检索结果-内蒙古大学图书馆

4th International Conference on information Science, Parallel and Distributed Systems, ISPDS 2023

作者： Liu, Shiyue Xiao, Yannan Wang, Xueyong Huang, Wenming Deng, Zhenrong School of Computer and Information Security Guilin University of Electronic Technology Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin China School of Computer and Information Security Guilin University of Electronic Technology Guilin China Guilin Xintong Technology Co. Guilin China

ISBN: (纸本)9798350337181

In recent years, large-scale pretrained natural language processing models such as BERT, GPT3 have achieved good results in processing tasks. However, in daily applications, these large-scale language models usually exist large model size or long running time, and the model portability and application are not very convenient. To settle this problem, we come up with a lightweight summarization generation method based on knowledge distillation (LW-BERT-KD, abbreviated as LBK model) to prove that complex neural network knowledge (taking BERT model as an example) can be extracted to lightweight language processing models (taking BiLSTM model as an example), thus achieving the purpose of complex knowledge extraction and model compression. In this paper, the BERT model is regarded as the teacher model, and the BiLSTM is regarded as the student model. The knowledge distillation technology is the transfer of knowledge from teacher models to student models, so that the generated model is effective, lightweight, and easy to port. On the Chinese abstract generation dataset, the training effect of this model is significantly better than the basic Transformer baseline. The experimental results show that if the training parameters are increased by 100 times, the model achieves comparable results with complex preprocessing language models. © 2023 IEEE.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Continual Learning with a Memory of Non-similar Samples 1

引用

17th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2022

作者： Min, Qilang He, Juanjuan Yang, Liuyan Fu, Yue College of Computer Science and Technology Wuhan University of Science and Technology Wuhan430081 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan China

ISBN: (数字)9789819915491

ISBN: (纸本)9789819915484

The replay method is an effective strategy to address the problem of catastrophic forgetting, a key challenge for continuous learning. However, the sample sets obtained by replay-based methods generally suffer from local data information deficiencies. This problem leads to an imbalance in the plasticity-stability of the model on older tasks. This paper proposes a novel method, called non-similar sample storage (NSS). Non-similar refers to the Euclidean distance for feature vectors of different samples being far. NSS extracts the feature vectors of the samples and then calculates the similarity of the feature vectors for each sample after the current task training. Samples that contribute less to the model classification effect among similar samples are iteratively deleted, and the subset of low-similarity samples is retained. Moreover, NSS reserves 30% of the storage space for saving samples near the center of the sample set. Low-similarity samples stored by NSS get larger losses during the replay process, leading to lower training effectiveness of the current task. This paper introduces a knowledge distillation strategy to solve this problem. A variable parameter was used to balance the classification loss of the new task with the distillation loss of the old task (NSS-D). Experimental results in CIFAR10 and imbalanced CIFAR10 show that NSS maximizes the data’s global information and can retain the model’s ability to recognize old tasks better. Compared with classical algorithms, NSS-D performs better on CIFAR100 (48.8%) and ImageNet-200 (36.7%). © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

End-to-End Paired Ambisonic-Binaural Audio Rendering

引用

IEEE/CAA Journal of Automatica Sinica 2024年第2期11卷 502-513页

作者： Yin Zhu Qiuqiang Kong Junjie Shi Shilei Liu Xuzhou Ye Ju-Chiang Wang Hongming Shan Junping Zhang Shanghai Key Laboratory of Intelligent Information Processing School of Computer ScienceFudan UniversityShanghai 200433China Beijing ByteDance Technology Co.Ltd. Shanghai 201102China. Chinese University of Hong Kong Hong KongChina IEEE Institute of Science and Technology for Brain-Inspired Intelligence and MOE Frontiers Center for Brain Science Fudan UniversityShanghai 200433 Shanghai Center for Brain Science and Brain-Inspired Technology Shanghai 200031China

