Education National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian China

Users worldwide widely use cloud storage because of its efficiency, convenience, and high availability. Multi-cloud storage is usually selected to ensure the high availability of data. Unfortunately, when data is migrated and replicated between multi-cloud data centers, it is not easy to guarantee data con-sistency. This paper proposes an efficient, secure, and new data consistency verification scheme using blockchain technology. In order to reduce the computation and communication overhead in the verification process, our scheme uses encrypted tags to build Merkle hash tree to generate unique and lightweight verification proofs and does not use third-party auditors. The final theoretical and experimental analysis shows that our scheme has higher security and a faster verification process in multi-cloud storage.

关键词： Cloud computing data centers Costs Blockchains Behavioral sciences

来源：评论

学校读者我要写书评

暂无评论

Joint Statistical and Causal Feature Modulated Face Anti-Spoofing

Joint Statistical and Causal Feature Modulated Face Anti-Spo...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Xin Dong Tao Wang Zhendong Li Hao Liu School of Information Engineering Ningxia University Yinchuan China Collaborative Innovation Center for Ningxia Big Data and Artificial Intelligence Co-Founded by Ningxia Municipality and Ministry of Education Yinchuan China Key Laboratory of the Internet of Water and Digital Water Governance of the Yellow River in Ningxia Yinchuan China

In this paper, we propose a hierarchical feature modulation (HFM) approach for stable face anti-spoofing in unseen domains and unseen attacks. The conventional multi-domain based generalizable approaches likely lead to local optima due to the complicated or heuristic learning paradigm. Inspired by the fact that high-level semantic disturbances and low-level miscellaneous bias jointly cause the distribution shift, HFM aims to modulate the fine-grained feature in a hierarchical manner. Specifically, we complement the structural feature with patch-wise learnable statistical information, i.e. local difference histogram, to relieve the overfitting on high-level semantics. We further introduce the structural causal model (SCM) with imaging color model to reveal that presenting mediums and capturing devices destroy the liveness-relevant information from the low level. Thus we model this hidden entanglement as a distribution mixture problem and propose the expectation-maximization (EM) based causal intervention to remove these miscellanies. Experimental results on public datasets demonstrate the effectiveness of HFM, especially in out-of-distribution settings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Structural Equivariance Self-Supervised Learning for Facial Pose Estimation

Structural Equivariance Self-Supervised Learning for Facial ...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yaoxing Wang Heng Zhou Zhendong Li Xian Mo Hao Liu School of Information Engineering Ningxia University Yinchuan China Collaborative Innovation Center for Ningxia Big Data and Artificial Intelligence Co-Founded by Ningxia Municipality and Ministry of Education Yinchuan China Key Laboratory of the Internet of Water and Digital Water Governance of the Yellow River in Ningxia Yinchuan China

In this paper, we propose a self-supervised learning method for robust facial pose estimation. Conventional methods usually split the coherent head motion into discrete and finite outputs, likely leading to bias prediction because the performance of head pose estimation highly relies on structural facial appearance. To address this issue, our model achieves structural equivariance to poses through a self-supervised learning strategy from extrinsic attributes of face neighbors and underlying local associations. Specifically, we construct a complete neighbor graph to capture the extrinsic properties of face neighbors, where different latent semantic attributes are assigned to each subgraph. Accordingly, we design a set of proxy tasks based on different attribute subgraphs, where the model is encouraged to learn the underlying relation of local features under pose variation. Extensive experimental results on the challenging, widely evaluated datasets indicate the effectiveness of our model compared with the state of the arts.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive Spectral Broadening Filter-Based Phased Array Focused Ultrasound Imaging for High-Echo Target Detection

SSRN

引用

SSRN 2024年

作者： Lou, Cuijuan Zhou, Quan Li, Ranyang Liu, Wufeng Li, Yan Yuchi, Ming Ding, Mingyue Key Laboratory of Grain Information Processing and Control Henan University of Technology Henan Key Laboratory of Grain Photoelectric Detection and Control China School of Artificial Intelligence and Big Data Henan University of Technology Zhengzhou450001 China Department of Automation School of Automation Wuhan University of Technology Wuhan430070 China Department of Biomedical Engineering School of Life Science and Technology Key Laboratory of Molecular Biophysics of the Ministry of Education Medical Ultrasound Laboratory Huazhong University of Science and Technology Wuhan430074 China

