检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Yang, Jianan Gao, Chenchao Xiao, Zhiqing Zhao, Junbo Wu, Sai Chen, Gang Wang, Haobo College of Computer Science and Technology Zhejiang University China Institute of Blockchain and Data Security China School of Software Technology Zhejiang University China International School of Information Science and Engineering Dalian University of Technology China

The recent large-scale text-to-image generative models have attained unprecedented performance, while people established adaptor modules like LoRA and DreamBooth to extend this performance to even more unseen concept tokens. However, we empirically find that this workflow often fails to accurately depict the out-of-distribution concepts. This failure is highly related to the low quality of training data. To resolve this, we present a framework called Controllable Adaptor Towards Out-of-Distribution Concepts (CATOD). Our framework follows the active learning paradigm which includes high-quality data accumulation and adaptor training, enabling a finer-grained enhancement of generative results. The aesthetics score and concept-matching score are two major factors that impact the quality of synthetic results. One key component of CATOD is the weighted scoring system that automatically balances between these two scores and we also offer comprehensive theoretical analysis for this point. Then, it determines how to select data and schedule the adaptor training based on this scoring system. The extensive results show that CATOD significantly outperforms the prior approaches with an 11.10 boost on the CLIP score and a 33.08% decrease on the CMMD metric. © 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

Deep Fusion Co-occurrence Hashing for Image Retrieval 5

Deep Fusion Co-occurrence Hashing for Image Retrieval

引用

5th IEEE International Conference on Information Systems and computer Aided Education, ICISCAE 2022

作者： Yang, Ming Wan, Biao School of Computer Technology and Software Engineering Wuhan Polytechnic Wuhan China

ISBN: (数字)9781665481229

ISBN: (纸本)9781665481229

Improving the perception of objects for an image through label co-occurrence correlation is shown to improve the hash quality. Existing methods ignore the relationship between different representation regions and lack highlighting of salient features when fusing co-occurrence label vectors with image embeddings. To tackle this issue, we proposed a new fusion scheme, i.e., Multi-mapping Multi-modal Factorized Bilinear pooling (MMFB), which extends the single image feature to multiple representations to achieve fusion. As a result, we propose a deep fusion co-occurrence hashing algorithm that uses MMFB instead of MFB in the backbone of the label-attended hash (LAH) algorithm and uses SAGPooling to enhance the perception of attention. Extensive experiments over public benchmarks with multiple labels demonstrate that our algorithm can outperform LAH and state-of-the-art hashing algorithms. © 2022 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Based on FCOS and HSV Recognition Algorithms for Oil Level and Implementations of Train Hydraulic Brake 2

Based on FCOS and HSV Recognition Algorithms for Oil Level a...

引用

2nd International Conference on Frontiers of Electronics, Information and Computation Technologies, ICFEICT 2022

作者： Chen, Qiuyang Pan, Kaixin Zhao, Jianyang Ding, Weihong School of Computer and Software Engineering Huaiyin Institute of Technology Huaian China

ISBN: (数字)9781665454766

ISBN: (纸本)9781665454766

An important application in the field of Digital Image Processing is reading water level recognition. Currently, the automatic recognition method of train hydraulic brake oil level is uncommon, mostly by eye observation oil level position which can cause much errors and poor efficiency. Our project is about how to realize the automatic recognition of train hydraulic brake oil level reading. In this regard, we propose a model algorithm based on FCOS and HSV algorithm. © 2022 IEEE.

关键词： Water levels

来源：评论

学校读者我要写书评

暂无评论

Class-Adaptive Threshold for Class Imbalanced Semi-Supervised Learning 29

Class-Adaptive Threshold for Class Imbalanced Semi-Supervise...

引用

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

作者： Liu, Xiaoyu Wei, Xiang Wang, Jingjie Lu, Siyang Xing, Weiwei School of Software Engineering Beijing Jiaotong University Beijing China School of Computer and Information Technology Beijing Jiaotong University Beijing China

ISBN: (纸本)9798350330717

The recently proposed class-imbalanced semi-supervised learning (CISSL) algorithms achieved impressive performance by effectively leveraging unlabeled data. However, these algorithms often rely on a pre-defined fixed confidence threshold to filter unlabeled data during training, which overlooks the varying learning dynamics across different classes in class-imbalanced scenarios. Consequently, valuable data could be discarded, leading to degraded performance on minority classes. To tackle this issue, we introduce a novel method called Class-Adaptive Threshold (CAT), which dynamically defines and adjusts the confidence threshold based on the learning status of each class. The core idea of CAT is to iteratively update the thresholds for different classes at each time step, enabling us to fully exploit valuable information that would otherwise be ignored using fixed threshold algorithms. Importantly, CAT does not introduce any additional inference processes. In our experiments, the proposed algorithm achieves state-of-the-art performance on various class-imbalanced datasets. Furthermore, we show that CAT can be seamlessly integrated into the renowned CISSL algorithm, resulting in a remarkable boost in their performance. © 2023 IEEE.