Binaural rendering is of great interest to virtual reality and immersive media. Although humans can naturally use their two ears to perceive the spatial information contained in sounds, it is a challenging task for machines to achieve binaural rendering since the description of a sound field often requires multiple channels and even the metadata of the sound sources. In addition, the perceived sound varies from person to person even in the same sound field. Previous methods generally rely on individual-dependent head-related transferred function(HRTF)datasets and optimization algorithms that act on HRTFs. In practical applications, there are two major drawbacks to existing methods. The first is a high personalization cost, as traditional methods achieve personalized needs by measuring HRTFs. The second is insufficient accuracy because the optimization goal of traditional methods is to retain another part of information that is more important in perception at the cost of discarding a part of the information. Therefore, it is desirable to develop novel techniques to achieve personalization and accuracy at a low cost. To this end, we focus on the binaural rendering of ambisonic and propose 1) channel-shared encoder and channel-compared attention integrated into neural networks and 2) a loss function quantifying interaural level differences to deal with spatial information. To verify the proposed method, we collect and release the first paired ambisonic-binaural dataset and introduce three metrics to evaluate the content information and spatial information accuracy of the end-to-end methods. Extensive experimental results on the collected dataset demonstrate the superior performance of the proposed method and the shortcomings of previous methods.

关键词： Ambisonic attention binaural rendering neural network

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 29

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

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Li, Zhiyao Li, Aimin Zhang, Yuechen Kong, Xiaotong Li, Wenqiang 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

ISBN: (纸本)9798350330717

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. © 2023 IEEE.

关键词： attention mechanism defect detection PCB YOLOv7

来源：评论

学校读者我要写书评

暂无评论

Five-level anti-counterfeiting based on versatile luminescence of tri-doped double perovskites

引用

Nano Research 2024年第11期17卷 9971-9979页

作者： Xingru Yang Yuhang Sheng Linglong Zhang Lun Yang Fangjian Xing Yunsong Di Cihui Liu Fengrui Hu Xifeng Yang Guofeng Yang Yushen Liu Zhixing Gan Center for Future Optoelectronic Functional Materials School of Computer and Electronic Information/School of Artificial Intelligence Nanjing Normal University Nanjing 210023 China College of Physics Nanjing University of Aeronautics and Astronautics Key Laboratory of Aerospace Information Materials and Physics (NUAA) MIIT Nanjing 211106 China Hubei Key Laboratory of Photoelectric Materials and Devices School of Materials Science and Engineering Hubei Normal University Huangshi 435002 China College of Engineering and Applied Sciences and MOE Key Laboratory of Intelligent Optical Sensing and Manipulation Nanjing University Nanjing 210093 China College of Electronic and Information Engineering Changshu Institute of Technology Suzhou 215500 China School of Science Jiangsu Provincial Research Center of Light Industrial Optoelectronic Engineering and Technology Jiangnan University Wuxi 214122 China Yancheng Polytechnic College Yancheng 224005 China

Luminescent materials with multi-emission features are difficult to be replicated, which are highly desirable for advanced anti-counterfeiting. Here, we report the pioneering synthesis of Mn^(2+)/Yb^(3+)/Er^(3+) tri-doped Cs2Ag0.8Na0.2InCl6 double perovskites (MYE-DP), which exhibit photoluminescence (PL) covering from visible to near-infrared (NIR). The PL colors under excitations of 254 and 365 nm are notably different due to the changed relative emission intensities of self-trapped excitons (STEs) and Mn^(2+) d–d transition. Moreover, under the excitation of a NIR laser, the MYE-DP exhibits upconversion (UC) emissions of Mn^(2+) and Er^(3+). After ceasing the excitation, the long-lived trapped electrons can be thermally released to Mn^(2+) and Er^(3+) ions, resulting in both visible and NIR afterglow. Based on multi-modal emissions of the MYE-DP, we demonstrate a five-level anti-counterfeiting strategy, which significantly increases the anti-counterfeiting security. In addition, this work provides valuable insights into the energy transfer between STEs, Mn^(2+), Ln^(3+), and traps, laying a solid foundation for future development of new lead-free perovskites.

