检索结果-内蒙古大学图书馆

MFFNet: A lightweight multi-feature fusion network for UAV infrared object detection

Egyptian Journal of Remote Sensing and Space Science 2024年第2期27卷 268-276页

作者： Chen, Yunlei Liu, Ziyan Zhang, Lihui Wu, Yingyu Zhang, Qian Zheng, Xuhui College of Big Data and Information Engineering Guizhou University Guizhou550025 China The State Key Laboratory of Public Big Data Guizhou University Guizhou550025 China

In light of issues such as unnoticeable texture features and limited resolution of infrared image objects, a lightweight multi-scale feature fusion method for UAV infrared object recognition is presented to enhance the performance of UAVs carrying intelligent devices to detect infrared objects. By changing the anchorless frame strategy of the YOLOX method, a lightweight Multi-Feature Fusion Network (MFFNet) for UAV IR image object recognition is proposed. First, a lightweight backbone network is built using ShuffleNetv2_block, spatial pyramid pooling, and other modules to reduce the network's number of parameters and inference time while maintaining its capacity to extract features. Second, we develop a multi-feature fusion module to improve the detection capabilities of the model for IR objects by fusing the local features and the overall characteristics of IR objects since the texture features of IR objects are challenging to employ, but the boundary information is evident. The boundary frame regression loss is then optimized using SIoU by comparing the predicted frame to the actual frame in terms of angle, distance, shape, and IoU (Intersection over Union), which forces the model to reach the optimum predicted box more quickly. © 2024 National Authority of Remote Sensing & Space Science

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

FIR-YOLACT:Fusion of ICIoU and Res2Net for YOLACT on Real-Time Vehicle Instance Segmentation

引用

Computers, Materials & Continua 2023年第12期77卷 3551-3572页

作者： Wen Dong Ziyan Liu Mo Yang Ying Wu College of Big Data and Information Engineering Guizhou UniversityGuiyang550025China The State Key Laboratory of Public Big Data Guizhou UniversityGuiyang550025China

Autonomous driving technology has made a lot of outstanding achievements with deep learning,and the vehicle detection and classification algorithm has become one of the critical technologies of autonomous driving *** vehicle instance segmentation can perform instance-level semantic parsing of vehicle information,which is more accurate and reliable than object ***,the existing instance segmentation algorithms still have the problems of poor mask prediction accuracy and low detection ***,this paper proposes an advanced real-time instance segmentation model named FIR-YOLACT,which fuses the ICIoU(Improved Complete Intersection over Union)and Res2Net for the YOLACT ***,the ICIoU function can effectively solve the degradation problem of the original CIoU loss function,and improve the training convergence speed and detection *** Res2Net module fused with the ECA(Efficient Channel Attention)Net is added to the model’s backbone network,which improves the multi-scale detection capability and mask prediction ***,the Cluster NMS(Non-Maximum Suppression)algorithm is introduced in the model’s bounding box regression to enhance the performance of detecting similarly occluded *** experimental results demonstrate the superiority of FIR-YOLACT to the based methods and the effectiveness of all *** processing speed reaches 28 FPS,which meets the demands of real-time vehicle instance segmentation.

关键词： Instance segmentation real-time vehicle detection YOLACT Res2Net ICIoU

来源：评论

学校读者我要写书评

暂无评论

Leaving None Behind: data-Free Domain Incremental Learning for Major Depressive Disorder Detection

引用

IEEE Transactions on Affective Computing 2024年第02期16卷 758-770页

作者： Chen, Tao Guo, Yanrong Hao, Shijie Hong, Richang Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data China Hefei University of Technology Ministry of Education and School of Computer Science and Information Engineering Hefei230009 China

