检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Ma, Jie Wang, Pinghui Wang, Zewei Kong, Dechen Hu, Min Han, Ting Liu, Jun The Ministry of Education of Key Laboratory for Intelligent Networks and Network Security School of Cyber Science and Engineering Xi’an Jiaotong University Shaanxi Xi’an710049 China The Ministry of Education of Key Laboratory for Intelligent Networks and Network Security School of Automation Science and Engineering Xi’an Jiaotong University Shaanxi Xi’an710049 China The China Mobile Research Institute China The Shannxi Provincial Key Laboratory of Big Data Knowledge Engineering School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an710049 China

Question answering methods are well-known for leveraging data bias, such as the language prior in visual question answering and the position bias in machine reading comprehension (extractive question answering). Current debiasing methods often come at the cost of significant in-distribution performance to achieve favorable out-of-distribution generalization ability, while non-debiasing methods sacrifice a considerable amount of out-of-distribution performance in order to obtain high in-distribution performance. Therefore, it is challenging for them to deal with the complicated changing real-world situations. In this paper, we propose a simple yet effective novel loss function with adaptive loose optimization, which seeks to make the best of both worlds for question answering. Our main technical contribution is to reduce the loss adaptively according to the ratio between the previous and the current optimization state on mini-batch training data. This loose optimization can be used to prevent non-debiasing methods from overlearning data bias while enabling debiasing methods to maintain slight bias learning. Experiments on the visual question answering datasets, including VQA v2, VQA-CP v1, VQA-CP v2, GQA-OOD, and the extractive question answering dataset SQuAD demonstrate that our approach enables QA methods to obtain state-of-the-art in- and out-of-distribution performance in most cases. The source code has been released publicly in https://***/reml-group/ALO. Copyright © 2023, 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

BEW-YOLO: An Improved Method for PCB Defect Detection Based on YOLOv7

BEW-YOLO: An Improved Method for PCB Defect Detection Based ...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Zhiyao Li Aimin Li Yuechen Zhang Xiaotong Kong Wenqiang Li Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

The PCB defect object size is small and the detection process is susceptible to background interference, usually have the problem of missed and false detection. In order to solve the above problems, an improved method based on YOLOv7 is proposed in this paper. Firstly, the bi-level routing attention (BRA) has been added to the header of the original YOLOv7 model to capture global dependencies and ensure the accuracy of small object detection and localization. Secondly, the explicit visual center (EVC) block is introduced before the fusion of mid-level features and high-level features to capture the global remote dependencies of top-level features, extract the features in local corner regions, achieve a comprehensive feature representation. Finally, the loss function is improved by changing the loss function of the original model to Wise-IoU, which allows our model to focus more on ordinary-quality anchor boxes and improve the performance of the detector while decreasing the competitiveness of anchor boxes for high-quality samples and reducing the influence of low-quality samples on the detection results. The experimental results show that the improved model improves 5% in AP and 1.9% in both AR and mAP over the original YOLOv7 model. Meanwhile, comparison experiments are conducted on the data-enhanced PCB dataset, which proves the superiority of our model over other state-of-the-art models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dual-Domain Attention Based Adaptive Graph Convolutional Network for EEG Emotion Recognition

Dual-Domain Attention Based Adaptive Graph Convolutional Net...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Xu, Tie Zhang, Tong Chen, Bianna Chen, C.L. Philip All authors are with the Guangdong Provincial Key Laboratory of AI Large Model and Intelligent Cognition the School of Computer Science and Engineering South China University of Technology Guangzhou 510006 China and are with the Pazhou Lab Guangzhou 510335 China and are with Engineering Research Center of the Ministry of Education on Health Intelligent Perception and Paralleled Digital-Human Guangzhou China.