关键词： class-imbalance class-imbalanced semi-supervised learning dynamic threshold semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Learning Label Shift Correction for Test-Agnostic Long-Tailed Recognition 41

Learning Label Shift Correction for Test-Agnostic Long-Taile...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Wei, Tong Mao, Zhen Zhou, Zi-Hao Wan, Yuanyu Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China School of Software Technology Zhejiang University Ningbo China

Long-tail learning primarily focuses on mitigating the label distribution shift between long-tailed training data and uniformly distributed test data. However, in real-world applications, we often encounter a more intricate challenge where the test label distribution is agnostic. To address this problem, we first theoretically establish the substantial potential for reducing the generalization error if we can precisely estimate the test label distribution. Motivated by the theoretical insight, we introduce a simple yet effective solution called label shift correction (LSC). LSC estimates the test label distribution within the proposed framework of generalized black box shift estimation, and adjusts the predictions from a pre-trained model to align with the test distribution. Theoretical analyses confirm that accurate estimation of test label distribution can effectively reduce the generalization error. Extensive experimental results demonstrate that our method significantly outperforms previous state-of-the-art approaches, especially when confronted with non-uniform test label distribution. Notably, the proposed method is general and complements existing long-tail learning approaches, consistently improving their performance. The source code is available at https://***/Stomach-ache/label-shift-correction. Copyright 2024 by the author(s)

关键词： Black-box testing

来源：评论

学校读者我要写书评

暂无评论

Self-supervised Hypergraph Transformer with Alignment and Uniformity for Recommendation

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer Science 2024年第3期51卷 292-300页

作者： Yang, XianFeng Liu, Yang School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan China School of computer Science and Software Engineering University of Science and Technology Liaoning Anshan China

Graph neural networks have proven their effectiveness for user-item interaction graph collaborative filtering. However, most of the existing recommendation models highly depended on abundant and high-quality datasets and neglected the alignment and uniformity of embedding representation. The noisy and skewed distribution of data from real-world applications is ubiquitous. The alignment and uniformity are crucial for representation learning. In this paper, we propose SHTAU (self-supervised hypergraph transformer with alignment and uniformity for the recommendation) to address the problem. Specifically, we first perform a graph neural network on the user-item interaction graph, then captures the global collaboration relationship between users and items through the hypergraph transformer structure, and use the extracted global information to generate self-supervised signals for data enhancement on the user-item interaction graph to enhance the robustness of the recommendation algorithm. Simultaneously, alignment and uniformity auxiliary task update embeddings from different angles to improve performance. Extensive experiments are conducted on Yelp, Gowalla, MovieLens, Amazon-book and Tmall datasets. The experimental results show that SHTAU has obvious advantages over the baseline methods. © (2024), (International Association of Engineers). All Rights Reserved.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Research on Attribute-Based Privacy-Preserving Computing Technologies 4th

Research on Attribute-Based Privacy-Preserving Computing Tec...

引用

4th International Conference on Big Data and Security, ICBDS 2022

作者： Qiu, Shuo Ni, Wenhui Shi, Yanfeng Xu, Wanni School of Software Engineering Jinling Institute of Technology Nanjing211169 China School of Computer Engineering Nanjing Institute of Technology Nanjing211167 China School of Internet of Things Engineering Hohai University Changzhou213022 China

ISBN: (纸本)9789819932993

Privacy-preserving computing is an important topic in epidemic prevention, credit report and education resource sharing. Data analysis is the basis for realizing the overall speed increase of returning to work and production. This paper comprehensively summarizes the current academic research on privacy-preserving computing. In this work, we systematically summarize the four aspects of the related schemes on the attribute-based encryption schemes: keyword search, symmetric search, PSI, homomorphic encryption. We classify the schemes and compare the same-type schemes accordingly. Finally, we present the directions and challenges for our future work. This paper is intended to provide convenience for the subsequent research on privacy-preserving computing. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Privacy-preserving techniques