Noise suppression and resolution improvement are important issues in high-echo target ultrasound imaging detection. To address this problem, this paper proposes a phased array focused ultrasound imaging method based on an adaptive spectral broadening filter. The proposed method first standardizes the received signals after fixed-point transmission by subtracting the mean of the received aperture signals and dividing by the standard deviation of the received aperture signals. Then, spectralbroadening was achieved through covariance and temporal autocorrelation coefficient calculations. Finally, the variance factor proposed for the first time is calculated as a weight from standardized received data after fixed-point transmission focusing to obtain the final scanline data. To evaluate the performance of the proposed method in high-echo target ultrasound imaging detection, experimental phantom images and two views of the interventricular septum including the parasternal long-axisviews and the apical four-chamber views, are reconstructed. In three scenarios, some finer structures of the targets in the images by the proposed method can be more easily identified compared to delay and sum (DAS), square-neighborhood robust signal mean-to-standard-deviation factor (SN-RSMSF), and coherence factor beamforming (CF). For the experimental phantom data, the image resolution measured by -20dB mainlobe width of the proposed method can reach 14.2 percents of DAS, 18.3 percents of SN-RSMSF and 18.3 percents of CF. The proposed method also outperforms the other three methods in terms of noise suppression. The proposed method can be used to detect diseases that involve high-echo targets such as stones, heart valves, and calcifications. © 2024, The Authors. All rights reserved.

关键词： Ultrasonic imaging

来源：评论

学校读者我要写书评

暂无评论

Cross-Modality Fourier Feature for Medical Image Synthesis

Cross-Modality Fourier Feature for Medical Image Synthesis

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Mei Ma Ling Lin Heng Wang Zhendong Li Hao Liu School of Information Engineering Ningxia University Yinchuan China Collaborative Innovation Center for Ningxia Big Data and Artiffcial Intelligence Co-Founded by Ningxia Municipality and Ministry of Education Yinchuan China Key Laboratory of the Internet of Water and Digital Water Governance of the Yellow River in Ningxia Yinchuan China

In this paper, we propose a cross-modality fourier feature (CMFF) method via frequency selection, which learns the rational anatomical structure for targeting medical modality images. Unlike existing works seeking pixel-wise intensity discrepancy likely misleading to bias anatomical structures, our approach strongly holds the medical prior that different modality MRI images should share the same anatomical structure. To achieve this, our method instead learns to convert MRI images to the auxiliary frequency domain. Moreover, we adopt the Shapley value to quantify the contribution of each frequency, with respect to the structure for MRI image pairs of different modalities. Thus our approach learns to refine the anatomical structure generated by the target modality iteratively. Extensive experimental results on the BraTS dataset show that our model surpasses the performance compared to SOTAs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mandari: Multi-Modal Temporal knowledge Graph-aware Sub-graph Embedding for Next-POI Recommendation

Mandari: Multi-Modal Temporal Knowledge Graph-aware Sub-grap...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Xiaoqian Liu Xiuyun Li Yuan Cao Fan Zhang Xiongnan Jin Jinpeng Chen School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing China Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Ministry of Education Beijing China The Technology Innovation Center of Cultural Tourism Big Data of Hebei Province Chengde China Hebei Normal University for Nationalities Chengde China Knowledge Discovery and Data Mining Research Center Zhejiang Lab Hangzhou China

Next-POI recommendation aims to explore from user check-in sequence to predict the next possible location to be visited. Existing methods are often difficult to model the implicit association of multi-modal data with user choices. Moreover, traditional methods struggle to fully explore the variation of user preferences at variable time intervals. To tackle these limitations, we propose a Multi-Modal Temporal knowledge Graph-aware Sub-graph Embedding approach (Mandari). We first construct a novel Multi-Modal Temporal knowledge Graph. Based on the proposed knowledge graph, we integrate multi-modal information and leverage the graph attention network to calculate sub-graph prediction probability. Next, we implement a temporal knowledge mining method to model the segmentation and periodicity of user check-in and obtain temporal prediction probability. Finally, we fuse temporal prediction probability with the previous sub-graph prediction probability to obtain the final result. Extensive experiments demonstrate that our approach outperforms existing state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Graph Convolutional Neural Network with Inter-layer Cascade Based on Attention Mechanism 7

Graph Convolutional Neural Network with Inter-layer Cascade ...

