检索结果-内蒙古大学图书馆

International Conference on Computer Vision (ICCV)

作者： Siyuan Liang Baoyuan Wu Yanbo Fan Xingxing Wei Xiaochun Cao Institute of Information Engineering Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China School of Data Science The Chinese University of Hong Kong Shenzhen China Secure Computing Lab of Big Data Shenzhen Research Institute of Big Data Shenzhen China Tencent Shenzhen China Institute of Artificial Intelligence Hangzhou Innovation Institute Beihang University Beijing China

ISBN: (纸本)9781665428132

Object detection has been widely used in many safety- critical tasks, such as autonomous driving. However, its vulnerability to adversarial examples has not been sufficiently studied, especially under the practical scenario of black-box attacks, where the attacker can only access the query feedback of predicted bounding-boxes and top- 1 scores returned by the attacked model. Compared with black-box attack to image classification, there are two main challenges in black-box attack to detection. Firstly, even if one bounding-box is successfully attacked, another sub- optimal bounding-box may be detected near the attacked bounding-box. Secondly, there are multiple bounding- boxes, leading to very high attack cost. To address these challenges, we propose a Parallel Rectangle Flip Attack (PRFA) via random search. We explain the difference between our method with other attacks in Fig. 1. Specifically, we generate perturbations in each rectangle patch to avoid sub-optimal detection near the attacked region. Besides, utilizing the observation that adversarial perturbations mainly locate around objects’ contours and critical points under white-box attacks, the search space of attacked rectangles is reduced to improve the attack efficiency. Moreover, we develop a parallel mechanism of attacking multiple rectangles simultaneously to further accelerate the attack process. Extensive experiments demonstrate that our method can effectively and efficiently attack various popular object detectors, including anchor-based and anchor- free, and generate transferable adversarial examples.

关键词： Costs Perturbation methods Detectors Object detection Predictive models Search problems Task analysis

来源：评论

学校读者我要写书评

暂无评论

When Evolutionary Computation Meets Privacy

arXiv

引用

arXiv 2023年

作者： Zhao, Bowen Chen, Wei-Neng Li, Xiaoguo Liu, Ximeng Pei, Qingqi Zhang, Jun Guangzhou Institute of Technology Xidian University Guangzhou China The School of Computer Science and Technology South China University of Technology Guangzhou China The School of Computing and Information Systems Singapore Management University Singapore Singapore The College of Computer and Data Science Fuzhou University Fujian China Cyberspace Security Research Center Peng Cheng Laboratory Shenzhen China School of Telecommunications Engineering Xidian University Xian China Zhejiang Normal University Jinhua China Hanyang University Ansan Korea Republic of

Recently, evolutionary computation (EC) has been promoted by machine learning, distributed computing, and big data technologies, resulting in new research directions of EC like distributed EC and surrogate-assisted EC. These advances have significantly improved the performance and the application scope of EC, but also trigger privacy leakages, such as the leakage of optimal results and surrogate model. Accordingly, evolutionary computation combined with privacy protection is becoming an emerging topic. However, privacy concerns in evolutionary computation lack a systematic exploration, especially for the object, motivation, position, and method of privacy protection. To this end, in this paper, we discuss three typical optimization paradigms (i.e., centralized optimization, distributed optimization, and data-driven optimization) to characterize optimization modes of evolutionary computation and propose BOOM (i.e., oBject, mOtivation, pOsition, and Method) to sort out privacy concerns in evolutionary computation. Specifically, the centralized optimization paradigm allows clients to outsource optimization problems to the centralized server and obtain optimization solutions from the server. While the distributed optimization paradigm exploits the storage and computational power of distributed devices to solve optimization problems. Also, the data-driven optimization paradigm utilizes data collected in history to tackle optimization problems lacking explicit objective functions. Particularly, this paper adopts BOOM to characterize the object and motivation of privacy protection in three typical optimization paradigms and discusses potential privacy-preserving technologies balancing optimization performance and privacy guarantees in three typical optimization paradigms. Furthermore, this paper attempts to foresee some new research directions of privacy-preserving evolutionary computation. © 2023, CC BY.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Context-Aware Refinement Network Incorporating Structural Connectivity Prior for Brain Midline Delineation 23rd

Context-Aware Refinement Network Incorporating Structural Co...

