检索结果-内蒙古大学图书馆

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Li, Jicun Li, Xingjian Wang, Tianyang Wang, Shi Cao, Yanan Xu, Chengzhong Dou, Dejing Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Big Data Lab Baidu Research China University of Alabama Birmingham United States Institute of Information Engineering Chinese Academy of Sciences China State Key Lab of Iotsc University of Macau China

ISBN: (纸本)9781728163277

Fine-tuning pre-trained language models, such as BERT, has shown enormous success among various NLP tasks. Though simple and effective, the process of fine-tuning has been found unstable, which often leads to unexpected poor performance. To increase stability and generalizability, most existing works resort to maintaining the parameters or representations of pre-trained models during fine-tuning. Nevertheless, very little work explores mining the reliable part of pre-learned information that can help to stabilize fine-tuning. To address this challenge, we introduce a novel solution in which we fine-tune BERT with stabilized cross-layer mutual information. Our method aims to preserve the reliable behaviors of cross-layer information propagation, instead of preserving the information itself, of the pre-trained model. Therefore, our method circumvents the domain conflicts between pre-trained and target tasks. We conduct extensive experiments with popular pre-trained BERT variants on NLP datasets, demonstrating the universal effectiveness and robustness of our method. © 2023 IEEE.

关键词： Fine-tuning Stability Mutual information Pre-trained Language Model

来源：评论

学校读者我要写书评

暂无评论

Image encryption based on 2D-SAHM chaotic system and a novel DNA operation rule

引用

The European Physical Journal Special Topics 2023年第6期233卷 1311-1330页

作者： Huang, Lilian Ye, Youxin Liu, Yang College of Information and Communication Engineering Harbin Engineering University Harbin China Key Laboratory of Advanced Marine Communication and Information Technology Harbin Engineering University Ministry of Industry and Information Technology Harbin China National Key Laboratory of Underwater Acoustic Technology Harbin Engineering University Harbin China Sichuan Key Laboratory of Agile Intelligent Computing Southwest China Institute of Electronic Technology Chengdu China

With the continuous development of information technology, ensuring information security has become an important issue. As a widely used multimedia tool, images often face the risk of leakage. Therefore, this paper proposes an image encryption algorithm based on 2D-SAHM chaotic system and a new DNA operation rule. The algorithm first constructs a new chaotic system 2D-SAHM, which has better chaotic characteristics and can generate more random chaotic sequences than the traditional low-dimensional chaotic system. And then, on the basis of this system, the algorithm scrambles and diffuses the image. In the scrambling stage, the whole image is converted into a one-dimensional pixel matrix and divided into several sub-images by double Joseph scrambling. In the diffusion stage, to solve the problem that traditional DNA encryption relies too much on chaotic sequences, this paper proposes a new DNA operation rule. This rule determines the operation symbol of DNA by the type of amino acid, which improves the randomness of the algorithm. The final simulation results and performance analysis show that the algorithm has high security and strong anti-interference ability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Subdomain Alignment for Cross-domain Image Classification

Deep Subdomain Alignment for Cross-domain Image Classificati...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Yewei Zhao Hu Han Shiguang Shan Xilin Chen Key Laboratory of Intelligent Information Processing Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China China University of the Chinese Academy of Sciences Beijing China

Unsupervised domain adaptation (UDA), which aims to transfer knowledge learned from a labeled source domain to an unlabeled target domain, is useful for various cross-domain image classification scenarios. A commonly used approach for UDA is to minimize the distribution differences between two domains, and subdomain alignment is found to be an effective method. However, most of the existing subdomain alignment methods are based on adversarial learning and focus on subdomain alignment procedures without considering the discriminability among individual subdomains, resulting in slow convergence and unsatisfactory adaptation results. To address these issues, we propose a novel deep subdomain alignment method for UDA in image classification, which consists of a Union Subdo-main Contrastive Learning (USCL) module and a Multi-view Subdomain Alignment (MvSA) strategy. USCL can create discriminative and dispersed subdomains by bringing samples from the same subdomain closer while pushing away samples from different subdomains. MvSA makes use of labeled source domain data and easy target domain data to perform target-to-source and target-to-target alignment. Experimental results on three image classifi-cation datasets (Office-31, Office-Home, Visda-17) demonstrate that our proposed method is effective for UDA and achieves promising results in several cross-domain image classification tasks. Our code will be available: https://***/zhaoyewei/DSACDIC.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Long and Recent Preference Learning with Recent-k Items Distribution for Recommender System

