检索结果-内蒙古大学图书馆

2022 Findings of the Association for Computational Linguistics: EMNLP 2022

作者： Liu, Xiangyang Sun, Tianxiang Huang, Xuanjing Qiu, Xipeng School of Computer Science Fudan University China Shanghai Key Laboratory of Intelligent Information Processing Fudan University China

Prompt tuning is a parameter-efficient tuning (PETuning) method for utilizing pre-trained models (PTMs) that simply prepends a soft prompt to the input and only optimizes the prompt to adapt PTMs to downstream tasks. Although it is parameter- and deployment-efficient, its performance still lags behind other state-of-the-art PETuning methods. Besides, the training cost of prompt tuning is not significantly reduced due to the back-propagation through the entire model. Through empirical analyses, we shed some light on the lagging performance of prompt tuning and recognize a trade-off between the propagation distance from label signals to the inserted prompt and the influence of the prompt on model outputs. Further, we present Late Prompt Tuning (LPT) that inserts a late prompt into an intermediate layer of the PTM instead of the input layer or all layers. The late prompt is obtained by a neural prompt generator conditioned on the hidden states before the prompt insertion layer and therefore is instance-dependent. Through extensive experimental results across various tasks and PTMs, we show that LPT can achieve competitive performance to full model tuning and other PETuning methods under both full-data and few-shot scenarios while possessing faster training speed and lower memory cost. © 2022 Association for Computational Linguistics.

关键词： Backpropagation

来源：评论

学校读者我要写书评

暂无评论

Efficient DOA Estimation Based on Cauchy Loss Variable Step Size Algorithm 6

Efficient DOA Estimation Based on Cauchy Loss Variable Step ...

引用

6th IEEE International Conference on Electronic information and Communication Technology, ICEICT 2023

作者： Xu, Xingchao Li, Yingsong College of Information and Communications Engineering Harbin Engineering University Harbin150001 China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei China

ISBN: (纸本)9798350399059

The Cauchy loss function is robust to large outliers and has successful applications in signal processing. In this paper, a DOA estimation algorithm based on adaptive zero technology is proposed, which updates the weight of the filter by applying the Cauchy loss function, and further improves the algorithm performance by using the variable step size method. The algorithm step size is adjusted by accumulating errors and establishing a nonlinear function with instantaneous errors. The DOA estimation ability, estimation error and accuracy of the improved Cauchy algorithm in the impulse noise environment are analyzed. The algorithm is verified by simulation experiments. © 2023 IEEE.

关键词： Impulse noise

来源：评论

学校读者我要写书评

暂无评论

Privacy protection oriented on data stream computing

Privacy protection oriented on data stream computing

引用

2022 International Conference on Computer Application and information Security, ICCAIS 2022

作者： He, Renjie Zheng, Xianghan Wang, Gong School of Computer and Big Data Fuzhou University Fujian Fuzhou China The Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fujian Fuzhou China

ISBN: (纸本)9781510663459

Data security has always been one of the public concerns, and homomorphic encryption technology, as one of the effective means to ensure data security, has always been a hot topic of academic research. Traditional machine learning is trained in a batch environment. In practice, data owners tend to outsource data and model training tasks to third-party clouds with huge computing resources, but data outsourcing carries the risk of privacy leakage. Therefore, in order to prevent this situation, an effective method is to encrypt the data before the outsourcing, and the third-party cloud trains the machine model of the ciphertext data. This method has special requirements for encryption algorithms which should support computation directly on the ciphertext data. This paper presents a novel data flow computing privacy protection framework based on the homomorphic encryption algorithm CKKS and the flow data processing engine Flink, called SDPPF (Streaming Data Privacy Protection on Flink). The proposed framework supports the functions of data stream encryption, decryption and ciphertext computing, and expands the functions of vector point multiplication and array sum operation on the basic simultaneous operation supported by the original CKKS algorithm. This paper also selects a classical machine learning algorithm: KNN algorithm, combined with the homomorphic encryption algorithm CKKS to realize the privacy protection machine learning algorithm. © 2023 SPIE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale and Improved Skip Connections Network for Skin Lesion Segmentation 9

Multi-Scale and Improved Skip Connections Network for Skin L...

引用

9th International Conference on intelligent Computing and Signal processing, ICSP 2024

作者： Zhang, Botao Chen, Jun College of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China

ISBN: (纸本)9798350376548

To solve the problem that the current skin lesion segmentation networks have a poor segmentation accuracy when lesion areas are of different shapes and sizes and low contrast at the edge areas, based on U-Net, we present a skin lesion segmentation network based on multi-scale and improved skip connections. Firstly, a multi-scale feature enhancement module is designed to replace the U-Net's 3× 3 convolution blocks, which can improve the feature extraction ability of the network about lesion areas of different shapes and sizes. Secondly, a lesion attention module is introduced into the skip connection to improve the semantic expression of low-level features and the location attention of high-level features, which can improve the fine-grained information transmission efficiency at the skip connection. Finally, a new hybrid loss function is designed to calculate the label and the edge loss of lesion areas, which improves the ability of the network to segment lesion areas and edges. Experiments are conducted on the ISIC2017 and ISIC2018 datasets, and the results prove that our method have a higher segmentation accuracy in skin lesion segmentation. © 2024 IEEE.