ISBN: (纸本)9781665410205

The asymmetry of emotional responses is observed in electroencephalogram (EEG) of different frequency bands across various spatial brain regions in neuroscience research. Many prior works have primarily emphasized the dependencies among channels in the spatial domain, neglecting the dynamic interaction of EEG in both spatial and frequency domains, which may limit the performance of EEG emotion recognition. To address these issues, we propose the dual-domain attention based adaptive graph convolutional network (DDA-AGCN) for EEG emotion recognition. Specifically, we propose the lightweight dual-domain attention mechanism (DDA) based on random vector similarity measurement and the squeezeexcitation technique to capture important characteristics in the channel and frequency domain respectively. Furthermore, the adaptive graph convolutional network (AGCN) is utilized to adaptively filter and refine low signal-to-noise ratio EEG data, while also learning the dynamic connectivity patterns among important EEG channels and extracting higher-level abstract features for emotion recognition tasks. To validate the effectiveness of the proposed method, experimental comparisons were conducted on SEED, SEED-IV, and MPED. The experimental results show that our method achieves highly competitive classification performance compared to existing methods. Moreover, under fair comparison, the DDA demonstrates better performance and computational efficiency than self-attention. © 2024 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Few-shot Face Image Translation via GAN Prior Distillation

arXiv

引用

arXiv 2023年

作者： Zhao, Ruoyu Zhu, Mingrui Wang, Xiaoyu Wang, Nannan State Key Laboratory of Integrated Services Networks Xidian University Xi’an China School of Computer Science and Technology University of Science and Technology of China China

Face image translation has made notable progress in recent years. However, when training on limited data, the performance of existing approaches significantly declines. Although some studies have attempted to tackle this problem, they either failed to achieve the few-shot setting (less than 10) or can only get suboptimal results. In this paper, we propose GAN Prior Distillation (GPD) to enable effective few-shot face image translation. GPD contains two models: a teacher network with GAN Prior and a student network that fulfills end-to-end translation. Specifically, we adapt the teacher network trained on large-scale data in the source domain to the target domain with only a few samples, where it can learn the target domain’s knowledge. Then, we can achieve few-shot augmentation by generating source domain and target domain images simultaneously with the same latent codes. We propose an anchor-based knowledge distillation module that can fully use the difference between the training and the augmented data to distill the knowledge of the teacher network into the student network. The trained student network achieves excellent generalization performance with the absorption of additional knowledge. Qualitative and quantitative experiments demonstrate that our method achieves superior results than state-of-the-art approaches in a few-shot setting. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Self‑Generated Buried Submicrocavities for High‑Performance Near‑Infrared Perovskite Light‑Emitting Diode

引用

Nano-Micro Letters 2023年第8期15卷 355-367页

作者： Jiong Li Chenghao Duan Qianpeng Zhang Chang Chen Qiaoyun Wen Minchao Qin Christopher C.S.Chan Shibing Zou Jianwu Wei Zuo Xiao Chuantian Zuo Xinhui Lu Kam Sing Wong Zhiyong Fan keyou Yan School of Environment and Energy State Key Lab of Luminescent Materials and DevicesGuangdong Provincial Key Laboratory of Solid Wastes Pollution Control and RecyclingSouth China University of TechnologyGuangzhou 510000People’s Republic of China Department of Electronic and Computer Engineering The Hong Kong University of Science and TechnologyClear Water BayKowloonHong KongPeople’s Republic of China Department of Physics The Chinese University of Hong KongShatinHong KongPeople’s Republic of China Department of Physics The Hong Kong University of Science and TechnologyClear Water BayKowloon 999077Hong KongPeople’s Republic of China School of Chemistry and Chemical Engineering Guangxi UniversityNanning 530004People’s Republic of China Center for Excellence in Nanoscience(CAS) Key Laboratory of Nanosystem and Hierarchical Fabrication(CAS)National Center for Nanoscience and TechnologyBeijing 100190People’s Republic of China

ABSTRACT Embedding submicrocavities is an effective approach to improve the light out-coupling efficiency(LOCE)for planar perovskite light-emitting diodes(PeLEDs).In this work,we employ phenethylammonium iodide(PEAI)to trigger the Ostwald ripening for the downward recrystallization of perovskite,resulting in spontaneous formation of buried submicrocavities as light output *** simulation suggests the buried submicrocavities can improve the LOCE from 26.8 to 36.2%for near-infrared ***,PeLED yields peak external quantum efficiency(EQE)increasing from 17.3%at current density of 114 mA cm^(−2)to 25.5%at current density of 109 mA cm^(−2)and a radiance increasing from 109 to 487 W sr^(−1)m^(−2)with low *** turn-on voltage decreased from 1.25 to 1.15 V at 0.1 W sr^(−1)m^(−2).Besides,downward recrystallization process slightly reduces the trap density from 8.90×10^(15)to 7.27×10^(15)cm^(−3).This work provides a self-assembly method to integrate buried output coupler for boosting the performance of PeLEDs.

