检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Wang, Rui Wu, Xiao-Jun Li, Hui Kittler, Josef School of Artificial Intelligence and Computer Science Jiangnan University Wuxi214122 China Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University China Centre for Vision Speech and Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom

Symmetric positive definite (SPD) matrix has been demonstrated to be an effective feature descriptor in many scientific areas, as it can encode spatiotemporal statistics of the data adequately on a curved Riemannian manifold, i.e., SPD manifold. Although there are many different ways to design network architectures for SPD matrix nonlinear learning, very few solutions explicitly mine the geometrical dependencies of features at different layers. Motivated by the great success of self-attention mechanism in capturing long-range relationships, an SPD manifold self-attention mechanism (SMSA) is proposed in this paper using some manifold-valued geometric operations, mainly the Riemannian metric, Riemannian mean, and Riemannian optimization. Then, an SMSA-based geometric learning module (SMSA-GLM) is designed for the sake of improving the discrimination of the generated deep structured representations. Extensive experimental results achieved on three benchmarking datasets show that our modification against the baseline network further alleviates the information degradation problem and leads to improved accuracy. Copyright © 2023, The Authors. All rights reserved.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Local and Global Feature Adaptive Adjustment Network for Remote Sensing Image Scene Classification

Local and Global Feature Adaptive Adjustment Network for Rem...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Feng Cao Chang Liu Deyu Li Yuhua Qian Chao Zhang Hu Zhang School of Computer and Information Technology (School of Big Data) Shanxi University Taiyuan China Key Laboratory of Computational Intelligence and Chinese Information Processing Ministry of Education Shanxi University Taiyuan China Institute of Big Data and Industry Shanxi University Taiyuan China

Convolutional neural network (CNN)-based methods have been extensively used for remote sensing scene classification (RSSC) and have obtained remarkable classification results. However, its limitations in extracting global features have hindered further improvement. Transformers can directly capture global features through self-attention mechanisms, but they have deficiencies in modeling local features. Currently, an approach that directly combines CNN and Transformer features may lead to feature imbalance, and introduce redundant information. To address these problems, we propose a local and global feature adaptive adjustment network (LGFAANet) for RSSC. First, we employ a dual-branch network structure to extract local and global features from remote sensing scene images. Second, we design a local and global feature adaptive adjustment module (LGFAA) to dynamically allocate weights to the features. Third, we use a multi-layer feature aggregation module (MLFA) to aggregate the adjusted features, thereby further enhancing feature representation. Finally, we introduce joint loss to accelerate network convergence, while reducing intra-class distance and increasing inter-class distance. Experimental results demonstrate that our proposed method displays enhanced feature representation ability and 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

Combining Enhancement and Fusion for Low-Light Visible and Infrared Image

Combining Enhancement and Fusion for Low-Light Visible and I...

引用

Chinese Automation Congress (CAC)

作者： Shaoji Li Kunpeng Zhang Yudong Liang Chao Zhang Xuekui Shangguan School of Computer and Information Technology Shanxi University Taiyuan China Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education Shanxi Information Industry Technology Research Institute Co. Ltd China

Visible and infrared fusion aims to create a fused image that encompasses not only complex texture details and target-specific information but also facilitates advanced visual analyses. However, existing fusion algorithms rarely focus on the fusion of visible and infrared images in low-light environments. Therefore, in this article we propose a enhancement and fusion network for low-light visible and infrared that processes images in two stages. In the first stage, we correct the color shift of the visible light image caused by abnormal-light source and enhance the brightness of the image. In the second stage, we use the fusion network to fuse the enhancement results of the first stage with infrared, and use the loss function to constrain the network. Finally, we explore the performance of our fusion results for object detection tasks. Experimental results show that our fusion results have obvious brightness enhancement effect, high color contrast, obvious texture details and target information, and also achieve good performance in target detection tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Designing Novel Cognitive Diagnosis Models via Evolutionary Multi-Objective Neural Architecture Search

arXiv

引用

arXiv 2023年

作者： Yang, Shangshang Ma, Haiping Zhen, Cheng Tian, Ye Zhang, Limiao Jin, Yaochu Zhang, Xingyi The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Artificial Intelligence Anhui University Hefei230039 China The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Institutes of Physical Science and Information Technology Anhui University Hefei230601 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui University Anhui Hefei230601 China The Faculty of Technology Bielefeld Unversity Bielefeld33619 Germany