引用

IEEE Transactions on Multimedia 2025年

作者： Gao, Yongbiao Niu, Sijie Lv, Guohua Ling, Miaogen Geng, Xin 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 Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Jinan China Southeast University Ministry of Education Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Application China University of Jinan Shandong Provincial Key Laboratory of Ubiquitous Intelligent Computing School of Information Science and Engineering China Nanjing University of Information Science and Technology School of Computer Science China Southeast University School of Computer Science and Engineering China

Reinforcement learning (RL) aims to formulate the recommendation task as a Markov decision process (MDP) and trains an agent to automatically learn the optimal recommendation policy from interaction trajectories through trial-and-error and reward mechanisms. However, most existing RL-based approaches overlook the correlation between items and the dynamics of user interests implied in temporally close interactions. Therefore, in this paper, we propose a reinforcement learning method that incorporates a "recent-k items"distribution to capture users' local preferences. Specifically, we model the output layer as two distinct branches. The "recent-k items"branch, formulated with a Kullback-Leibler divergence loss, learns the recent interests of users, whereas the other branch utilizes a one-step temporal difference error to capture long-term preferences. The proposed structure is integrated into deep Q-learning and actor-critics, resulting in two enhanced methods named R k Q and R k AC, respectively. Furthermore, a novel soft inter-reward is carefully designed to enhance the proposed method, and we theoretically prove the convergence of the proposed algorithm. We perform extensive experiments on two large real-world datasets and conduct further analysis of the influences of different action sequences, time intervals, and enhancement capabilities for state-of-the-art models. The experimental results demonstrate the efficacy of our proposed methods. © 1999-2012 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Big-Moe: Bypassing Isolated Gating For Generalized Multimodal Face Anti-Spoofing

Big-Moe: Bypassing Isolated Gating For Generalized Multimoda...

引用

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

作者： Yingjie Ma Zitong Yu Xun Lin Weicheng Xie Linlin Shen College of Computer Science and Software Engineering Shenzhen University Great Bay University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In the domain of facial recognition security, multimodal Face Anti-Spoofing (FAS) is essential for countering presentation attacks. However, existing technologies encounter challenges due to modality biases and imbalances, as well as domain shifts. Our research introduces a Mixture of Experts (MoE) model to address these issues effectively. We identified three limitations in traditional MoE approaches to multimodal FAS: (1) Coarse-grained experts’ inability to capture nuanced spoofing indicators; (2) Gated networks’ susceptibility to input noise affecting decision-making; (3) MoE’s sensitivity to prompt tokens leading to overfitting with conventional learning methods. To mitigate these, we propose the Bypass Isolated Gating MoE (BIG-MoE) framework, featuring: (1) Fine-grained experts for enhanced detection of subtle spoofing cues; (2) An isolation gating mechanism to counteract input noise; (3) A novel differential convolutional prompt bypass enriching the gating network with critical local features, thereby improving perceptual capabilities. Extensive experiments on four benchmark datasets demonstrate significant generalization performance improvement in multimodal FAS task. The code is released at https://***/murInJ/BIG-MoE.

关键词： Convolutional codes Sensitivity Convolution Face recognition Noise Logic gates Feature extraction Security Speech processing Overfitting

来源：评论

学校读者我要写书评

暂无评论

Learning with Open-world Noisy Data via Class-independent Margin in Dual Representation Space

arXiv

引用

arXiv 2025年

作者： Pan, Linchao Gao, Can Zhou, Jie Wang, Jinbao College of Computer Science and Software Engineering Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China