引用

23rd International Conference on Medical Image computing and Computer-Assisted Intervention, MICCAI 2020

作者： Wang, Shen Liang, Kongming Li, Yiming Yu, Yizhou Wang, Yizhou Center for Data Science Peking University Beijing China Advanced Institute of Information Technology Peking University Hangzhou China Department of Computer Science Peking University Beijing China Deepwise AI Lab Beijing China Center on Frontiers of Computing Studies Peking University Beijing China

ISBN: (纸本)9783030597276

Brain midline delineation can facilitate the clinical evaluation of brain midline shift, which plays an important role in the diagnosis and prognosis of various brain pathology. Nevertheless, there are still great challenges with brain midline delineation, such as the largely deformed midline caused by the mass effect and the possible morphological failure that the predicted midline is not a connected curve. To address these challenges, we propose a context-aware refinement network (CAR-Net) to refine and integrate the feature pyramid representation generated by the UNet. Consequently, the proposed CAR-Net explores more discriminative contextual features and larger receptive field, which is of great importance to predict largely deformed midline. For keeping the structural connectivity of the brain midline, we introduce a novel connectivity regular loss (CRL) to punish the disconnectivity between adjacent coordinates. Moreover, we address the ignored prerequisite of previous regression-based methods that the brain CT image must be in the standard pose. A simple pose rectification network is presented to align the source input image to the standard pose image. Extensive experimental results on the CQ dataset and one inhouse dataset show that the proposed method requires fewer parameters and outperforms three state-of-the-art methods in terms of four evaluation metrics. Code is available at https://***/ShawnBIT/Brain-Midline-Detection. © 2020, Springer Nature Switzerland AG.

关键词： Computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Fire-Image-DenseNet (FIDN) for predicting wildfire burnt area using remote sensing data

arXiv

引用

arXiv 2024年

作者： Pang, Bo Cheng, Sibo Huang, Yuhan Jin, Yufang Guo, Yike Prentice, I. Colin Harrison, Sandy P. Arcucci, Rossella Department of Earth Science and Engineering Imperial College London London United Kingdom Data Science Institute Department of Computing Imperial College London London United Kingdom CEREA École des Ponts and EDF R&D Institut Polytechnique de Paris Île-de-France France Department of Land Air and Water Resources University of California DavisCA United States Georgina Mace Centre for the Living Planet Department of Life Sciences Imperial College London London United Kingdom Geography & Environmental Science University of Reading Reading United Kingdom Department of Computer Science and Engineering Hong Kong university of science and technology Hong Kong Computer Network Information Center Chinese Academy of Sciences Beijing China

Predicting the extent of massive wildfires once ignited is essential to reduce the subsequent socioeconomic losses and environmental damage, but challenging because of the complexity of fire behaviour. Existing physicsbased models are limited in predicting large or long-duration wildfire events. Here, we develop a deep-learning-based predictive model, Fire-Image-DenseNet (FIDN), that uses spatial features derived from both near real-time and reanalysis data on the environmental and meteorological drivers of wildfire. We trained and tested this model using more than 300 individual wildfires that occurred between 2012 and 2019 in the western US. In contrast to existing models, the performance of FIDN does not degrade with fire size or duration. Furthermore, it predicts final burnt area accurately even in very heterogeneous landscapes in terms of fuel density and flammability. The FIDN model showed higher accuracy, with a mean squared error (MSE) about 82% and 67% lower than those of the predictive models based on cellular automata (CA) and the minimum travel time (MTT) approaches, respectively. Its structural similarity index measure (SSIM) averages 97%, outperforming the CA and FlamMap MTT models by 6% and 2%, respectively. Additionally, FIDN is approximately three orders of magnitude faster than both CA and MTT models. The enhanced computational efficiency and accuracy advancements offer vital insights for strategic planning and resource allocation for firefighting operations. © 2024, CC BY.