Cognitive diagnosis plays a vital role in modern intelligent education platforms to reveal students’ proficiency in knowledge concepts for subsequent adaptive tasks. However, due to the requirement of high model interpretability, existing manually designed cognitive diagnosis models hold too simple architectures to meet the demand of current intelligent education systems, where the bias of human design also limits the emergence of effective cognitive diagnosis models. In this paper, we propose to automatically design novel cognitive diagnosis models by evolutionary multiobjective neural architecture search (NAS). Specifically, we observe existing models can be represented by a general model handling three given types of inputs and thus first design an expressive search space for the NAS task in cognitive diagnosis. Then, we propose multi-objective genetic programming (MOGP) to explore the NAS task’s search space by maximizing model performance and interpretability. In the MOGP design, each architecture is transformed into a tree architecture and encoded by a tree for easy optimization, and a tailored genetic operation based on four sub-genetic operations is devised to generate offspring effectively. Besides, an initialization strategy is also suggested to accelerate the convergence by evolving half of the population from existing models’ variants. Experiments on two real-world datasets demonstrate that the cognitive diagnosis models searched by the proposed approach exhibit significantly better performance than existing models and also hold as good interpretability as human-designed models. Copyright © 2023, The Authors. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Data Augmentation for Deep Learning Based a Utomaticmo Dulation Recognition

SSRN

引用

SSRN 2023年

作者： Ma, Hongbin Feng, Zhixi Yang, Shuyuan Wang, Min Wu, Tao Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Xidian University Xi’an710071 China Key Laboratory of Radar Signal Processing Xidian University Xi’an710071 China Xidian University China Institute School of Artificial Intelligence Xidian University TaiBai road 2# Shannxi Province Xi’an China

Data augmentation, as a strategy to expand training datasets, can be utilized to improve the accuracy of Deep Learning(DL)-based models to a certain extent. However, existing data augmentation methods for the DL-based Automatic Modulation Recognition (AMR) task lack a theoretical basis, and the availability of these methods to different types of AMR models has not been evaluated. In this paper, we first model the transformation process from an information source to a modulation signal and analyze the parameters that influence the difference between modulation signals for the theoretical basis of data augmentation in the AMR field. Then we propose nine signal augmentation methods to generate argumentation signals by modifying the influence parameters in the amplitude domain, the time domain, and the frequency domain. Finally, we conduct a series of experiments on the public RML2016.10a and RML2016.10b datasets to evaluate the effectiveness of the proposed methods andanalyze the availability of these methods to Convolutional Neural Network (CNN)-based AMR models, and hybrid AMR models based on CNN and Recurrent Neural Network. © 2023, The Authors. All rights reserved.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Dataset for Recognizing Chinese Semantic Frames based on the Semantic Scenario of the "Yi A Wei B" Construction 23

引用

23rd Chinese National Conference on computational Linguistics, CCL 2024

作者： Yang, Peiyuan Su, Xuefeng Li, Juncai Yan, Zhichao Chai, Qinghua Li, Ru School of Computer and Information Technology Shanxi University China School of Modern Logistics Shanxi Vocational University of Engineering Science and Technology China School of Foreign Languages Shanxi University China Key Laboratory of Computational Intelligence and Chinese Information Processing Ministry of Education China

ISBN: (纸本)9780000000002

In Chinese, specific sentence structures often carry semantic meaning, a characteristic underexplored in existing datasets. Leveraging the Chinese Frame Semantic Knowledge Base, we conducted deep semantic analysis, focusing on the structure "Yi A Wei B" found in the 2020 "People’s Daily" corpus. We created a frame recognition dataset with this structure, comprising 23,849 example sentences and 141 corresponding frames. Experiments featuring multiple frame recognition models revealed recognition difficulties due to insufficient target word information. Two approaches, target word transformation and data enhancement, increased model accuracy to 88.19%, thereby enhancing the model’s ability to extract construction-embedded semantics. © 2024 China National Conference on computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

HD-KT: Advancing Robust Knowledge Tracing via Anomalous Learning Interaction Detection 24

HD-KT: Advancing Robust Knowledge Tracing via Anomalous Lear...

