检索结果-内蒙古大学图书馆

International Conference on computer Vision (ICCV)

作者： Yin-Yin He Jianxin Wu Xiu-Shen Wei State Key Laboratory for Novel Software Technology Nanjing University China School of Computer Science and Engineering Nanjing University of Science and Technology China

ISBN: (纸本)9781665428132

We tackle the long-tailed visual recognition problem from the knowledge distillation perspective by proposing a Distill the Virtual Examples (DiVE) method. Specifically, by treating the predictions of a teacher model as virtual examples, we prove that distilling from these virtual examples is equivalent to label distribution learning under certain constraints. We show that when the virtual example distribution becomes flatter than the original input distribution, the under-represented tail classes will receive significant improvements, which is crucial in long-tailed recognition. The proposed DiVE method can explicitly tune the virtual example distribution to become flat. Extensive experiments on three benchmark datasets, including the large-scale iNaturalist ones, justify that the proposed DiVE method can significantly outperform state-of-the-art methods. Further-more, additional analyses and experiments verify the virtual example interpretation, and demonstrate the effectiveness of tailored designs in DiVE for long-tailed problems.

关键词： Visualization computer vision Predictive models Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Ran: A Randomness-Anchored Watermark Attacking Network Using Deep Learning

SSRN

引用

SSRN 2022年

作者： Lia, Fan Li, Kunqi Huang, Yuanyuan Cheng, Zhitao Wang, Junfeng Tang, Yong National Key Laboratory of Fundamental Science on Synthetic Vision Sichuan University Sichuan Chengdu610065 China School of Information and Software Engineering University of Electronic Science and Technology of China Sichuan Chengdu610054 China School of Mathematical Sciences University of Electronic Science and Technology of China Sichuan Chengdu610054 China School of Computer Science and Engineering University of Electronic Science and Technology of China Sichuan Chengdu610054 China

Research on watermark attacking is essential to reinforce robust watermarking methods by providing new attacking benchmarks. Recently, there is an emergence of attacking methods based on deep learning, in which perceptual loss and watermark loss are utilized to train the neural networks for the imperceptibility of watermarked images and the disruption of attacked watermarks. In this work, we propose a novel randomness-anchored attacking network (RAN) based on deep learning. In RAN, we introduce an alternative watermark loss to attack the watermarks into random noises by anchoring to randomness rather than the original watermarks. Extensive attacking experiments of comparisons with traditional attacking schemes show that the proposed RAN models can achieve satisfying performance in preserving the visual fidelity of attacked watermarked images with competitive attacking ability. The proposed methods add new inspirations to the design of stealthy and effective attacking models based on deep learning, with significant implications for developing robust watermarking. © 2022, The Authors. All rights reserved.

关键词： Watermarking

来源：评论

学校读者我要写书评

暂无评论

Multi-view clustering guided by unconstrained non-negative matrix factorization

引用

Knowledge-Based Systems 2023年 266卷

作者： Deng, Ping Li, Tianrui Wang, Dexian Wang, Hongjun Peng, Hong Horng, Shi-Jinn School of Computer and Software Engineering Xihua University Chengdu610039 China School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Chengdu611756 China Department of Computer Science and Information Engineering National Taiwan University of Science and Technology Taipei106 Taiwan

Multi-view clustering based on non-negative matrix factorization (NMFMvC) is a well-known method for handling high-dimensional multi-view data. To satisfy the non-negativity constraint of the matrix, NMFMvC is usually solved using the Karush–Kuhn–Tucker (KKT) conditions. However, this optimization method is poorly scalable. To this end, we propose an unconstrained non-negative matrix factorization multi-view clustering (uNMFMvC) model. First, the objective function was constructed by decoupling the elements of the matrix and combining the elements with a non-linear mapping function in a non-negative value domain. The objective function was then optimized using the stochastic gradient descent (SGD) algorithm. Subsequently, three uNMFMvC methods were constructed based on different mapping functions and detailed reasoning was provided. Finally, experiments were conducted on eight public datasets and compared with cutting-edge multi-view clustering methods. The experimental results demonstrate that the proposed model has significant advantages. © 2023 Elsevier B.V.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Self-Adaptive Teaching-Learning-Based Optimizer with Improved Rbf and Sparse Autoencoder for High-Dimensional Problems