关键词： Perovskite light-emitting diodes Downward recrystallization Buried submicrocavities Light out-coupling efficiency Radiative recombination

来源：评论

学校读者我要写书评

暂无评论

Disentangled Noisy Correspondence Learning

arXiv

引用

arXiv 2024年

作者： Dang, Zhuohang Luo, Minnan Wang, Jihong Jia, Chengyou Han, Haochen Wan, Herun Dai, Guang Chang, Xiaojun Wang, Jingdong The School of Computer Science and Technology The Ministry of Education Key Laboratory of Intelligent Networks and Network Security The Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Shaanxi Xi'An710049 China SGIT AI Lab State Grid Shaanxi Electric Power Company Limited State Grid Corporation of China Shaanxi China The School of Information Science and Technology University of Science and Technology China United Arab Emirates The Baidu Inc China

Cross-modal retrieval is crucial in understanding latent correspondences across modalities. However, existing methods implicitly assume well-matched training data, which is impractical as real-world data inevitably involves imperfect alignments, i.e., noisy correspondences. Although some works explore similarity-based strategies to address such noise, they suffer from sub-optimal similarity predictions influenced by modality-exclusive information (MEI), e.g., background noise in images and abstract definitions in texts. This issue arises as MEI is not shared across modalities, thus aligning it in training can markedly mislead similarity predictions. Moreover, although intuitive, directly applying previous cross-modal disentanglement methods suffers from limited noise tolerance and disentanglement efficacy. Inspired by the robustness of information bottlenecks against noise, we introduce DisNCL, a novel information-theoretic framework for feature Disentanglement in Noisy Correspondence Learning, to adaptively balance the extraction of MII and MEI with certifiable optimal cross-modal disentanglement efficacy. DisNCL then enhances similarity predictions in modality-invariant subspace, thereby greatly boosting similarity-based alleviation strategy for noisy correspondences. Furthermore, DisNCL introduces soft matching targets to model noisy many-to-many relationships inherent in multi-modal input for noise-robust and accurate cross-modal alignment. Extensive experiments confirm DisNCL's efficacy by 2% average recall improvement. Mutual information estimation and visualization results show that DisNCL learns meaningful MII/MEI subspaces, validating our theoretical analyses. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Symbiosis Rather Than Aggregation: Towards Generalized Federated Learning via Model Symbiosis

引用

IEEE Internet of Things Journal 2025年

作者： Liu, Yuange Liu, Yuru Zhang, Weishan Zheng, Chaoqun Jiang, Wei Luo, Daobin Qiao, Qiao Meng, Lingzhao Zhao, Hongwei Yang, Su College of Computer Science and Technology Qingdao266580 China Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Jinan250014 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Jinan250014 China Information Science Academy of China Electronics Technology Group Corporation Beijing100036 China Fudan University School of Computer Science Shanghai200433 China

Federated Learning (FL) faces significant challenges in scenarios with non-IID (non-independent and identically distributed) data distributions across participating clients. Traditional aggregation-based approaches often struggle with the inherent misalignment between local and global optimization objectives, leadingwhich leads to gradient divergence and suboptimal generalization performance. This paper proposes a novel FL framework that replaces conventional aggregation with a biologically inspired model symbiosis approach called FedSym, which employs a dual-level symbiotic mechanism. Ectosymbiosis performs coarse-grained hierarchical parameter recombinations through random layer-wise model combination, while endosymbiosis enables fine-grained intra-layer parameter fusion through weighted averaging, collectively steering model updates towards flatter loss landscapes. Our theoretical analysis demonstrates that FedSym's convergence rate is O(1T) under non-IID conditions, which matches the convergence properties of FedAvg. Extensive experimentsevaluations across multiple datasets and model architectures show that FedSym achieves substantial improvements over state-of-the-art FL methods, particularly in challenging scenarios with high data heterogeneity, and demonstrates robust performance across varying numbers of participating clients and federation scales. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

computer aided diagnosis of diabetic retinopathy based on multi-view joint learning

引用

computers in Biology and Medicine 2024年 174卷 108428-108428页

作者： Xu, Xuebin Liu, Dehua Huang, Guohua Wang, Muyu Lei, Meng Jia, Yang School of Computer Science and Technology Xi'an University of Posts and Telecommunications Shaanxi Xi'an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Shaanxi Xi'an710121 China Xi'an Key Laboratory of Big Data and Intelligent Computing Shaanxi Xi'an710121 China Weinan Central Hospital Shaanxi Xi'an714099 China