引用

33rd ACM Web Conference, WWW 2024

作者： Ma, Haiping Yang, Yong Qin, Chuan Yu, Xiaoshan Yang, Shangshang Zhang, Xingyi Zhu, Hengshu Information Materials and Intelligent Sensing Laboratory of Anhui Province Institutes of Physical Science and Information Technology Anhui University Anhui Hefei China Institutes of Physical Science and Information Technology Anhui University Anhui Hefei China Career Science Lab BOSS Zhipin PBC School of Finance Tsinghua University Beijing China School of Artificial Intelligence Anhui University Anhui Hefei China The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Anhui Hefei China Career Science Lab BOSS Zhipin Beijing China

ISBN: (纸本)9798400701719

Knowledge tracing (KT) is a crucial task in online learning, aimed at tracing and predicting each student's knowledge states throughout their learning process. Over the past decade, it has garnered widespread attention due to it provides the potential for more tailored and adaptive online learning experiences. Although most current KT methodologies emphasize optimizing network structures to enhance predictive accuracy for future student performance, they often neglect anomalous interactions in students' learning processes, which may arise from low data quality (i.e., inferior question quality) and abnormal student behaviors (i.e., guessing and mistakes). To this end, in this paper, we propose a novel framework, termed HD-KT, designed to enhance the robustness of existing KT methodologies with Hybrid learning interactions Denoising approach. Specifically, we introduce two detectors for anomalous learning interactions, namely knowledge state-guided anomaly detector and student profile-guided anomaly detector. In the first detection module, we design a sequential autoencoder to identify anomalous learning interactions by detecting atypical student knowledge states. In the second module, we incorporate an attention mechanism by modeling a student's long-term profile to capture irregular interactions. Extensive experiments on four real-world benchmark datasets have decisively shown our HD-KT markedly boosts the robustness of numerous prevailing KT models, consequently increasing the accuracy of future student performance predictions. Additionally, our case studies highlight the versatility of HD-KT in addressing diverse downstream tasks, such as exercise quality analysis and learning behavior-based student clustering. © 2024 ACM.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Enhanced Clutter Suppression and GMTIm Algorithm with Modified DKP and NCS for Single-Channel Spaceborne-Maneuvering BFSAR

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Liu, Yuzhou Song, Xuan Li, Yachao Wang, Yitao Guo, Yanhong Ye, Pei Wang, Xuanqi Shi, Guangming Xidian University National Key Laboratory of Radar Signal Processing Xi’an710071 China Northwestern Polytechnical University School of Astronautics Xi’an710072 China DalianNaval Academy Operation Software and Simulation Institute Dalian116018 China Dalian University of Technology Institute for Advanced Intelligence Dalian116024 China Xidian University School of Physics Xi’an710071 China Xidian University School of Artificial Intelligence Xi’an710071 China Peng Cheng Laboratory Shenzhen518055 China

Single-channel spaceborne-maneuvering bistatic forward-looking synthetic aperture radar (SS-BFSAR) enables the maneuvering platform to achieve high-resolution forward-looking imaging without deploying additional antennas or transmitting the radar signal. Nevertheless, achieving the suppression of spatial variant clutter with only the single-channel configuration remains a critical challenge for the ground moving target imaging (GMTIm) mission of SS-BFSAR. This study proposes an enhanced clutter suppression and GMTIm algorithm for SS-BFSAR. First, the proposed modified deramp-keystone processing (DKP) completely decouples the echo signal in range and azimuth while avoiding the signal-to-clutter ratio (SCR) degradation caused by the azimuth spectrum aliasing. Subsequently, two pre-focusing approaches are developed with nonlinear chirp scaling (NCS), i.e., global NCS and block NCS, to achieve deep focusing of spatial variant clutter while introducing differences of Doppler frequency position (DFP) between the clutter and GMT. These approaches preserve the clutter consistency of the pre-focus results, thereby ensuring that the GMT signal exhibits high SCR following the image domain cancellation. Finally, a matched filter and the proposed monostatic-equivalent model are used to refocus the GMT and estimate its velocity. The proposed algorithm can simultaneously obtain the well-focused ground scene image and the GMTIm result without DFP drift caused by the target’s motion. Comparative experiments using simulation and real data demonstrate the effectiveness and superiority of the proposed algorithm. © 1980-2012 IEEE.

