检索结果-内蒙古大学图书馆

作者：王锡亮青岛理工大学

学位级别：硕士

高光谱图像蕴含丰富的光谱信息和空间信息,在多个领域都具有广泛的应用。目前,深度学习方法由于具有出色的特征表达能力,因此许多学者已经将深度学习方法应用于高光谱图像分类,并取得了显著的成果。然而,仍然存在时序特征利用不充分,局... 详细信息

高光谱图像蕴含丰富的光谱信息和空间信息,在多个领域都具有广泛的应用。目前,深度学习方法由于具有出色的特征表达能力,因此许多学者已经将深度学习方法应用于高光谱图像分类,并取得了显著的成果。然而,仍然存在时序特征利用不充分,局部信息与全局信息之间关联性的忽略等问题。因此本文围绕充分利用高光谱图像中的时序特征和挖掘局部信息与全局信息之间的关联性,主要研究了以下两个内容: 1)提出了一种用于高光谱图像分类的多尺度特征增强模型(Multi-Scale Feature Enhancement module,MSFE),在实现不同尺度特征增强的同时能够有效解决时序特征利用不充分的问题。首先,为了提取不同尺度的特征,构建基于三维深度可分离卷积(3D-Depth-wise Separable Convolution,3D-DSC)的多尺度空谱特征提取模块(Multi-scale Spatial-Spectral Feature Extraction module,MSSFE);其次,为了增强多尺度特征表示以及对关键信息进行加权,提出基于有效通道注意力的特征增强模块(Feature Enhancement module based on Effective Channel Attention,FE-ECA);然后,为了揭示高光谱图像中的频率特性,挖掘更具判别性的时序特征,构建了基于transformer encoder结合傅里叶注意力机制(transformer encoder with Fourier Attention,TE-FA)的模型,进一步增强了多尺度特征的融合;最后,采用线性层实现分类。在3个高光谱数据集上的实验结果表明,本文提出的MSFE方法能够取得较好的分类性能。 2)构建了一种基于谱相关增强的高光谱图像分类模型(Hyperspectral Image Classification module based on Spectral Correlation Enhancement,SCE-HIC),在挖掘全局信息与局部信息之间关联性的同时能够获取更全面的空间-光谱信息。首先,为了获取高光谱图像中的浅层空间-光谱信息,构建了基于2D-CNN和3D-CNN并行结构的浅层空间-光谱特征提取模块(Shallow spectral-spatial Feature Extraction module,SFE);其次,为了提取全局信息和局部信息以及两者之间的关联性,构建了基于谱相关增强的特征提取模块(Feature Extraction module for Spectral Correlation Enhancement,SCEFE);然后,采用transformer encoder(TE)模块来获取深层上下文信息;最后,采用基于Soft Max的线性层得到分类结果。在3个高光谱数据集上的结果表明,本文提出的SCE-HIC方法能够有效的实现高光谱图像分类。

关键词：高光谱图像分类多尺度特征增强谱相关增强卷积神经网络 transformer encoder

来源：评论

学校读者我要写书评

暂无评论

Bladder lesion detection using EfficientNet and hybrid attention transformer through attention transformation

引用

SCIENTIFIC REPORTS 2025年第1期15卷 1-17页

作者： Sharma, Poonam Sharma, Bhisham Yadav, Dhirendra Prasad Thakral, Deepti Webber, Julian L. Chitkara Univ Inst Engn & Technol Rajpura 140401 Punjab India Chitkara Univ Ctr Res Impact & Outcome Rajpura 140401 Punjab India GLA Univ Dept Comp Engn & Applicat Mathura Uttar Pradesh India Manav Rachna Univ Dept Comp Sci & Technol Faridabad India Kuwait Coll Sci & Technol KCST Dept Elect & Commun Engn Doha Area 7th Ring Rd Kuwait 13133 Kuwait

Bladder cancer diagnosis is a challenging task because of its intricacy and variation of tumor features. Moreover, morphological similarities of the cancerous cells make manual diagnosis time-consuming. Recently, machine learning and deep learning methods have been utilized to diagnose bladder cancer. However, manual feature requirements for machine learning and the high volume of data for deep learning make them less reliable for real-time application. This study developed a hybrid model using CNN (Convolutional Neural Network) and less attention-based ViT (Vision transformer) for bladder lesion diagnosis. Our hybrid model contains two blocks of the inceptionV3 to extract spatial features. Furthermore, the global co-relation of the features is achieved using hybrid attention modules incorporated in the ViT encoder. The experimental evaluation of the model on a dataset consisting of 17,540 endoscopic images achieved an average accuracy, precision and F1-score of 97.73%, 97.21% and 96.86%, respectively, using a 5-fold cross-validation strategy. We compared the results of the proposed method with CNN and ViT-based methods under the same experimental condition, and we achieved much better performance than our counterparts.