关键词： anti-counterfeiting photoluminescence self-trapped excitons upconversion

来源：评论

学校读者我要写书评

暂无评论

Image Generation of Tomato Leaf Disease Identification Based on Small-ACGAN

引用

computers, Materials & Continua 2023年第7期76卷 175-194页

作者： Huaxin Zhou Ziying Fang Yilin Wang Mengjun Tong School of Mathematics and Computer Science Zhejiang A&F UniversityHangzhou311300China Zhejiang Provincial Key Laboratory of Forestry Intelligent Monitoring and Information Technology Research Hangzhou311300China School of Humanities and Law Zhejiang A&F UniversityHangzhou311300China Department of Computer Science and Engineering Lehigh UniversityPA18015USA

Plant diseases have become a challenging threat in the agricultural *** learning approaches for plant disease detection and classification have been adopted to detect and diagnose these diseases ***,deep learning entails extensive data for training,and it may be challenging to collect plant *** though plant datasets can be collected,they may be uneven in *** a result,the problem of classification model overfitting *** study targets this issue and proposes an auxiliary classifier GAN(small-ACGAN)model based on a small number of datasets to extend the available ***,after comparing various attention mechanisms,this paper chose to add the lightweight Coordinate Attention(CA)to the generator module of Auxiliary Classifier GANs(ACGAN)to improve the image ***,a gradient penalty mechanism was added to the loss function to improve the training stability of the *** show that the proposed method can best improve the recognition accuracy of the classifier with the doubled *** AlexNet,the accuracy was increased by 11.2%.In addition,small-ACGAN outperformed the other three GANs used in the ***,the experimental accuracy,precision,recall,and F1 scores of the five convolutional neural network(CNN)classifiers on the enhanced dataset improved by an average of 3.74%,3.48%,3.74%,and 3.80%compared to the original ***,the accuracy of MobileNetV3 reached 97.9%,which fully demonstrated the feasibility of this *** general experimental results indicate that the method proposed in this paper provides a new dataset expansion method for effectively improving the identification accuracy and can play an essential role in expanding the dataset of the sparse number of plant diseases.

关键词： Deep learning ACGAN CA gradient penalty tomato diseases identification

来源：评论

学校读者我要写书评

暂无评论

Consistency-aware unsupervised label learning for cross-domain person re-identification

引用

Multimedia Tools and Applications 2024年 1-20页

作者： Geng, Yanbing Lian, Yongjian Cui, Fangshu Zhang, Xiaowei Zhou, Mingliang Zhang, Geao School of Data Science and Technology North University of China Shanxi Taiyuan030051 China Shandong Key Laboratory of Intelligent Information Processing School of Computer Science and Technology Qingdao University Qingdao266071 China School of Computer Science Chongqing University 174 Shazheng Street Shapingba District Chongqing400044 China College of Information Science and Engineering Northeastern University 11 Lane 3 Wenhua Road Heping District Liaoning Shenyang110819 China

Un-refined pseudo labels always disturb the cross-domain Re-ID performance in unsupervised clustering methods. In this paper, we propose a consistency-aware unsupervised label learning network to refine noisy labels for promising domain adaptation. Specifically, we use a hetero-generated label consistency constraint to mine possible label information, keep a reference consistency of the target pairs on the relative comparative characteristics. We then use a cross-granularity attention consistency constraint to refine the pseudo labels meanwhile learning multi-granularity discriminative representation, keeping a self-similarity consistency of the corresponding parts on the discriminative regions. Our model is fine-tuned by the refined pseudo-labels to reduce the domain gap while coping with the intra-domain variation. Experimental results demonstrate that the proposed method can achieve superior performance on several benchmark datasets. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Denoising Diffusion Path: Attribution Noise Reduction with An Auxiliary Diffusion Model 38

Denoising Diffusion Path: Attribution Noise Reduction with A...