SSRN

引用

SSRN 2022年

作者： Bi, Jing Wang, Ziqi Yuan, Haitao Zhang, Jia Zhou, MengChu School of Software Engineering Faculty of Information Technology Beijing University of Technology Beijing100124 China School of Automation Science and Electrical Engineering Beihang University Beijing100191 China Department of Computer Science The Lyle School of Engineering Southern Methodist University DallasTX75205 United States Department of Electrical and Computer Engineering New Jersey Institute of Technology NewarkNJ07102 United States

Evolutionary algorithms are commonly used to solve many complex optimization problems in different fields. Yet, their performance is limited when dealing with high-dimensional complex problems because they often require enormous computational resources to yield desired solutions, and they may easily trap into local optima. To solve this problem, this work proposes a Selfadaptive Teaching-learning-based Optimizer with an improved Radial basis function model and a sparse Autoencoder (STORA). In STORA, a Self-adaptive Teaching-Learning-Based Optimizer (STLBO) is designed to dynamically adjust parameters for balancing exploration and exploitation abilities. Then, a sparse autoencoder (SAE) is adopted as a dimension reduction method to compress search space into lower-dimensional one for more efficiently guiding population to converge towards global optima. Besides, an Improved Radial Basis Function model (IRBF) is designed as a surrogate model to balance training time and prediction accuracy. It is adopted to save computational resources for improving overall performance. In addition, a dynamic population allocation strategy is adopted to well integrate SAE and IRBF in STORA. We evaluate STORA by comparing it with several state-of-the-art algorithms through eight benchmark functions. We further test its actual performance by applying it to solve a real-world computation offloading problem. © 2022, The Authors. All rights reserved.

关键词： Radial basis function networks

来源：评论

学校读者我要写书评

暂无评论

A GSO-based multi-objective technique for performance optimization of blockchain-based industrial Internet of things

引用

International Journal of Communication Systems 2024年第15期37卷

作者： Zanbouri, Kouros Darbandi, Mehdi Nassr, Mohammad Heidari, Arash Navimipour, Nima Jafari Yalcın, Senay Department of Computer Engineering Tabriz Branch Islamic Azad University Tabriz Iran Pôle Universitaire Léonard de Vinci Paris France Communication Technology Engineering Department Tartous University Tartus Syria Department of Mathematics and Natural Sciences Gulf University for Science and Technology Mishref Campus Kuwait Department of Computer Engineering Faculty of Engineering and Natural Science İstanbul Atlas University Turkey Department of Software Engineering Haliç University Istanbul Turkey Department of Computer Engineering Kadir Has University Istanbul Turkey Research Center of High Technologies and Innovative Engineering Western Caspian University Baku Azerbaijan Future Technology Research Center National Yunlin University of Science and Technology Douliou Taiwan Department of Energy System Engineering School of Engineering and Natural Sciences Bahçeşehir University Istanbul Turkey

The latest developments in the industrial Internet of things (IIoT) have opened up a collection of possibilities for many industries. To solve the massive IIoT data security and efficiency problems, a potential approach is considered to satisfy the main needs of IIoT, such as high throughput, high security, and high efficiency, which is named blockchain. The blockchain mechanism is considered a significant approach to boosting data protection and performance. In the quest to amplify the capabilities of blockchain-based IIoT, a pivotal role is accorded to the Glowworm Swarm Optimization (GSO) algorithm. Inspired by the collaborative brilliance of glowworms in nature, the GSO algorithm offers a unique approach to harmonizing these conflicting aims. This paper proposes a new approach to improve the performance optimization of blockchain-based IIoT using the GSO algorithm due to the blockchain's contradictory objectives. The proposed blockchain-based IIoT system using the GSO algorithm addresses scalability challenges typically associated with blockchain technology by efficiently managing interactions among nodes and dynamically adapting to network demands. The GSO algorithm optimizes the allocation of resources and decision-making, reducing inefficiencies and bottlenecks. The method demonstrates considerable performance improvements through extensive simulations compared to traditional algorithms, offering a more scalable and efficient solution for industrial applications in the context of the IIoT. The extensive simulation and computational study have shown that the proposed method using GSO considerably improves the objective function and blockchain-based IIoT systems' performance compared to traditional algorithms. It provides more efficient and secure systems for industries and corporations. © 2024 John Wiley & Sons Ltd.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Sound-Dr: Reliable Sound Dataset and Baseline Artificial Intelligence System for Respiratory Illnesses