关键词： Travel time

来源：评论

学校读者我要写书评

暂无评论

Ensuring DNN Solution Feasibility for Optimization Problems with Convex Constraints and Its Application to DC Optimal Power Flow Problems

arXiv

引用

arXiv 2021年

作者： Zhao, Tianyu Pan, Xiang Chen, Minghua Low, Steven H. Information Engineering The Chinese University of Hong Kong Hong Kong School of Data Science City University of Hong Kong Steven Hong Kong Department of Computing and Mathematical Sciences California Institute of Technology United States

Ensuring solution feasibility is a key challenge in developing Deep Neural Network (DNN) schemes for solving constrained optimization problems, due to inherent DNN prediction errors. In this paper, we propose a "preventive learning" framework to guarantee DNN solution feasibility for problems with convex constraints and general objective functions without post-processing, upon satisfying a mild condition on constraint calibration. Without loss of generality, we focus on problems with only inequality constraints. We systematically calibrate inequality constraints used in DNN training, thereby anticipating prediction errors and ensuring the resulting solutions remain feasible. We characterize the calibration magnitudes and the DNN size sufficient for ensuring universal feasibility. We propose a new Adversarial-Sample Aware training algorithm to improve DNN’s optimality performance without sacrificing feasibility guarantee. Overall, the framework provides two DNNs. The first one from characterizing the sufficient DNN size can guarantee universal feasibility while the other from the proposed training algorithm further improves optimality and maintains DNN’s universal feasibility simultaneously. We apply the framework to develop DeepOPF+ for solving essential DC optimal power flow problems in grid operation. Simulation results over IEEE test cases show that it outperforms existing strong DNN baselines in ensuring 100% feasibility and attaining consistent optimality loss ( Copyright © 2021, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

BR-GAN: Bilateral Residual Generating Adversarial Network for Mammogram Classification 23rd

BR-GAN: Bilateral Residual Generating Adversarial Network fo...

引用

23rd International Conference on Medical Image computing and Computer-Assisted Intervention, MICCAI 2020

作者： Wang, Chu-ran Zhang, Fandong Yu, Yizhou Wang, Yizhou Center for Data Science Peking University Beijing China Advanced Institute of Information Technology Peking University Hangzhou China Center on Frontiers of Computing Studies Peking University Beijing China Department of Computer Science Peking University Beijing China Deepwise AI Lab Beijing China

ISBN: (纸本)9783030597122

Mammogram malignancy classification with only image-level annotations is challenging due to a lack of lesion annotations. If we can generate the healthy version of the diseased data, we can easily explore the lesion features. An intuitive idea of such generation is to use existing Cycle-GAN based methods. They achieve the healthy generation regarding healthy images as reference domain, while maintaining the original content by cycle consistency mechanism. However, healthy mammogram patterns are diverse which may lead to uncertain generations. Moreover, the back translation from healthy to the original remains an ill-posed problem due to lack of lesion information. To address these problems, we propose a novel model called bilateral residual generating adversarial network(BR-GAN). We use the Cycle-GAN as a basic framework while regarding the contralateral as generation reference based on the bilateral symmetry prior. To address the ill-posed back translation problem, we propose a residual-preserved mechanism to try to preserve the lesion features from the original features. The generated features and the original features are aggregated for further classification. BR-GAN outperforms current state-of-the-art methods on INBreast and in-house datasets. © 2020, Springer Nature Switzerland AG.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

Driving Behavior Safety Assessment in Edge computing Using Multitask Discriminative TS Fuzzy Model

