检索结果-内蒙古大学图书馆

RGB-guided hyperspectral image super-resolution with deep progressive learning

CAAI Transactions on Intelligence Technology 2024年第3期9卷 679-694页

作者： Tao Zhang Ying Fu Liwei Huang Siyuan Li Shaodi You Chenggang Yan School of Computer Science and Technology Beijing Institute of TechnologyBeijingChina Satellite Information Intelligent Processing and Application Research Laboratory Beijing Institute of Remote SensingBeijingChina Key Laboratory of Spectral Imaging Technology Xi'an Institute of Optics and Precision Mechanics of Chinese Academy of SciencesXi'anChina Institute of Informatics University of AmsterdamAmsterdamNetherlands School of Communication Engineering Hangzhou Dianzi UniversityHangzhouChina

Due to hardware limitations,existing hyperspectral(HS)camera often suffer from low spatial/temporal ***,it has been prevalent to super-resolve a low reso-lution(LR)HS image into a high resolution(HR)HS image with a HR RGB(or mul-tispectral)image *** approaches for this guided super-resolution task often model the intrinsic characteristic of the desired HR HS image using hand-crafted ***,researchers pay more attention to deep learning methods with direct supervised or unsupervised learning,which exploit deep prior only from training dataset or testing *** this article,an efficient convolutional neural network-based method is presented to progressively super-resolve HS image with RGB image ***-ically,a progressive HS image super-resolution network is proposed,which progressively super-resolve the LR HS image with pixel shuffled HR RGB image ***,the super-resolution network is progressively trained with supervised pre-training and un-supervised adaption,where supervised pre-training learns the general prior on training data and unsupervised adaptation generalises the general prior to specific prior for variant testing *** proposed method can effectively exploit prior from training dataset and testing HS and RGB images with spectral-spatial *** has a good general-isation capability,especially for blind HS image *** experimental results show that the proposed deep progressive learning method out-performs the existing state-of-the-art methods for HS image super-resolution in non-blind and blind cases.

关键词： computer vision deep neural networks image processing image resolution unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Near-field Source DOA Estimation Algorithm Based on De-impact Function under Impulse Noise 7

Near-field Source DOA Estimation Algorithm Based on De-impac...

引用

7th IEEE International Conference on Electronic information and Communication Technology, ICEICT 2024

作者： Xu, Xingchao Pang, Baohe Li, Yingsong Li, Liping Zou, Dingcheng Zlatanov, Nikola Harbin Engineering University College of Information and Communication Engineering Harbin150001 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China Innopolis University Faculty of Computer and Engineering Sciences Innopolis Russia

ISBN: (纸本)9798350384437

In addressing the issue of localizing near-field source signals in the presence of impulse noise, this manuscript introduces a novel de-impact function designed for preprocessing received signals to alleviate the interference caused by impulse noise. Simulation experiments verify the effectiveness of the proposed de-impact function in effectively suppressing impulse noise. Furthermore, to augment estimation precision, a novel algorithm for near-field source localization is proposed. Building upon the framework of correlation entropy theory, a new correntropy covariance matrix is formulated to replace the original signal covariance matrix for signal processing. Through a succession of low-bias approximations between near-field and far-field scenarios, the algorithm converts the original 2-D search into 1-D operations. Additionally, the conventional spectral peak search is replaced by polynomial solving to further mitigate the computational complexity of the algorithm. © 2024 IEEE.

关键词： Impulse noise

来源：评论

学校读者我要写书评

暂无评论

Diffusion Recursive Minimum Error Entropy Algorithm 22

Diffusion Recursive Minimum Error Entropy Algorithm

引用

6th International Conference on Digital Signal processing, ICDSP 2022

作者： Cai, Peng Lin, Dongyuan Yan, Wenxing Wang, Shiyuan Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Southwest University Chongqing400715 China

ISBN: (纸本)9781450395809

Distributed estimation algorithms under the mean square error (MSE) criterion have received a lot of attention due to their simplicity and good estimation performance for distributed estimates in Gaussian noise environments. However, when the noise does not obey the Gaussian distribution, the performance of these algorithms can degrade seriously. In this paper, a robust distributed estimation algorithm, called the diffusion recursive minimum error entropy (DRMEE), is proposed by combining the diffusion strategy and the minimum error entropy (MEE) criterion. Since MEE criterion has been proved to be insensitive to many types of non-Gaussian noise models, the proposed algorithm is expected to improve the robustness of distributed estimation algorithms under the MSE criterion, significantly. The superior performance of DRMEE is confirmed by simulation results in the scenario of system identification with two multi-peak distribution noise environments. © 2022 ACM.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Fault-Tolerant Control for Underwater Vehicle with Actuator Saturation and Faults 5th

Fault-Tolerant Control for Underwater Vehicle with Actuato...