Learning with Noisy Labels (LNL) aims to improve the model generalization when facing data with noisy labels, and existing methods generally assume that noisy labels come from known classes, called closed-set noise. However, in real-world scenarios, noisy labels from similar unknown classes, i.e., open-set noise, may occur during the training and inference stage. Such open-world noisy labels may significantly impact the performance of LNL methods. In this study, we propose a novel dual-space joint learning method to robustly handle the open-world noise. To mitigate model overfitting on closed-set and open-set noises, a dual representation space is constructed by two networks. One is a projection network that learns shared representations in the prototype space, while the other is a One-Vs-All (OVA) network that makes predictions using unique semantic representations in the class-independent space. Then, bi-level contrastive learning and consistency regularization are introduced in two spaces to enhance the detection capability for data with unknown classes. To benefit from the memorization effects across different types of samples, class-independent margin criteria are designed for sample identification, which selects clean samples, weights closed-set noise, and filters open-set noise effectively. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods and achieves an average accuracy improvement of 4.55% and an AUROC improvement of 6.17% on CIFAR80N. Copyright © 2025, 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

OTFS Channel Estimator based on Embedded Pilot Sequence Similarity

OTFS Channel Estimator based on Embedded Pilot Sequence Simi...

引用

Communication technology and information technology (ICCTIT), International Conference on

作者： Youzhi Zhao Linyu Wang Jianhong Xiang Yang Liu College of Information and Communication Engineering Harbin Engineering University Harbin China Agile and Intelligent Computing Key Laboratory China Electronic Technology Group(cetc-10) Sichuan China

ISBN: (数字)9798331528973

ISBN: (纸本)9798331528980

Traditional orthogonal time-frequency space (OTFS) channel estimation schemes place guard symbols around pilots to avoid interference from data symbols, thereby reducing spectrum efficiency (SE). To address this issue, this paper proposes an OTFS channel estimator based on the similarity of embedded pilot sequences (EPSS). Firstly, according to prior channel information, multiple pilots are sparsely embedded into an OTFS data frame, preventing mutual interference between pilots while fully utilizing the channel diversity gain, and the guard symbols of the pilots at the transmitter are revoked to improve SE. Secondly, at the receiver, a shift sequence with strong correlation to the embedded pilot sequence at the transmitter is designed. Through linear search, when the autocorrelation value of the shift sequence with the pilot sequence is greater than a threshold, the delay-Doppler taps of the channel can be estimated. Finally, an inverse gain matrix is designed to eliminate interference from data symbols to the pilots, thereby obtaining the channel gain. Through the design of an OTFS communication system, simulation results verify that the EPSS scheme significantly improves SE with a slight reduction in reliable communication performance.

关键词： Time-frequency analysis Spectral efficiency Partial transmit sequences Simulation Channel estimation Symbols Interference Receivers Diversity methods Autocorrelation

来源：评论

学校读者我要写书评

暂无评论

Natural Human Skin‑Inspired Wearable and Breathable Nanofiber‑based Sensors with Excellent Thermal Management Functionality

引用

Advanced Fiber Materials 2024年第6期6卷 1955-1968页

作者： Peng Wang Xiaodan Li Guifen Sun Guoqing Wang Qing Han Chuizhou Meng Zhonghe Wei Yang Li School of Mechanical Engineering University of JinanJinan 250022China School of Information and Control Engineering China University of Mining and TechnologyXuzhou 221116China State Key Laboratory for Reliability and Intelligence of Electrical Equipment Engineering Research Center of Ministry of Education for Intelligent Rehabilitation Device and Detection TechnologyHebei Key Laboratory of Smart Sensing and Human‑Robot InteractionSchool of Mechanical EngineeringHebei University of TechnologyTianjin 300401China Shandong Provincial Key Laboratory of Network‑Based Intelligent Computing School of Information Science and EngineeringUniversity of JinanJinan 250022China Network Information Center Department of Computer ScienceQilu University of Technology(Shandong Academy of Sciences)Jinan 250353China School of Integrated Circuits Shandong UniversityJinan 250101China