关键词： Bladder Cancer Deep learning transformer encoder Self-Attention Hybrid attention Vision transformer InceptionV3

来源：评论

学校读者我要写书评

暂无评论

Directional Graph transformer-Based Control Flow Embedding for Malware Classification 22nd

Directional Graph Transformer-Based Control Flow Embedding f...

引用

22nd International Conference on Intelligent Data Engineering and Automated Learning

作者： Moon, Hyung-Jun Bu, Seok-Jun Cho, Sung-Bae Yonsei Univ Dept Artificial Intelligence Seoul 03722 South Korea Yonsei Univ Dept Comp Sci Seoul 03722 South Korea

ISBN: (纸本)9783030916077;9783030916084

Considering the fatality of malware attacks, the data-driven approach using massive malware observations has been verified. Deep learning-based approaches to learn the unified features by exploiting the local and sequential nature of control flowgraph achieved the best performance. However, only considering local and sequential information from graph-based malware representation is not enough to model the semantics, such as structural and functional nature of malware. In this paper, functional nature are combined to the control flowgraph by adding opcodes, and structural nature is embedded through DeepWalk algorithm. Subsequently, we propose the transformer-based malware control flow embedding to overcome the difficulty in modeling the long-term control flow and to selectively learn the code embeddings. Extensive experiments achieved performance improvement compared to the latest deep learning-based graph embedding methods, and in a 37.50% improvement in recall was confirmed for the Simda botnet attack.

关键词： Malware classification Control flow graph Graph embedding Attention mechanism transformer encoder

来源：评论

学校读者我要写书评

暂无评论

Fine-Grained Spatial-Temporal Representation Learning with Missing Data Completion for Traffic Flow Prediction 17th

Fine-Grained Spatial-Temporal Representation Learning with M...

引用

17th International Conference on Collaborative Computing: Networking Applications and Worksharing

作者： Wang, Shiqi Gao, Min Wang, Zongwei Wang, Jia Wu, Fan Wen, Junhao Chongqing Univ Sch Big Data & Software Engn Chongqing Peoples R China

ISBN: (纸本)9783030926342;9783030926359

Spatial-temporal traffic flow prediction is beneficial for controlling traffic and saving traffic time. Researchers have proposed prediction models based on spatial-temporal representation learning. Although these models have achieved better performance than traditional methods, they seldom consider several essential aspects: 1) distances and directions from the spatial aspect, 2) the bi-relation among historical time intervals from the temporal aspect, and 3) missing historical traffic data, which leads to an imprecise spatial-temporal features extraction. To this end, we propose Fine-Grained Features learning based on transformer-encoder and Graph convolutional networks (FGFTG) to improve the performance of traffic flow prediction in a missing data scenario. FGFTG consists of two components: feature extractors and a data completer. The feature extractors learn fine-grained spatial-temporal representations from spatial and temporal perspectives. They extract smoother representation with the information of distance and direction from a spatial perspective based on graph convolutional networks and node2vec and achieve bidirectional learning for temporal perspective utilizing transformer encoder. The data completer simulates the traffic flow data distribution and generates reliable data to fill in missing data based on generative adversarial networks. Experiments on two public datasets demonstrate the effectiveness of our approach over the state-of-the-art methods.

关键词： Traffic flow prediction Generative adversarial network Graph convolutional neural network transformer encoder

来源：评论

学校读者我要写书评

暂无评论

MACCIF-TDNN: MULTI ASPECT AGGREGATION OF CHANNEL AND CONTEXT INTERDEPENDENCE FEATURES IN TDNN-BASED SPEAKER VERIFICATION

MACCIF-TDNN: MULTI ASPECT AGGREGATION OF CHANNEL AND CONTEXT...

引用

IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)

作者： Wang, Fangyuan Song, Zhigang Jiang, Hongchen Xu, Bo Chinese Acad Sci Inst Automat Beijing Peoples R China Beijing Univ Technol Fac Informat Technol Beijing Peoples R China

ISBN: (纸本)9781665437394

Most of the recent state-of-the-art results for speaker verification are achieved by X-vector and its subsequent variants. In this paper, we propose a new network architecture which aggregates the channel and context interdependence features from multi aspects based on Time Delay Neural Network (TDNN). Firstly, we use the SE-Res2Blocks as in ECAPA-TDNN to explicitly model the channel interdependence to realize adaptive calibration of channel features, and process local context features in a multi-scale way at a more granular level compared with conventional TDNN-based methods. Secondly, we explore to use the encoder structure of transformer to model the global context interdependence features at an utterance level which can capture better long term temporal characteristics. Before the pooling layer, we aggregate the outputs of SE-Res2Blocks and transformer encoders to leverage the complementary channel and context interdependence features learned by themself respectively. Finally, instead of performing a single attentive statistics pooling, we also find it beneficial to extend the pooling method in a multi-head way which can discriminate features from multiple aspects. The proposed MACCIF-TDNN architecture can outperform most of the state-of-the-art TDNN based systems on VoxCelebl test sets.