引用

5th China Conference on intelligent Networked Things, CINT 2022

作者： Li, Hongfei Xu, Jing Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Southwest University Chongqing400715 China

ISBN: (纸本)9789811989148

Underwater vehicle system, as a kind of special machine capable of underwater resource exploration, submarine pipeline maintenance, marine environment reconnaissance and submarine rescue, is a common tool in modern marine exploitation. Underwater vehicles play an important role in the survey and exploration of marine resource. The fault tolerant control for underwater vehicle system with external disturbance and actuator faults is studied in this paper. The fault observer can estimate the fault in the existence of disturbance environment. A sufficient condition for the existence of fault observer is proposed which guarantees the stability of the closed-loop system under actuator faults. Moreover, a fault-tolerant controller is developed to compensate for the failure effects on the system by updating the design feedback matrices online. For the fault-tolerant controller, Lyapunov function is used to obtain the stability for underwater vehicle system about actuator saturation. Finally, an example is included to show the effectiveness of the presented theory. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Lyapunov functions

来源：评论

学校读者我要写书评

暂无评论

Competition on robust deep learning

引用

National Science Review 2023年第6期10卷 13-15页

作者： Yinpeng Dong Chang Liu Wenzhao Xiang Hang Su Jun Zhu Department of Computer Science and Technology Institute for AI Tsinghua-Bosch Joint ML Center THBI Lab BNRist Center Tsinghua University Institute of Image Communication and Networks Engineering in the Department of Electronic Engineering (EE) Shanghai Jiao Tong University Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Peng Cheng Laboratory Pazhou Laboratory (Huangpu)

PROBLEM In recent years,the rapid development of artificial intelligence (AI) technology,especially machine learning and deep learning, is profoundly changing human production and *** various fields,such as robotics,face recognition,autonomous driving and healthcare,AI is playing an important ***,although AI is promoting the technological revolution and industrial progress,its security risks are often *** studies have found that the wellperforming deep learning models are extremely vulnerable to adversarial examples [1-3].The adversarial examples are crafted by applying small,humanimperceptible perturbations to natural examples,but can mislead deep learning models to make wrong *** vulnerability of deep learning models to adversarial examples can raise security and safety threats to various realworld applications.

关键词： robustness adversarial example adversarial training deep learning

来源：评论

学校读者我要写书评

暂无评论

Safety and Ethical Concerns of Large Language Models 22

Safety and Ethical Concerns of Large Language Models

引用

22nd Chinese National Conference on Computational Linguistics, CCL 2023

作者： Xi, Zhiheng Zheng, Rui Gui, Tao School of Computer Science Fudan University Shanghai China Shanghai Key Laboratory of Intelligent Information Processing Shanghai China Institute of Modern Languages and Linguistics Fudan University Shanghai China

ISBN: (纸本)9781713889915

Recent months have witnessed significant progress in the field of large language models (LLMs). Represented by ChatGPT and GPT-4, LLMs perform well in various natural language processing tasks and have been applied to many downstream applications to facilitate people’s lives. However, there still exist safety and ethical concerns. Specifically, LLMs suffer from social bias, robustness problems, and poisoning issues, all of which may induce LLMs to spew harmful contents. We propose this tutorial as a gentle introduction to the safety and ethical issues of LLMs. © 2023 China National Conference on Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Structure-constrain Source Free Domain Adaptation with Regularized Knowledge Distillation of Source Model 13

Structure-constrain Source Free Domain Adaptation with Regul...

引用

13th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2024

作者： Yang, Dan Peng, Xin Su, Cheng Tan, Dayu Chen, Chaoyang Zhong, Weimin Ministry of Education East China University of Science and Technology Key Laboratory of Smart Manufacturing in Energy Chemical Process Shanghai200237 China Ministry of Education Anhui University Key Laboratory of Intelligent Computing and Signal Processing Anhui Hefei230601 China School of Information and Electrical Engineering Hunan University of Science and Technology Xiangtan China

ISBN: (纸本)9798350361674

Transfer learning aims to leverage the knowledge of the source domain to help the learning of unlabeled target domain models. However, all conventional transfer learning methods assume that samples from source and target domains are always freely accessible. However, this assumption is rarely plausible in real-world due to data privacy. To combat this challenge, we introduce Structure-constrain Source Free Domain Adaptation with regularized Knowledge Distillation of source model (SSFDA-KD). Our method is based on the observations that a deterministic classification result can be obtained when the target data distribution aligns with the source data distribution, and a well-trained model not only yields a deterministic classification for a sample but also has clear category boundaries, which implies samples that are close together belong to the same category. From those, we first generate the source model with labeled source data, which is regarded as a well-trained model. Then, we identify target prototypes with lower self-entropy and assign the pseudo-labels to other samples according to the neighborhood structure. Finally, we refine the target model by minimizing prediction loss, constraining internal structure via triplet loss, and reducing knowledge distillation loss. Experiments of fault diagnosis based on WWTPs are conducted to validate its effectiveness. © 2024 IEEE.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

Video Rumor Classification Based on Multi-modal Theme and keyframe Fusion 17th

Video Rumor Classification Based on Multi-modal Theme and ...