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Gu, Yi Chen, Zhiyu Wang, Lu Shen, Jinsong Bashir, Ali Kashif Wang, Wei Jiangnan University School of Artificial Intelligence and Computer Science Wuxi214122 China Jiangnan University Engineering Research Center of Intelligent Technology for Healthcare Ministry of Education Wuxi214122 China Chongqing University School of Big Data and Software Engineering Chongqing400044 China Jiangsu Keli Internet Information Technology Co. Ltd Jingjiang214500 China Manchester Metropolitan University Department of Computing and Mathematics United Kingdom Woxsen University Woxsen School of Business Hyderabad502 345 India Lebanese American University Department of Computer Science and Mathematics Beirut Lebanon Shenzhen MSU-BIT University Artificial Intelligence Research Institute Shenzhen518172 China

Driving behavior safety analysis in edge computing involves the real-time collection and processing of vehicle driving data. Fuzzy models have advantages in analyzing driving behavior due to their excellent ability to handle uncertain information. This study develops a multitask discriminative Takagi-Sugeno fuzzy model (MD-TS-FM) for driving behavior safety assessment. To comprehensively analyze the correlation and differences in multitask driving behaviors, the designed consequent part consists of two parts: task-shared part reflects the shared intrinsic structure information that are consistent across different driving tasks, and task-specific part reflects distinct characteristics and variations specific to each task, allowing the model to address the unique aspects of different driving behaviors. Accordingly, the task-shared consequent part is characterized by low-rank property, which mines global structural information within the fuzzy space;whereas the task-specific consequent part exhibits sparsity, which removes non-discriminative and irrelevant information. This sparsity ensures that the model focuses on the most critical features for each specific task. Furthermore, a discriminative diversity term is introduced to enhance the diversity between tasks, which explores the consistent information of task-shared consequents while reducing the overlap of task-specific consequents. Experimental results indicate that the MD-TS-FM model can be effectively applied to driving behavior safety assessment. © 1975-2011 IEEE.

关键词： driving behavior safety assessment edge computing fuzzy model multitask learning

来源：评论

学校读者我要写书评

暂无评论

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Learning

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Lea...

引用

IEEE International Conference on Industrial Informatics (INDIN)

作者： Weipeng Cao Xuyang Yao Zhiwu Xu Yinghui Pan Yixuan Sun Dachuan Li Bohua Qiu Muheng Wei Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen) Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Stony Brook University New York United States Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China ZhenDui Industry Artificial Intelligence Co. Ltd Shenzhen China Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China

ISBN: (数字)9798331527471

ISBN: (纸本)9798331527488

Realizing Generalized Zero-Shot Learning (GZSL) based on large models is emerging as a prevailing trend. However, most existing methods merely regard large models as black boxes, solely leveraging the features output by the final layer while disregarding potential performance enhancements from other layers. Indeed, numerous researchers have visually depicted variations in the features learned across different layers of neural networks. Motivated by this observation, we propose a Vision Transformer (ViT)-based GZSL method named Depth-Aware Multi-Modal ViT (DAM2ViT), which exploits multi-level features of ViT. DAM2ViT incorporates a multi-modal interaction block to align semantic information of categories across multiple layers, thereby augmenting the model's capacity to learn associations between visual and semantic spaces. Extensive experiments conducted on three benchmark datasets (i.e., CUB, SUN, AWA2) have showcased that DAM2ViT achieves competitive results compared to state-of-the-art methods.

关键词： Visualization Adaptation models Semantics Zero shot learning Neural networks Termination of employment Transformers Market research Sun Optimization

来源：评论

学校读者我要写书评

暂无评论

A novel binary modified beluga whale optimization algorithm using ring crossover and probabilistic state mutation for enhanced bladder cancer diagnosis