关键词： speaker verification speaker recognition x-vector transformer encoder ECAPA

来源：评论

学校读者我要写书评

暂无评论

An improved YOLOv5-based vegetable disease detection method

引用

COMPUTERS AND ELECTRONICS IN AGRICULTURE 2022年 202卷

作者： Li, Jiawei Qiao, Yongliang Liu, Sha Zhang, Jiaheng Yang, Zhenchao Wang, Meili Northwest A&F Univ Yangling 712100 Shaanxi Peoples R China Minist Agr Key Lab Agr Internet Things Yangling 712100 Shaanxi Peoples R China Shaanxi Key Lab Agr Informat Percept & Intelligen Yangling 712100 Shaanxi Peoples R China Univ Sydney Fac Engn Australian Ctr Field Robot ACFR Sydney NSW 2006 Australia

The vegetable is the most dynamic cash crop in the cultivation industry, and vegetable diseases are closely related to food security. Due to the characteristics of different diseases being similar and interference from the external environment, it makes difficult to detect vegetable diseases. Therefore, we propose an improved algorithm for vegetable disease detection based on YOLOv5s. The CSP, FPN and NMS modules in YOLOv5s are improved to eliminate the influence of the external environment, enhance the extraction capability of multi-scale features, and improve the detection range and detection performance. To verify the effectiveness and generalization of the model, we collected and labeled 1000 images of five diseases. Experiments show that the mAP of vegetable disease detection reached 93.1%, effectively reducing missed detection and wrong detection caused by the complex background and improving detection and localization effects on the small-scale disease. Compared with nanodet-plus, YOLOv4-tiny, YOLOv5s and YOLOX-s, the proposed algorithm has higher detection accuracy and localization accuracy than the other algorithms. The model size is 17.1 MB, and the average time to detect each image on the test platform is about 0.03 s, providing a new theoretical basis and research ideas for disease detection.

关键词： Vegetable disease detection Deep learning transformer encoder Inception module Intelligent agriculture

来源：评论

学校读者我要写书评

暂无评论

Dense Oil Tank Detection and Classification via YOLOX-TR Network in Large-Scale SAR Images

引用

REMOTE SENSING 2022年第14期14卷 3246-3246页

作者： Wu, Qian Zhang, Bo Xu, Changgui Zhang, Hong Wang, Chao Chinese Acad Sci Aerosp Informat Res Inst Key Lab Digital Earth Sci Beijing 100094 Peoples R China Int Res Ctr Big Data Sustainable Dev Goals Beijing 100049 Peoples R China Univ Chinese Acad Sci Coll Resources & Environm Beijing 100049 Peoples R China

Oil storage tank detection and classification in synthetic aperture radar (SAR) images play a vital role in monitoring energy distribution and consumption. Due to the SAR side-looking imaging geometry and multibouncing scattering mechanism, dense oil tank detection and classification tasks have faced more challenges, such as overlapping, blurred contours, and geometric distortion, especially for small-sized tanks. To address the above issues, this paper proposes YOLOX-TR, an improved YOLOX based on the transformer encoder and structural reparameterized VGG-like (RepVGG) blocks, to achieve end-to-end oil tank detection and classification in densely arranged areas of large-scale SAR images. Based on YOLOX, the transformer encoder, a self-attention-based architecture, is integrated to enhance the representation of feature maps and capture the region of interest of oil tanks in densely distributed scenarios. Furthermore, RepVGG blocks are employed to reparameterize the backbone with multibranch typologies to strengthen the distinguishable feature extraction of multi-scale oil tanks without increasing computation in inference time. Eventually, comprehensive experiments based on a Gaofen-3 1 m oil tank dataset (OTD) demonstrated the effectiveness of the transformer encoder and RepVGG blocks, as well as the performance superiority of YOLOX-TR with a mAP and mAP(0.5) of 60.8% and 94.8%, respectively.

关键词： YOLOX-TR oil tank classification large-scale SAR images dense oil tanks transformer encoder RepVGG

来源：评论

学校读者我要写书评

暂无评论

Object Interaction Recommendation with Multi-Modal Attention-based Hierarchical Graph Neural Network

Object Interaction Recommendation with Multi-Modal Attention...