引用

17th CCF Conference on Computer Supported Cooperative Work and Social Computing, ChineseCSCW 2022

作者： You, Jinpeng Lin, Yanghao Lin, Dazhen Cao, Donglin Artificial Intelligence Department Xiamen University Xiamen361005 China The Key Laboratory of Cognitive Computing and Intelligent Information Processing of Fujian Education Institutions Wuyi University Wuyishan354300 China

ISBN: (纸本)9789819923557

In recent years, short video platforms have become the main source of online rumors. According to the statistics of Shanghai online rumor refutation platform in 2021, the number of short video rumors was about five times that of short video rumors in 2020, which makes it necessary to detect rumors of short videos. At present, short video rumor detection has the problem of multi-modal information fusion, the traditional multi-modal fusion uses deep learning to obtain the underlying features of multi-modality and then aggregate them into cross-modal features. However, there are distortions of theme and tampering with key-frame in rumor videos. Therefore, short video rumors need to learn features from the perspective of theme and key-frame. Aiming at the problem of multi-modal information fusion of short video rumors, this paper proposes a short video rumor detection model (TKCM) based on theme and key-frame. It uses aggregation network to obtain the theme feature of video, attention network to obtain the key-frame feature, and fuses multi-modality by modal adjustment mechanism for short video rumor detection. Experimental results show that the F1 score of the proposed method on the short video rumor dataset is improved by 2%–5% compared with some state-of-the-art video classification models. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Specific Emitter Identification based on CNN and Transformer 5

Specific Emitter Identification based on CNN and Transformer

引用

5th International Academic Exchange Conference on Science and Technology Innovation, IAECST 2023

作者： Wang, Bin Gao, Ning Wang, Feng The 38th Research Institute of China Electronics Technology Group Corporation Key Laboratory of Aperture Array and Space Application Key Laboratory of Intelligent Information Processing Anhui Hefei230088 China Hefei University of Technology School of Computer and Information Hefei230601 China

ISBN: (纸本)9798350357738

Specific emitter identification(SEI) plays an increasingly crucial and potential role in both military and civilian scenarios. It refers to a process to discriminate individual emitters from each other by analyzing extracted characteristics from given radio signals. In this paper, we present a novel radiation source identification method named CNNFormer based on a hybrid architecture of Convolutional Neural Network and Transformer, harnessing the strengths of both architectures to enhance feature extraction and sequence modeling. We demonstrate the effectiveness of our approach on simulation datasets, achieving state-of-the-art accuracy in emitter identification. We showcase outstanding performance of our method on simulation datasets, achieving 98.29% three-class identification accuracy the emitter dataset with three devices and 97.60% ten-class identification accuracy on an RF fingerprint dataset with ten XSPR transmitters. Furthermore, our model allows for insight into the key features contributing to identification. This work contributes to enhancing the security and reliability of wireless communication systems. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A study on low-dose CT image denoising method based on similar block learning 5

A study on low-dose CT image denoising method based on simil...

引用

2023 5th International Conference on information Science, Electrical, and Automation Engineering, ISEAE 2023

作者： Fu, Huijuan Xi, Xiaoqi Han, Yu Zhu, Linlin Liu, Mengnan Tan, Siyu Liu, Chang Li, Lei Yan, Bin Henan Key Laboratory of Imaging and Intelligent Processing Pla Strategic Support Force Information Engineering University Zhengzhou45000 China Zhengzhou University School of Software Zhengzhou45000 China

ISBN: (纸本)9781510667440

X-ray tomographic imaging has become an important analytical tool with a wide range of applications. It is inevitable that noise is introduced in CT images, and noise reduction is necessary. To solve this problem, we considered to use the nonlocal property of similar block search and proposed a deep learning network based on similar block learning for noise reduction of micro CT short exposure time scanned images to improve the scanning efficiency while ensuring high quality imaging. The method uses the output of the nonlocal method as a data preprocessing algorithm by combining a nonlocal block matching algorithm with a convolutional neural network, and uses a residual channel attention mechanism to learn the features after feature extraction, which reduces noise while preserving image details. Experimental results show that the method can remove noise from CT images quickly and effectively, and compared with the classical CPCE noise reduction method, the method improves the PSNR index by 1.52 dB, which is consistent with the theoretical assumption. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Noise abatement

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：