引用

7th IEEE International Conference on Cloud Computing and Intelligence Systems, CCIS 2021

作者： Wei, Lu Liu, Yiting Feng, Kaiyuan Li, Jianzhao Sheng, Kai Wu, Yue Xidian University Key Laboratory of Big Data and Intelligent Vision School of Computer Science and Technology Xi'an710071 China Xidian University Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Electronic Engineering Xi'an710071 China Academy of Advanced Interdisciplinary Research Xidian University Xi'an710071 China

ISBN: (纸本)9781665441490

In recent years, graph data in the non-Euclidean space has been widely used, and the methods and techniques for learning graph data in many deep learning fields have been continuously developed, such as the Graph neural network (GNN). The structural characteristics of graph data, the aggregation mode and representation mode of node information, and the node neighbor information are the core issues of GNN. However, most of the existing graph convolutional neural networks have an excessive smoothing problem, which limits the learning ability of the model. Aiming at the over-smoothing problem of the current algorithm, this paper enhances the learning of graph data by improving the expression ability of local information and global features. This paper constructs a cascade structure between graph convolutional layers. This kind of network structure realizes the dense connection of convolutional layers, makes the local feature information is effectively used, and further enhances the graph representation ability. Introduce self-attention and TopK into the Readout module, selectively aggregate and express feature information, and use graph-level information more efficiently. Graph classification is a downstream task to verify the performance of the proposed model. Experimental results prove that this densely structured graph convolutional network can effectively aggregate local node information and global graph-level information. © 2021 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

SDGFormer: An Efficient Convolution Network Structurally Similar to Transformer

SDGFormer: An Efficient Convolution Network Structurally Sim...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Chaohao Wen Xun Gong School of Computing and Artificial Intelligence SWJTU Chengdu China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education China National Engineering Laboratory of Integrated Transportation Big Data Application Technology SWJTU Chengdu China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province SWJTU Chengdu China

Deep Neural Networks (DNN) have achieved extraordinary success in many visual recognition tasks. Visual Transformer (ViT), which is derived from Natural Language Processing (NLP), has achieved state-of-the-art (SOTA) results on many tasks due to its capability of capturing long-range dependencies in visual data. However, Existing ViT models are challenging to deploy on devices due to their massive computational consumption, huge memory overhead, and reliance on large datasets. In this work, we address these issues by replacing some computationally expensive and memory-intensive modules in ViT with standard Convolutional Neural Network (CNN) modules. Firstly, we propose an efficient Self-Attention module called SDG-Attention (SDGA) with linear space and time complexity, and an economical FeedForward Network (FFN) composed of group convolution and shuffle channel (SFFN). Then, we develop a lightweight CNN model with SDGA and SFFN, SDGFormer, which embraces several priors of ViT and is LayerNorm-Free. We evaluate SDGFormer on ImageNet-1K and Mini-ImageNet, and the SDGFormer-S achieves a comparable top-1 accuracy of 77.6% on ImageNet-1K with 9.1M parameters and 1.6 GFlops regimes. Moreover, our SDGFormer-T achieves SOTA performance on Mini-ImageNet with 83.3% accuracy, demonstrating good generalization on small datasets without extra data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Continual Learning for Smart City: A Survey

arXiv

引用

arXiv 2024年

作者： Yang, Li Luo, Zhipeng Zhang, Shiming Teng, Fei Li, Tianrui School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Southwest Jiaotong University Sichuan Chengdu611756 China

With the digitization of modern cities, large data volumes and powerful computational resources facilitate the rapid update of intelligent models deployed in smart cities. Continual learning (CL) is a novel machine learning paradigm that constantly updates models to adapt to changing environments, where the learning tasks, data, and distributions can vary over time. Our survey provides a comprehensive review of continual learning methods that are widely used in smart city development. The content consists of three parts: 1) Methodology-wise. We categorize a large number of basic CL methods and advanced CL frameworks in combination with other learning paradigms including graph learning, spatial-temporal learning, multi-modal learning, and federated learning. 2) Application-wise. We present numerous CL applications covering transportation, environment, public health, safety, networks, and associated datasets related to urban computing. 3) Challenges. We discuss current problems and challenges and envision several promising research directions. We believe this survey can help relevant researchers quickly familiarize themselves with the current state of continual learning research used in smart city development and direct them to future research trends. Copyright © 2024, The Authors. All rights reserved.

关键词： Smart city

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：