arXiv

引用

arXiv 2022年

作者： Hoang, Truong V. Nguyen, Quang H. Nguyen, Cuong Q. Nguyen, Phong X. Nguyen, Hoang D. AI Center FPT Software Company Limited Viet Nam Reliable Machine Learning Group Viet Nam School of Computer Science and Information Technology University College Cork Ireland

As the burden of respiratory diseases continues to fall on society worldwide, this paper proposes a high-quality and reliable dataset of human sounds for studying respiratory illnesses, including pneumonia and COVID-19. It consists of coughing, mouth breathing, and nose breathing sounds together with metadata on related clinical characteristics. We also develop a proof-of-concept system for establishing baselines and benchmarking against multiple datasets, such as Coswara and COUGHVID. Our comprehensive experiments show that the Sound-Dr dataset has richer features, better performance, and is more robust to dataset shifts in various machine learning tasks. It is promising for a wide range of real-time applications on mobile devices. The proposed dataset and system will serve as practical tools to support healthcare professionals in diagnosing respiratory disorders. The dataset and code are publicly available here: https://***/ReML-AI/Sound-Dr/.MSC Codes 68-11, 92-XX © 2022, CC BY.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

An extensive empirical study of inconsistent labels in multi-version-project defect data sets

arXiv

引用

arXiv 2021年

作者： Liu, Shiran Guo, Zhaoqiang Li, Yanhui Wang, Chuanqi Chen, Lin Sun, Zhongbin Zhou, Yuming State Key Laboratory for Novel Software Technology Nanjing University China Department of Computer Science and Technology Nanjing University China School of Computer Science & Technology China University of Mining and Technology China

The label quality of defect data sets has a direct influence on the reliability of defect prediction models. In this study, for multi-version-project defect data sets, we propose an approach to automatically detecting instances with "inconsistent labels" (i.e. the phenomena of instances having the same source code but different labels over multiple versions of a software project) and understand their influence on the evaluation and interpretation of defect prediction models. Based on five multi-version-project defect data sets (either widely used or the most up-to-date in the literature) collected by diverse approaches, we find that: (1) most versions (>90%) in the investigated defect data sets contain inconsistent labels with varying degrees;(2) the existence of inconsistent labels in a training data set may considerably change the prediction performance of a defect prediction model as well as can lead to the identification of substantially different true defective modules;and (3) the importance ranking of independent variables in a defect prediction model can be substantially shifted due to the existence of inconsistent labels. The above findings reveal that inconsistent labels in defect data sets can profoundly change the prediction ability and interpretation of a defect prediction model. Therefore, we strongly suggest that practitioners should detect and exclude inconsistent labels in defect data sets to avoid their potential negative influence on defect prediction models. What is more, it is necessary for researchers to improve existing defect label collection approaches to reduce inconsistent labels. Furthermore, there is a need to re-examine the experimental conclusions of previous studies using multi-version-project defect data sets with a high ratio of inconsistent labels. Copyright © 2021, The Authors. All rights reserved.