引用

9th IEEE International Conference on Big Data (IEEE BigData)

作者： Zhang, Huijuan Liang, Lipeng Wang, Dongqing Tongji Univ Sch Software Engn Shanghai Peoples R China

ISBN: (纸本)9781665439022

Object interaction recommendation from Internet of Things (IoT) is a crucial basis for IoT related applications. While many efforts are devoted to suggesting object for interaction, the majority of models rigidly infer relationships from human social network, overlook the neighbor information in their own object social network and the correlation of multiple heterogeneous features, and ignore multi-scale structure of the network. To tackle the above challenges, this work focuses on object social network, formulates object interaction recommendation as multi-modals object ranking, and proposes Multi-Modal Attentionbased Hierarchical Graph Neural Network (MM-AHGNN), that describes object with multiple knowledge of actions and pair-wise interaction feature, encodes heterogeneous actions with multi-modal encoder, integrates neighbor information and fuses correlative multi-modal feature by intra-modal hybrid-attention graph convolution and inter-modal transformer encoder, and employs multi-modal multi-scale encoder to integrate multi-level information, for suggesting object interaction more flexibly. With extensive experiments on real-world datasets, we prove that MM-AHGNN achieves better recommendation results (improve 3-4% HR@3 and 4-5% NDCG@3) than the most advanced baseline. To our knowledge, our MM-AHGNN is the first research in GNN design for object interaction recommend ation. Source codes are available at: https://***/gaosaroma/MM-AHGNN.

关键词： Object Interaction Recommendation Object Social Network Hierarchical Graph Neural Network Multi-Modal Fusion transformer encoder Hybrid Attention

来源：评论

学校读者我要写书评

暂无评论

transformer-based hierarchical latent space VAE for interpretable remaining useful life prediction

引用

ADVANCED ENGINEERING INFORMATICS 2022年 54卷

作者： Jing, Tao Zheng, Pai Xia, Liqiao Liu, Tianyuan Hong Kong Polytech Univ Dept Ind & Syst Engn Hong Kong Peoples R China

Data-driven prediction of remaining useful life (RUL) has emerged as one of the most sought-after research in prognostics and health management (PHM). Nevertheless, most RUL prediction methods based on deep learning are black-box models that lack a visual interpretation to understand the RUL degradation process. To remedy the deficiency, we propose an intrinsically interpretable RUL prediction method based on three main modules: a temporal fusion separable convolutional network (TF-SCN), a hierarchical latent space variational auto-encoder (HLS-VAE), and a regressor. TF-SCN is used to extract the local feature information of the temporal signal. HLS-VAE is based on a transformer backbone that mines long-term temporal dependencies and compresses features into a hierarchical latent space. To enhance the streaming representation of the latent space, the temporal degradation information, i.e., health indicators (HI), is incorporated into the latent space in the form of inductive bias by using intermediate latent variables. The latent space can be used as a visual representation with self-interpretation to evaluate RUL degradation patterns visually. Experiments based on turbine engines show that the proposed approach achieves the same high-quality RUL prediction as black-box models while providing a latent space in which degradation rate can be captured to provide the interpretable evaluation.

关键词： Remaining useful life Interpretable estimation transformer encoder VAE Prognostics

来源：评论

学校读者我要写书评

暂无评论

One-Shot Multiple Object Tracking in UAV Videos Using Task-Specific Fine-Grained Features

引用

REMOTE SENSING 2022年第16期14卷 3853-3853页

作者： Wu, Han Nie, Jiahao He, Zhiwei Zhu, Ziming Gao, Mingyu Hangzhou Dianzi Univ Sch Elect Informat Hangzhou 310018 Peoples R China Zhejiang Prov Key Lab Equipment Elect Hangzhou 310009 Peoples R China

Multiple object tracking (MOT) in unmanned aerial vehicle (UAV) videos is a fundamental task and can be applied in many fields. MOT consists of two critical procedures, i.e., object detection and re-identification (ReID). One-shot MOT, which incorporates detection and ReID in a unified network, has gained attention due to its fast inference speed. It significantly reduces the computational overhead by making two subtasks share features. However, most existing one-shot trackers struggle to achieve robust tracking in UAV videos. We observe that the essential difference between detection and ReID leads to an optimization contradiction within one-shot networks. To alleviate this contradiction, we propose a novel feature decoupling network (FDN) to convert shared features into detection-specific and ReID-specific representations. The FDN searches for characteristics and commonalities between the two tasks to synergize detection and ReID. In addition, existing one-shot trackers struggle to locate small targets in UAV videos. Therefore, we design a pyramid transformer encoder (PTE) to enrich the semantic information of the resulting detection-specific representations. By learning scale-aware fine-grained features, the PTE empowers our tracker to locate targets in UAV videos accurately. Extensive experiments on VisDrone2021 and UAVDT benchmarks demonstrate that our tracker achieves state-of-the-art tracking performance.

关键词： multiple object tracking unmanned aerial vehicle video optimization contradiction task-specific representation transformer encoder fine-grained feature

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：