关键词： Problem solving

来源：评论

学校读者我要写书评

暂无评论

HCU-Net: An Efficient Fully Convolutional Neural Network for Thyroid Nodules Ultrasound Image Segmentation

HCU-Net: An Efficient Fully Convolutional Neural Network for...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Ren, Mengxi Liu, Jun School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan China

ISBN: (纸本)9781665410205

Thyroid nodules, which can manifest as solitary or multiple growths, are among the most prevalent diseases with a high incidence rate. When examining thyroid nodules, ultrasound is typically the first step. Ultrasound image segmentation of thyroid nodules can assist physicians in diagnosis. However, the following three factors limit the development of thyroid nodule segmentation: (1) most of the existing studies optimize the segmentation of single nodules, and the incidence of multiple nodules is higher, so the segmentation of multiple nodules is also very important;(2) the ultrasound image of thyroid nodules is difficult to segment because of its low resolution and fuzzy boundary;(3) Due to the small data set of thyroid nodule ultrasound, in such a small dataset, attention mechanisms may be prone to overfitting, resulting in poorer generalization performance. Therefore, the attention-based model may not be suitable for the segmentation of thyroid nodules. Hence, we propose Hybrid Convolutional U-Net (HCU-Net), a simple and strong fully convolutional neural network for the segmentation of single or multiple thyroid nodules. HCU-Net incorporates a large receptive field to ensure accurate and stable segmentation. Specifically, we design Hybrid Branch Block to enhance the network's feature extraction capability for single or multiple nodules in ultrasound images by integrating multi-scale features. Furthermore, we add Enhanced ConvNeXt Blocks to the U-Net's final layer, enabling the extraction of global contextual information for segmentation performance. The Experimental results show that our proposed method can effectively improve these issues on two publicly available datasets. In addition, compared to attention-based models, our network is simpler and more suitable for small datasets like ultrasound images. © 2024 IEEE.

关键词： Ultrasonic imaging

来源：评论

学校读者我要写书评

暂无评论

LLaMA-Unidetector: An LLaMA-Based Universal Framework for Open-Vocabulary Object Detection in Remote Sensing Imagery

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Xie, Jianlin Wang, Guanqun Zhang, Tong Sun, Yikang Chen, He Zhuang, Yin Li, Jun Beijing100081 China Peking University National Key Laboratory for Multimedia Information Processing Beijing100871 China China University of Geosciences School of Computer Science Hubei Key Laboratory of Intelligent Geo-Information Processing Wuhan430078 China

The object detection is a crucial task in the computer vision for remote sensing applications. However, the reliance of traditional methods on predefined and trained object categories limits their applicability in open-world scenarios. A key challenge in open-vocabulary object detection lies in accurately identifying unseen objects. Existing approaches often focus solely on detecting object locations, struggling to recognize the categories of previously unseen targets. To address this issue, we propose a novel benchmark, where models are trained on known base classes and evaluated on their performance in detecting and recognizing unseen or novel classes. To this end, we introduce LLaMA-Unidetector, a universal framework that incorporates textual information into a closed-set detector, enabling the generalization to open-set scenarios. Our LLaMA-Unidetector leverages a decoupled learning strategy that separates localization and recognition. In the first stage, a class-agnostic detector identifies objects, distinguishing only between foreground and background. In the second stage, the detected foreground objects are passed through TerraOV-LLM, a multimodal large language model (MLLM), for recognition, utilizing the strong generalization capabilities of large language models to infer the correct categories. We propose a self-built vision question answering (VQA) remote sensing dataset, TerraVQA, and conduct extensive experiments on the NWPU-VHR10, DOTA1.0, and DIOR datasets. The LLaMA-Unidetector achieves impressive results, with a performance of 75.46% AP, 50.22% AP, and 51.38% AP on the zero-shot detection benchmarks for the NWPU-VHR10, DOTA1.0, and DIOR datasets, respectively. © 1980-2012 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

keycap character detection model based on target classification 7

Keycap character detection model based on target classificat...