关键词： Defects

来源：评论

学校读者我要写书评

暂无评论

An explicit-joint and supervised-contrastive learning framework for few-shot intent classification and slot filling

arXiv

引用

arXiv 2021年

作者： Liu, Han Zhang, Feng Zhang, Xiaotong Zhao, Siyang Zhang, Xianchao School of Software Dalian University of Technology Key Laboratory for Ubiquitous Network Service Software of Liaoning Province School of Electronics Engineering Computer Science Peking University

Intent classification (IC) and slot filling (SF) are critical building blocks in task-oriented dialogue systems. These two tasks are closely-related and can flourish each other. Since only a few utterances can be utilized for identifying fast-emerging new intents and slots, data scarcity issue often occurs when implementing IC and SF. However, few IC/SF models perform well when the number of training samples per class is quite small. In this paper, we propose a novel explicit-joint and supervised-contrastive learning framework for few-shot intent classification and slot filling. Its highlights are as follows. (i) The model extracts intent and slot representations via bidirectional interactions, and extends prototypical network to achieve explicit-joint learning, which guarantees that IC and SF tasks can mutually reinforce each other. (ii) The model integrates with supervised contrastive learning, which ensures that samples from same class are pulled together and samples from different classes are pushed apart. In addition, the model follows a not common but practical way to construct the episode, which gets rid of the traditional setting with fixed way and shot, and allows for unbalanced datasets. Extensive experiments on three public datasets show that our model can achieve promising performance. Copyright © 2021, The Authors. All rights reserved.

关键词： Filling

来源：评论

学校读者我要写书评

暂无评论

Towards accurate and robust domain adaptation under noisy environments 29

Towards accurate and robust domain adaptation under noisy en...

引用

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Han, Zhongyi Gui, Xian-Jin Cui, Chaoran Yin, Yilong School of Software Shandong University Jinan250101 China National Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China School of Computer Science and Technology Shandong University of Finance and Economics China

ISBN: (纸本)9780999241165

In non-stationary environments, learning machines usually confront the domain adaptation scenario where the data distribution does change over time. Previous domain adaptation works have achieved great success in theory and practice. However, they always lose robustness in noisy environments where the labels and features of examples from the source domain become corrupted. In this paper, we report our attempt towards achieving accurate noise-robust domain adaptation. We first give a theoretical analysis that reveals how harmful noises influence unsupervised domain adaptation. To eliminate the effect of label noise, we propose an offline curriculum learning for minimizing a newly-defined empirical source risk. To reduce the impact of feature noise, we propose a proxy distribution based margin discrepancy. We seamlessly transform our methods into an adversarial network that performs efficient joint optimization for them, successfully mitigating the negative influence from both data corruption and distribution shift. A series of empirical studies show that our algorithm remarkably outperforms state of the art, over 10% accuracy improvements in some domain adaptation tasks under noisy environments. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Federated Quality Profiling: A quality evaluation of patient monitoring at the Edge

Federated Quality Profiling: A quality evaluation of patient...

引用

International Wireless Communications and Mobile Computing Conference, IWCMC

作者： Alramzana Nujum Navaz Mohamed Adel Serhani Hadeel T. El Kassabi Department of Information Systems and Security College of Information Technology United Arab Emirates University Al Ain United Arab Emirates University Department of Computer Science and Software Engineering Gina Cody School of Engineering and Computer Science Concordia University Montreal Canada

Continuous monitoring of patients involves collecting and analyzing sensory data from a multitude of sources. To overcome communication overhead, ensure data privacy and security, reduce data loss, and maintain efficient resource usage the processing and analytics are moved close to where the data is located (e.g., the Edge). Data quality (DQ) can be degraded because of imprecise or malfunctioning sensors, dynamic changes in the environment, transmission failures, or delays. Therefore, can mislead clinical judgments and cause incorrect actions, if not managed properly. In this paper, inspired by Federated Learning (FL), we propose a novel approach using Federated Data Quality (FDQ) Profiling to assess DQ at the edge considering a global quality profile aggregated based on local profiles. We conducted experiments to evaluate the effect of FDQ profiling on DQ improvement considering the assessment of outlier detection and unbalanced data. The results demonstrated that the improved DQ has a positive impact on the accuracy of four conventional machine learning models.

关键词： Wireless communication Patient monitoring Data privacy Image edge detection Data integrity Machine learning Sensors

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：