Diabetic retinopathy (DR) is a kind of ocular complication of diabetes, and its degree grade is an essential basis for early diagnosis of patients. Manual diagnosis is a long and expensive process with a specific risk of misdiagnosis. computer-aided diagnosis can provide more accurate and practical treatment recommendations. In this paper, we propose a multi-view joint learning DR diagnostic model called RT2Net, which integrates the global features of fundus images and the local detailed features of vascular images to reduce the limitations of single fundus image learning. Firstly, the original image is preprocessed using operations such as contrast-limited adaptive histogram equalization, and the vascular structure of the extracted DR image is segmented. Then, the vascular image and fundus image are input into two branch networks of RT2Net for feature extraction, respectively, and the feature fusion module adaptively fuses the feature vectors’ output from the branch networks. Finally, the optimized classification model is used to identify the five categories of DR. This paper conducts extensive experiments on the public datasets EyePACS and APTOS 2019 to demonstrate the method's effectiveness. The accuracy of RT2Net on the two datasets reaches 88.2% and 85.4%, and the area under the receiver operating characteristic curve (AUC) is 0.98 and 0.96, respectively. The excellent classification ability of RT2Net for DR can significantly help patients detect and treat lesions early and provide doctors with a more reliable diagnosis basis, which has significant clinical value for diagnosing DR. © 2024 The Authors

关键词： computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Millimeter-wave radar-based algorithm for multi-person identification

Millimeter-wave radar-based algorithm for multi-person ident...

引用

第43届中国控制会议

作者： Jingpeng Wei Jian Guo Ming Chen Zheyu Wang Suyun Sun School of Computer Science Nanjing University of Posts and Telecommunications Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks Nanjing University of Posts and Telecommunications

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Millimeter-wave radar-based identification technology has received extensive academic attention due to its advantages of passivity and nonintrusiveness. However, current research mostly focuses on single-target vital signs identification. And research on multi-person target identification is very few. Moreover, existing algorithms are unable to accurately monitor and separate multiple human targets in a scene, resulting in a low accuracy. To address these problems, this paper proposes a multi-person identification algorithm based on vital signs. The algorithm combines the minimum variance beam forming technique,the cell average constant false alarm rate and the k-means clustering method to extract the single person vital sign signals from the multi-person target signals. Next, the algorithm designs a multiscale fusion network model to extract features from phase one-dimensional waveform signals and two-dimensional short-time Fourier transform spectrograms, and then integrates ***, the purpose of identity recognition is achieved through classification. Simulation experiments show that the proposed algorithm effectively separate multi-person targets and achieve a higher recognition accuracy than that of traditional algorithms.

关键词： Multi-person identification FMCW radar beamforming feature fusion vital signs

来源：评论

学校读者我要写书评

暂无评论

OneDConv: Generalized Convolution for Transform-Invariant Representation

OneDConv: Generalized Convolution for Transform-Invariant Re...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Weng, Haohan Chen, C. L. Philip Yi, Ke Liu, Haiqi Zhang, Tong The authors are with the Guangdong Provincial Key Laboratory of AI Large Model and Intelligent Cognition the School of Computer Science and Engineering South China University of Technology Guangzhou 510006 China and is with the Pazhou Lab Guangzhou 510335 China and is with Engineering Research Center of the Ministry of Education on Health Intelligent Perception and Paralleled Digital-Human Guangzhou China.

ISBN: (纸本)9781665410205

Convolutional Neural networks (CNNs) have ex-hibited great power in various vision tasks. However, the lack of transform-invariant property limits their further applications in complicated real-world scenarios. In this work, we pro-posed a novel generalized one-dimension convolutional operator (OneDConv), which dynamically transforms the convolution kernels based on the input features in a computationally and parametrically efficient manner. The proposed operator can extract the transform-invariant features naturally. It improves the robustness and generalization of convolution without sac-rificing the performance of common images. The proposed OneDConv operator can substitute the vanilla convolution. Thus, it can readily be incorporated into popular convolutional architectures, supporting end-to-end training. Empirical evaluations on popular benchmarks reveal OneDConv's superior performance over the standard convolution and competitive models in handling canonical and distorted images. © 2024 IEEE.

关键词： Convolution

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：