引用

2024 7th International Conference on intelligent Manufacturing and Automation, IMA 2024

作者： Xiong, Taiping Zhu, Zhiguo Wang, Tinghao School of Computer and Information Security Guilin University of Electronic Technology Guangxi Guilin541004 China Key Laboratory of Image Graphics and Intelligent Processing in Guangxi Guilin University of Electronic Technology Guangxi Guilin541004 China

The production process of keycaps may result in surface character defects. The existing keycap character defect detection technology has low efficiency and accuracy, hindering the automation of keycap manufacturing. Addressing the challenge of extracting the entire keyboard from illuminated regions, this paper proposes a method using image feature points for template matching to extract the region of interest. Subsequently, leveraging prior knowledge, the paper addresses character segmentation and extraction on the keyboard. For character detection, the paper preprocesses images and classifies them by using an S-VGG network, yielding corresponding labels. © Published under licence by IOP Publishing Ltd.

关键词： Template matching

来源：评论

学校读者我要写书评

暂无评论

Noise-tolerant fixed-time leader-follower consensus controller design for multi-agent systems via fuzzy-neural-network

引用

Neural Computing and Applications 2025年 1-23页

作者： Dai, Jianhua Tan, Ping Xiao, Lin Wang, Zidong He, Yongjun Zuo, Qiuyue Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing MOE-LCSM Hunan Normal University Hunan Changsha410081 China Department of Computer Science Brunel University London UxbridgeUB8 3PH United Kingdom

The leader-follower consensus control problem in multi-agent systems (MASs) is critical and has received significant attention. However, the simultaneous achievement of fixed-time stability and robustness is often challenging in MASs due to their inherent complexity and uncertainty. This paper developed a controller based on the proposed noise-tolerant fixed-time fuzzy neural network (NF-FNN) model to realize the leader-follower consensus of MASs. Specifically, the introduction of an integral error term makes the NF-FNN model have powerful noise tolerance, and a fuzzy gain parameter generated by the Takagi-Sugeno fuzzy logic system makes the NF-FNN model have fuzzy adaptiveness. In addition, a new partition-sign-by-power activation function is developed to ensure fixed-time stability of the NF-FNN model. Theoretical analysis and comparative simulations confirm the superb swift stability and excellent noise tolerance of controllers based on the NF-FNN model for achieving the leader-follower consensus of MASs, as compared with existing methods. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Fuzzy neural networks

来源：评论

学校读者我要写书评

暂无评论

Design of Control Circuit for Active Metasurface Based on Varactor Diode

Design of Control Circuit for Active Metasurface Based on Va...

引用

2023 International Applied Computational Electromagnetics Society Symposium, ACES-China 2023

作者： Zhang, Yue Liu, Yuefei Yang, Guohui Zhang, Kuang Li, Yingsong School of Electronics and Information Engineering Harbin Institute of Technology Harbin China Ministry of Education Anhui University Key Laboratory of Intelligent Computing and Signal Processing Hefei China

ISBN: (纸本)9781733509657

A control circuit for active metasurface based on varactor diode is designed in this paper. By varying the reverse bias voltage on the varactor diode, the designed circuit can regulate the additional phase of the active meta-atoms. The circuit adopts a form of one master and multiple slaves, which can simultaneously control the bias voltage of 960 meta-atoms. Each slave can control up to 64 channels. The control accuracy is 0.04V. The power consumption of a single slave is 160mW. Though experiment verification, the circuit has a good effect in controlling the beam deflection of the metasurface and generating OAM beams. © 2023 Applied Computational Electromagnetics Society (ACES).

关键词： Timing circuits

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Collaborative Search with Adaptive Heuristics and Weight Vectors for Aerospace Multi-objective Optimal Control Problems 13

Multi-Agent Collaborative Search with Adaptive Heuristics an...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Cao, Li Wang, Maocai Parsonage, Ben Maddock, Christie Dai, Guangming China University of Geosciences School of Computer China China University of Geosciences Hubei Key Laboratory of Intelligent Geo-Information Processing Wuhan430074 China University of Strathclyde Department of Mechanical & Aerospace Engineering Glasgow United Kingdom

ISBN: (纸本)9798350308365

Optimal control optimization problems are relative complex and widespread in aerospace field. The evolutionary algorithms are useful methods in solving those problems and Multi Agent Collaborative Search Algorithm (MACS) is a effective method for them. It's a mix of evolution approach and gradient-based method. The evolution part includes individualistic and social heuristics with different characteristics. The latest version of MACS is Multi-Agent Collaborative Search optimal control algorithm (MACSoc) which has good performance on multi-objective optimal control problems. However, this algorithm has two important limitations: The two kinds of heuristics are performed evenly on each individuals which may weaken the algorithm efficiency;The Pareto Front in objective space may be uneven but the initial weight vectors of MACSoc is even. This may lead to diversity losing. We proposed a new algorithm MACSoc with adaptive heuristics and weight vectors (MACSoc-AH) which contains the following improvements: The two kinds of heuristics are executed on individuals based on the their characteristics;A weight vector adjusting process with a original trigger is added to improve diversity. The new algorithm is compared with MACSoc and shows competitive results. © 2024 IEEE.

关键词： Aerospace industry

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：