While deep learning techniques have shown promising performance in the Major Depressive Disorder (MDD) detection task, they still face limitations in real-world scenarios. Specifically, given the data scarcity, some efforts have resorted to aggregating data from different domains to expand the data volume. However, their effectiveness is currently limited by the domain gap and data privacy. Additionally, the class imbalance issue is particularly severe in our application, leading to biased classifying performance accordingly. To address these challenges, we propose data-Free Domain Incremental Learning for the MDD detection (DIL-MDD) task, accommodating multiple feature distributions by only accessing well-trained models from previous domains and the data in the current domain. Specifically, DIL-MDD consists of two key modules: Adaptive Class-tailored Threshold Learning (ACTL) and data-Free Domain Alignment (DFDA). The first module measures the discrepancy between the outputs of two sequential domains, based on which we learn a class-tailored threshold adaptively. Building on this, we differentiate between samples that either exhibit similarities or dissimilarities with the previous domain, where this similar sample set is identified to investigate the feature distribution of the historical data. The second module imposes an alignment constraint to narrow the gap between these two sample sets, thereby exploring the expertise of the previous domain. To validate the effectiveness of the proposed method, we conduct extensive experiments on the public MDD datasets, i.e., DAIC-WOZ, MODMA, and CMDC. We also apply our method to another mental health condition, Autism Spectrum Disorder (ASD), to further demonstrate its applicability. Finally, the ablation studies validate the superiority of the proposed modules. © 2010-2012 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Fine-Grained Cross-Modal Fusion Based Refinement for Text-to-Image Synthesis

引用

Chinese Journal of Electronics 2023年第6期32卷 1329-1340页

作者： SUN Haoran WANG Yang LIU Haipeng QIAN Biao Department of Computer Science and Information Engineering Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data Ministry of EducationHefei University of Technology

Text-to-image synthesis refers to generating visual-realistic and semantically consistent images from given textual descriptions. Previous approaches generate an initial low-resolution image and then refine it to be high-resolution. Despite the remarkable progress, these methods are limited in fully utilizing the given texts and could generate text-mismatched images, especially when the text description is complex. We propose a novel finegrained text-image fusion based generative adversarial networks(FF-GAN), which consists of two modules: Finegrained text-image fusion block(FF-Block) and global semantic refinement(GSR). The proposed FF-Block integrates an attention block and several convolution layers to effectively fuse the fine-grained word-context features into the corresponding visual features, in which the text information is fully used to refine the initial image with more details. And the GSR is proposed to improve the global semantic consistency between linguistic and visual features during the refinement process. Extensive experiments on CUB-200 and COCO datasets demonstrate the superiority of FF-GAN over other state-of-the-art approaches in generating images with semantic consistency to the given texts.

关键词： Visualization Fuses Convolution Semantics Linguistics Benchmark testing Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Dual-stream coupling network with wavelet transform for cross-resolution person re-identification

引用

Journal of Systems engineering and Electronics 2023年第3期34卷 682-695页

作者： SUN Rui YANG Zi ZHAO Zhenghui ZHANG Xudong Key Laboratory of Knowledge Engineering with Big Data(Ministry of Education) Hefei University of TechnologyHefei 230601China School of Computer and Information Hefei University of TechnologyHefei 230601China

Person re-identification is a prevalent technology deployed on intelligent *** have been remarkable achievements in person re-identification methods based on the assumption that all person images have a sufficiently high resolution,yet such models are not applicable to the open *** real world,the changing distance between pedestrians and the camera renders the resolution of pedestrians captured by the camera *** low-resolution(LR)images in the query set are matched with high-resolution(HR)images in the gallery set,it degrades the performance of the pedestrian matching task due to the absent pedestrian critical information in LR *** address the above issues,we present a dualstream coupling network with wavelet transform(DSCWT)for the cross-resolution person re-identification ***,we use the multi-resolution analysis principle of wavelet transform to separately process the low-frequency and high-frequency regions of LR images,which is applied to restore the lost detail information of LR ***,we devise a residual knowledge constrained loss function that transfers knowledge between the two streams of LR images and HR images for accessing pedestrian invariant features at various *** qualitative and quantitative experiments across four benchmark datasets verify the superiority of the proposed approach.