Wearable sensors have been rapidly developed for application in various human monitoring ***,the wearing comfort and thermal properties of these devices have been largely ignored,and these characteristics urgently need to be ***,we develop a wearable and breathable nanofiber-based sensor with excellent thermal management functionality based on passive heat preservation and active Joule heating *** multifunctional device consists of a micropatterned carbon nanotube(CNT)/thermoplastic polyurethane(TPU)nanofiber electrode,a microporous ionic aerogel electrolyte and a microstructured Ag/TPU nanofiber *** to the presence of a supercapacitive sensing mechanism and the appli-cation of microstructuration,the sensor shows excellent sensing performance,with a sensitivity of 24.62 ***,due to the overall porous structure and hydrophobicity of TPU,the sensor shows good breathability(62 mm/s)and water repellency,with a water contact angle of 151.2°.In addition,effective passive heat preservation is achieved by combining CNTs with high solar absorption rates(85%)as the top layer facing the outside,aerogel with a low thermal conductivity(0.063 W m-1 k-1)as the middle layer for thermal insulation,and Ag with a high infrared reflectance rate as the bottom layer facing the *** warming,this material yields a higher temperature than ***,the active Joule heat-ing effect is realized by applying current through the bottom resistive electrode,which can quickly increase the temperature to supply controlled warming on *** proposed wearable and breathable sensor with tunable thermal properties is promising for monitoring and heat therapy applications in cold environments.

关键词： Wearable sensor Breathable Personal thermal management Electrospun nanofibers Joule heating

来源：评论

学校读者我要写书评

暂无评论

Hexagonal Convolutional Neural Network for Spatial Transcriptomics Classification

Hexagonal Convolutional Neural Network for Spatial Transcrip...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Gao, Jing Zhang, Fa Hu, Kai Cui, Xuefeng Xiangtan University Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan China Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Medical Technology Beijing Institute of Technology Beijing China Xiangnan University Key Laboratory of Medical Imaging and Artificial Intelligence of Hunan Province Chenzhou China Shandong University School of Computer Science and Technology Qingdao China

ISBN: (纸本)9781665468190

Recent advances in spatial transcriptomics have enabled the comprehensive measurement of transcriptional profiles while retaining the spatial contextual information. Identifying spatial domains is a critical step in the analysis of spatially resolved transcriptomics. Existing unsupervised methods perform poorly on this task owing to the large amount of noise and dropout events in the transcriptomic profiles. To address this problem, we first extend an unsupervised algorithm to a supervised learning method that can identify useful features and reduce noise hindrance. Second, inspired by the classical convolution in convolutional neural networks (CNNs), we designed a regular hexagonal convolution to compensate for the missing gene expression patterns from adjacent nodes. Compared with the graph convolution in graph neural networks (GNNs), our hexagonal convolution can preserve the relative spatial location information of different nodes in graph-structured data. Third, based on the hexagonal convolution, a novel hexagonal Convolutional Neural Network (hexCNN) is proposed for spatial transcriptomics classification. Finally, we compared the proposed hexCNN with existing methods on the DLPFC dataset. The results show that hexCNN achieves a classification accuracy of 87.2% and an average Rand index (ARI) of 78.2% (1.9% and 3.3% higher than those of GNNs). © 2022 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

An Entity Alignment Algorithm Based on Ontology Enhancement and Multi-Feature Fusion

An Entity Alignment Algorithm Based on Ontology Enhancement ...

引用

Frontiers technology of information and Computer (ICFTIC), IEEE International Conference on

作者： Hao Song Yuxia Lei Kangli Zi Fuyuan Quan Tianhang Zhang Qi Li School of Computer Science Qufu Normal University Rizhao Shandong China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (数字)9798331541750

ISBN: (纸本)9798331541767

Entity alignment plays a crucial role in the integration of knowledge graphs. However, current knowledge graphs often suffer from inconsistent construction standards, structural heterogeneity, and imprecise semantic representation of entities, which can lead to suboptimal embedding of structural information. Moreover, most existing entity alignment methods rely heavily on structural information, which limits alignment efficiency. To address these challenges, this paper presents Onto-IMF, an ontology-enhanced entity alignment method based on multi-feature fusion. This approach aims to enhance the semantic representation of entities by incorporating ontology information, thereby reducing structural discrepancies among heterogeneous graphs and improving the embedding of structural information. The multi-feature fusion entity alignment leverages diverse semantic features, including relations, attributes, and entity names, to achieve more accurate alignment. Experimental results on various DBP15K subsets indicate that the proposed method achieves Hits@l scores of 86.6%, 93.0%, and 97.7%, respectively, representing an average improvement of 7.9 % over the best-performing baseline models.

关键词： Accuracy Semantics Knowledge graphs Contrastive learning Ontologies Data models Standards

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：