引用

38th Conference on Neural information processing Systems, NeurIPS 2024

作者： Lei, Yiming Li, Zilong Zhang, Junping Shan, Hongming Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University China Institute of Science and Technology for Brain-Inspired Intelligence MOE Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence MOE Frontiers Center for Brain Science Fudan University China

The explainability of deep neural networks (DNNs) is critical for trust and reliability in AI systems. Path-based attribution methods, such as integrated gradients (IG), aim to explain predictions by accumulating gradients along a path from a baseline to the target image. However, noise accumulated during this process can significantly distort the explanation. While existing methods primarily concentrate on finding alternative paths to circumvent noise, they overlook a critical issue: intermediate-step images frequently diverge from the distribution of training data, further intensifying the impact of noise. This work presents a novel Denoising Diffusion Path (DDPath) to tackle this challenge by harnessing the power of diffusion models for denoising. By exploiting the inherent ability of diffusion models to progressively remove noise from an image, DDPath constructs a piece-wise linear path. Each segment of this path ensures that samples drawn from a Gaussian distribution are centered around the target image. This approach facilitates a gradual reduction of noise along the path. We further demonstrate that DDPath adheres to essential axiomatic properties for attribution methods and can be seamlessly integrated with existing methods such as IG. Extensive experimental results demonstrate that DDPath can significantly reduce noise in the attributions-resulting in clearer explanations-and achieves better quantitative results than traditional path-based methods. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An experimental study of monotone acoustics in Huazang Temple Dialect of Tianzhu 6

An experimental study of monotone acoustics in Huazang Templ...

引用

6th International Conference on Intelligent Computing, Communication, and Devices, ICCD 2023

作者： Ding, Haiying Guo, Lei Zhang, Zhiwen Key Laboratory of China's Ethnic Languages and Information Technology of Ministry of Education Northwest Minzu University Gansu Lanzhou730000 China Gansu Provincial Key Laboratory of Intelligent Processing of National Languages Northwest Minzu University Gansu Lanzhou730000 China

ISBN: (数字)9781510666269

ISBN: (纸本)9781510666252

Tianzhu Tibetan Autonomous County is located at the eastern end of the Hexi Corridor. Huazangsi Town is the seat of the current Tianzhu County. According to the atlas of Chinese dialects, Huazangsi dialect belongs to the Hexi section of Lanyin Mandarin. Its tone system has some distinctive tonal characteristics in the three aspects of single tone, continuous tone sandhi and soft tone. This paper analyzes the characteristics of single tone in Tianzhu Huazang Temple dialect through the research method of experimental phonetics, and summarizes the tonal types, values and areas of single tone in Tianzhu Huazang Temple dialect, providing a teaching basis for the acquisition of Mandarin in this region. At the same time, it explores the development and change of the tone of Tianzhu Huazang Temple dialect under the contact with multi-national languages, analyzes the influence of Mandarin tone on the tone of Tianzhu Huazang Temple dialect, and makes a simple prediction of the future development trend of the tone of Tianzhu Huazang Temple dialect. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Linguistics

来源：评论

学校读者我要写书评

暂无评论

Research on Classroom Behavior Target Detection Algorithm based on YOLOv7 6

Research on Classroom Behavior Target Detection Algorithm ba...

引用

6th IEEE Advanced information Management, Communicates, Electronic and Automation Control Conference, IMCEC 2024

作者： Qiu, Wenke Wu, Xiaoming Liu, Xiangzhi Computer Science and Qilu University of Technology Shandong Academy of Sciences ShanDong Jinan 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 Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China

ISBN: (纸本)9798350316520

The integration of video information for the purpose of detecting students' behavior in the classroom, with the aim of enhancing teaching efficiency and maintaining a stable classroom environment, offers significant assistance. However, existing models usually struggle to achieve good accuracy due to the lack of datasets, dense targets, interclass occlusion, and other issues. To address these difficulties, the CD-YOLO classroom behavior detection algorithm is proposed in this paper. And the classroom behavior dataset (DSL-Dataset) is created. We propose a loss function named VAIoU, which can be combined with vector ratio to filter the prediction box. To further improve the detection accuracy of occluded targets, we propose an attention module CM module with command feature fusion. Moreover, in this paper, we improve the convolutional kernel to design a lightweight convolutional kernel FFconv. Experimental results on DSL-Dataset show that CD-YOLO outperforms existing one-stage detection models in terms of detection accuracy. © 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：