引用

Informatics in Medicine Unlocked 2024年 50卷

作者： Gharaibeh, Hasan Alawad, Noor Aldeen Nasayreh, Ahmad Al Mamlook, Rabia Emhamed Makhadmeh, Sharif Naser Bashkami, Ayah Abualigah, Laith Ezugwu, Absalom E. Computer Science Department Faculty of Information Technology and Computer Sciences Yarmouk University Irbid 21163 Jordan Department of Business Administration Trine University IN United States Department of Mechanical and Industrial Engineering University of Zawia Tripoli Libya Department of Information Technology King Abdullah II School of Information Technology The University of Jordan Amman 11942 Jordan Department Medical Laboratory Sciences – Faculty of Science Al Balqa Applied University Salt 19117 Jordan Department of Cyber Security and Cloud Computing Faculty of Information Technology Applied Science Private University Amman 11937 Jordan Artificial Intelligence and Sensing Technologies (AIST) Research Center University of Tabuk Tabuk 71491 Saudi Arabia Computer Science Department Al al-Bayt University Mafraq 25113 Jordan MEU Research Unit Middle East University Amman 11831 Jordan Applied science research center Applied science private university Amman 11931 Jordan Centre for Research Impact & Outcome Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura 140401 India Unit for Data Science and Computing North-West University 11 Hofman Street Potchefstroom 2520 South Africa Artificial Intelligence Research Center (AIRC) College of Engineering and Information Technology Ajman University Ajman P.O. Box 346 United Arab Emirates

Bladder cancer (BC) remains a significant global health challenge, requiring the development of accurate predictive models for diagnosis. In this study, a new Binary Modified White Whale Optimization (B-MBWO) algorithm is proposed to address the BC problem. The proposed method utilizes circular transitivity optimization and the Probabilistic State Mutation Algorithm (PSMA) to enhance its optimization performance. The new method is called the BBWORCPS algorithm. High-dimensional and complex medical datasets pose challenges to the original optimization algorithms in addressing the BC problem, motivating the proposed modifications to the original Beluga Whale Optimization algorithm. These enhancements, including quantum-inspired mutation and circular crossing, aim to improve solution space exploration and enhance the algorithm's effectiveness in handling intricate feature spaces. Through comprehensive experiments on BC datasets, the superiority of the BBWORCPS algorithm in terms of feature selection accuracy and computational efficiency is demonstrated compared to existing optimization methods. The obtained findings suggest that BBWORCPS offers a promising approach for developing more precise and reliable predictive models for bladder cancer analysis. © 2024 The Author(s)

关键词： Binary modified beluga whale optimization Bladder cancer Feature selection Machine learning Predictive modeling

来源：评论

学校读者我要写书评

暂无评论

Review Spam Detection Based on Multi-dimensional Features 9th

Review Spam Detection Based on Multi-dimensional Features

引用

9th International Conference on Artificial Intelligence and Mobile Services, AIMS 2020, held as part of the Services Conference Federation, SCF 2020

作者： Deng, Liming Wei, Jingjing Liang, Shaobin Wen, Yuhan Liao, Xiangwen College of Mathematics and Computer Science Fuzhou University Fuzhou350116 China Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing Fuzhou University Fuzhou350116 China Digital Fujian Institute of Financial Big Data Fuzhou350116 China College of Electronics and Information Science Fujian Jiangxia University Fuzhou350108 China

ISBN: (纸本)9783030596040

Review spam detection aims to detect the reviews with false information posted by the spammers on social media. The existing methods of review spam detection ignore the importance of the information hidden in the user interactive behaviors and fail to extract the indistinct contextual features caused by irregular writing style of reviews. In this paper, a new review spam detection method based on multi-dimensional features is proposed. The method utilizes the principal component analysis to get low-dimensional features to characterize the user-product relationship. Then, a neural network constructed with nested LSTM and capsule network is trained to extract textual context features and spatial structure features. Finally, the model combines the text and user behavioral features as the overall features, which are used as the input to the classification module to detect spam reviews. Experimental results show that the F1 value of our proposed method is 1.6%~3.5% higher than the existing methods, indicating the efficiency and effectiveness of our model, especially on the natural distribution datasets. © 2020, Springer Nature Switzerland AG.

关键词： Feature extraction

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：