关键词： cross-resolution feature invariant learning person re-identification residual knowledge transfer wavelet transform

来源：评论

学校读者我要写书评

暂无评论

A novel thermally-stable Ca2GaTaO6:Sm3+ phosphor and its application in WLEDs and anti-counterfeit inks

引用

Journal of Rare Earths 2025年第6期43卷 1120-1132页

作者： Zhang, Yanzhi Ling, Yi Cui, Ruirui Key Laboratory of Functional Composite Materials of Guizhou Province College of Big Data and Information Engineering Guizhou University Guiyang550025 China College of Physics Guizhou University Guiyang550025 China State Key Laboratory of Public Big Data Guizhou University Guiyang550025 China

In this study, a novel Ca2GaTaO6:Sm3+ phosphor was developed using the conventional high-temperature solid-phase method. The phase structure and morphology test results of phosphor indicate that the Ca2GaTaO6 material was successfully synthesized and the Sm3+ ions were successfully doped into the host lattice. When utilizing 406 nm excitation, the Ca2GaTaO6:xSm3+ phosphor has the strongest emission intensity at 599 nm and shows orange-red emission, which is mainly owing to the 4G5/2 → 6H7/2 jump of Sm3+ ions. For the performance of different concentrations of Sm3+ ions, 3 mol% performs the best. At this time, concentration quenching occurs, which is most predominantly induced by dipole–dipole (d–d) interactions. In terms of thermal stability, the Ca2GaTaO6:0.03Sm3+ phosphor shows good properties, with the luminescence intensity at 423 K exhibiting 88.17% of that at 298 K. The white light-emitting diodes (WLEDs) devices prepared using Ca2GaTaO6:0.03Sm3+ phosphor shows warm white light with excellent performance in terms of correlated color temperature and color rendering index (CCT = 3642 K, CRI, Ra = 93.5). In terms of anticounterfeit inks, the Ca2GaTaO6:0.03Sm3+ phosphor also shows good potential. These research results show that Ca2GaTaO6: Sm3+ phosphors have great performance for application in WLEDs and anti-counterfeit inks. © 2024 Chinese Society of Rare Earths

关键词： Phosphors

来源：评论

学校读者我要写书评

暂无评论

Multi-view Feature Learning for the Over-penalty in Adversarial Domain Adaptation

引用

data Intelligence 2024年第1期6卷 183-200页

作者： Yuhong Zhang Jianqing Wu Qi Zhang Xuegang Hu School of Computer and Information Engineering Hefei University of TechnologyHefei 230601China Key Laboratory of Knowledge Engineering with Big Data(Hefei University of Technology) The Ministry of Education of ChinaHefei 230009China

Domain adaptation aims to transfer knowledge from the labeled source domain to an unlabeled target domain that follows a similar but different ***,adversarial-based methods have achieved remarkable success due to the excellent performance of domain-invariant feature presentation ***,the adversarial methods learn the transferability at the expense of the discriminability in feature representation,leading to low generalization to the target *** this end,we propose a Multi-view Feature Learning method for the Over-penalty in Adversarial Domain ***,multi-view representation learning is proposed to enrich the discriminative information contained in domain-invariant feature representation,which will counter the over-penalty for discriminability in adversarial ***,the class distribution in the intra-domain is proposed to replace that in the inter-domain to capture more discriminative information in the learning of transferrable *** experiments show that our method can improve the discriminability while maintaining transferability and exceeds the most advanced methods in the domain adaptation benchmark datasets.

关键词： domain adaptation adversarial learning multi-view learning

来源：评论

学校读者我要写书评

暂无评论

A survey of unmanned aerial vehicle flight data anomaly detection:Technologies,applications,and future directions

引用

Science China(Technological Sciences) 2023年第4期66卷 901-919页

作者： YANG Lei LI ShaoBo LI ChuanJiang ZHANG AnSi ZHANG XuDong School of Mechanical Engineering Guizhou UniversityGuiyang 550025China State Key Laboratory of Public Big Data Guizhou UniversityGuiyang 550025China

Flight data anomaly detection plays an imperative role in the safety and maintenance of unmanned aerial vehicles(UAVs).It has attracted extensive attention from ***,the problems related to the difficulty in obtaining abnormal data,low model accuracy,and high calculation cost have led to severe challenges with respect to its practical ***,in this study,firstly,several UAV flight data simulation softwares are presented based on a brief presentation of the basic concepts of anomalies,the contents of UAV flight data,and the public datasets for flight data anomaly ***,anomaly detection technologies for UAV flight data are comprehensively reviewed,including knowledge-based,model-based,and data-driven ***,UAV flight data anomaly detection applications are briefly described and ***,the future trends and directions of UAV flight data anomaly detection are summarized and prospected,which aims to provide references for the following research.