关键词： Echo suppression

来源：评论

学校读者我要写书评

暂无评论

LE-CAM++: A Lighter and More Efficient CAM++ for Speaker Verification

LE-CAM++: A Lighter and More Efficient CAM++ for Speaker Ver...

引用

International Symposium on Chinese Spoken Language processing

作者： Shuanghong Liu Zhida Song Zhihua Fang Liang He School of Computer Science and Technology Xinjiang University Urumqi Xinjiang Key Laboratory of Signal Detection and Processing Urumqi School of Intelligence Science and Technology Xinjiang University Urumqi Department of Electronic Engineering and Beijing National Research Center for Information Science and Technology Tsinghua University Beijing

ISBN: (数字)9798331516826

ISBN: (纸本)9798331516833

Due to its superior performance and fewer parameters, CAM++ has become the state-of-the-art model for speaker verification tasks. This model uses 2D convolutional blocks to extract front-end features, which are then fed into a densely connected time-delay neural network backbone to extract deep features. However, the simple stacking of 2D convolutions may lead to the generation of a significant amount of redundant features, which is detrimental to efficient feature extraction. Furthermore, although CAM++ already has a relatively small number of parameters, there is still room for further optimization. To address these issues, this paper first employs depthwise separable convolutions to replace the dilated convolutions in the back-end network of CAM++, making the model more lightweight. Next, we introduce spatial and channel reconstruction convolution (SCConv) in the ResBlock module of CAM++ to reduce redundant features and optimize the feature extraction process. Finally, after SCConv, we apply squeeze and excitation attention mechanism to model the interdependencies between channels and recalibrate each channel, further enhancing the model's representational capacity. We name the resulting model LE-CAM++. Our proposed model achieves an EER of 0.686 and a minDCF of 0.084 on the VoxCeleb1–O dataset. Compared to the baseline model CAM ++, the EER is reduced by 11%, and the minDCF is reduced by 28%. Additionally, the model parameters are reduced by 8%.

关键词： Attention mechanisms Stacking Neural networks Feature extraction Optimization

来源：评论

学校读者我要写书评

暂无评论

Simplified Skip-Connected UNet for Robust Speaker Verification Under Noisy Environments

Simplified Skip-Connected UNet for Robust Speaker Verificati...

引用

International Symposium on Chinese Spoken Language processing

作者： Zonghui Wang Zhihua Fang Zhida Song Liang He School of Computer Science and Technology Xinjiang University Urumqi Xinjiang Key Laboratory of Signal Detection and Processing Urumqi School of Intelligence Science and Technology Xinjiang University Urumqi Department of Electronic Engineering Beijing National Research Center for Information Science and Technology Tsinghua University Beijing

ISBN: (数字)9798331516826

ISBN: (纸本)9798331516833

In recent years, deep neural network based methods for speaker verification have made remarkable progress in clean environments. However, background noise significantly reduces the accuracy and reliability of speaker verification systems by masking or changing the voice characteristics of the speaker. In this paper, we propose a cascaded framework optimized with multiobjective loss to mitigate the interference of different levels and types of noise on the speaker verification task. The proposed architecture consists of two components: a speech enhancement module based on improved 2D-UNet, which reduces the structural limitations of directly using classical UNet for noise reduction, and a back-end speaker embedding extraction module. We carry our experiments on the VoxCeleb1 and VOiCES datasets, as well as in the presence of out-of-domain noise conditions. The evaluations have demonstrated this method shows great potential for speaker verification in noisy environments.

关键词： Training Semantics Noise reduction Interference Speech enhancement Complexity theory Noise measurement Reliability Optimization signal to noise ratio

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：