关键词： unmanned aerial vehicle(UAV) flight data anomaly detection data-driven

来源：评论

学校读者我要写书评

暂无评论

ViGT: proposal-free video grounding with a learnable token in the transformer

引用

Science China(Information Sciences) 2023年第10期66卷 196-212页

作者： Kun LI Dan GUO Meng WANG School of Computer Science and Information Engineering Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Intelligent Interconnected Systems Laboratory of Anhui Province Institute of Artificial Intelligence Hefei Comprehensive National Science Center

The video grounding(VG) task aims to locate the queried action or event in an untrimmed video based on rich linguistic descriptions. Existing proposal-free methods are trapped in the complex interaction between video and query, overemphasizing cross-modal feature fusion and feature correlation for VG. In this paper, we propose a novel boundary regression paradigm that performs regression token learning in a transformer. Particularly, we present a simple but effective proposal-free framework, namely video grounding transformer(ViGT), which predicts the temporal boundary using a learnable regression token rather than multi-modal or cross-modal features. In ViGT, the benefits of a learnable token are manifested as follows.(1) The token is unrelated to the video or the query and avoids data bias toward the original video and query.(2) The token simultaneously performs global context aggregation from video and query ***, we employed a sharing feature encoder to project both video and query into a joint feature space before performing cross-modal co-attention(i.e., video-to-query attention and query-to-video attention) to highlight discriminative features in each modality. Furthermore, we concatenated a learnable regression token [REG] with the video and query features as the input of a vision-language transformer. Finally, we utilized the token [REG] to predict the target moment and visual features to constrain the foreground and background probabilities at each timestamp. The proposed ViGT performed well on three public datasets:ANet-Captions, TACoS, and YouCookⅡ. Extensive ablation studies and qualitative analysis further validated the interpretability of ViGT.

关键词： video grounding temporal sentence grounding boundary regression token learning proposal-free

来源：评论

学校读者我要写书评

暂无评论

Layer-Wise Learning Rate Optimization for Task-Dependent Fine-Tuning of Pre-Trained Models: An Evolutionary Approach

引用

ACM Transactions on Evolutionary Learning and Optimization 2024年第4期4卷 1-23页

作者： Bu, Chenyang Liu, Yuxin Huang, Manzong Shao, Jianxuan Ji, Shengwei Luo, Wenjian Wu, Xindong Key Laboratory of Knowledge Engineering with Big Data Ministry of Education and School of Computer Science and Information Engineering Hefei University of Technology Hefei China School of Artificial Intelligence and Big Data Hefei University Hefei China Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies School of Computer Science and Technology Harbin Institute of Technology Shenzhen China

The superior performance of large-scale pre-Trained models, such as Bidirectional Encoder Representations from Transformers (BERT) and Generative Pre-Trained Transformer (GPT), has received increasing attention in both academic and industrial research and has become one of the current research hotspots. A pre-Trained model refers to a model trained on large-scale unlabeled data, whose purpose is to learn general language representation or features for fine-Tuning or transfer learning in subsequent tasks. After pre-Training is complete, a small amount of labeled data can be used to fine-Tune the model for a specific task or domain. This two-stage method of "pre-Training+fine-Tuning"has achieved advanced results in natural language processing (NLP) tasks. Despite widespread adoption, existing fixed fine-Tuning schemes that adapt well to one NLP task may perform inconsistently on other NLP tasks given that different tasks have different latent semantic structures. In this article, we explore the effectiveness of automatic fine-Tuning pattern search for layer-wise learning rates from an evolutionary optimization perspective. Our goal is to use evolutionary algorithms to search for better task-dependent fine-Tuning patterns for specific NLP tasks than typical fixed fine-Tuning patterns. Experimental results on two real-world language benchmarks and three advanced pre-Training language models show the effectiveness and generality of the proposed framework. © 2024 held by the owner/author(s).

关键词： Semantics

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：