来源：评论

学校读者我要写书评

暂无评论

Dynamic defenses in cyber security:Techniques,methods and challenges Author links open overlay panel

引用

Digital Communications and Networks 2022年第4期8卷 422-435页

作者： Yu Zheng Zheng Li Xiaolong Xu Qingzhan Zhao School of Computer and Software Nanjing University of Information Science and TechnologyNanjing210044JiangsuChina Key Laboratory for Novel Software Technology Nanjing UniversityNanjing210023JiangsuChina College of Information Science and Technology Shihezi University Geospatial Information Engineering Research CenterChina

Driven by the rapid development of the Internet of Things,cloud computing and other emerging technologies,the connotation of cyberspace is constantly expanding and becoming the fifth dimension of human ***,security problems in cyberspace are becoming serious,and traditional defense measures(e.g.,firewall,intrusion detection systems,and security audits)often fall into a passive situation of being prone to attacks and difficult to take effect when responding to new types of network attacks with a higher and higher degree of coordination and *** constructing and implementing the diverse strategy of dynamic transformation,the configuration characteristics of systems are constantly changing,and the probability of vulnerability exposure is ***,the difficulty and cost of attack are increasing,which provides new ideas for reversing the asymmetric situation of defense and attack in ***,few related works systematically introduce dynamic defense mechanisms for cyber *** related concepts and development strategies of dynamic defense are rarely analyzed and *** bridge this gap,we conduct a comprehensive and concrete survey of recent research efforts on dynamic defense in cyber ***,we firstly introduce basic concepts and define dynamic defense in cyber ***,we review the architectures,enabling techniques and methods for moving target defense and mimic *** is followed by taxonomically summarizing the implementation and evaluation of dynamic ***,we discuss some open challenges and opportunities for dynamic defense in cyber security.

关键词： Cyber security Dynamic defense Moving target defense Mimic defense

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Emotion Recognition Method 10

Deep Learning Emotion Recognition Method

引用

10th IEEE International Conference on Cyber Security and Cloud Computing and 9th IEEE International Conference on Edge Computing and Scalable Cloud, CSCloud-EdgeCom 2023

作者： Xiao, Weidong Tan, Wenjin Xiong, Naixue Yang, Ce Chen, Lin Xie, Rui University of Technology Schoole of Software Engineering Xiamen Xiamen361024 China Hunan University of Science and Technology School of Computer Science and Engineering Xiangtan411201 China

ISBN: (纸本)9798350312461

Emotion recognition refers to the process of actively analyzing human emotions through computer technology, and it has become an important part of modern society. Traditional emotion recognition is mainly based on a single information source, such as text, speech, video, etc., from which emotional features are extracted for classification or regression to recognize human emotions. With the development of artificial intelligence technology, multimodal emotion recognition is gradually becoming widely used. It combines two or more types of information, such as text, speech, and visual information, in different ways to analyze emotions. Multimodal emotion recognition is far superior to a single modality in understanding emotions. This article mainly analyzes the technology of emotion analysis. Firstly, we introduce the basic concepts and research status of emotion recognition. Then, we introduce the main types of emotion recognition and describe various methods used in the process in detail. Finally, we discuss the challenges and future developments of emotion recognition. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

An Empirical Comparison of Machine and Deep Learning Algorithms for Predicting Maternal Health Risk 5th

An Empirical Comparison of Machine and Deep Learning Algorit...

引用

5th EAI International Conference on Cognitive Computing and Cyber Physical Systems, IC4S 2024

作者： N, Srinivasa Gupta Valarmathi, B. Kavitha, A. Gopini, Sai Bhuvan Seela, Hari Kumar Department of Manufacturing Engineering School of Mechanical Engineering Vellore Institute of Technology Tamil Nadu Vellore India Department of Software and Systems Engineering School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore India Department of Mathematics School of Advanced of Sciences Vellore Institute of Technology Tamil Nadu Vellore India

ISBN: (纸本)9783031770777

Maternal health is among the greatest challenges in the world, especially in rural areas as there lack medical practitioners, they do not have easily accessible publics clinics and transport is difficult. Therefore, high rates of maternal as well as infant morbidity and mortalities are recorded. This research utilizes Artificial Intelligence (AI) with machine learning algorithms to forecast and address maternal health hazards right at their onset stage. The current research utilizes the concept of AI along with many Machine Learning (ML) methods like the Ensemble Learning Model (ELM), Random Forest (RF), K-Nearest Neighbour (KNN), Decision-Tree (DT), XG-Boost (XGB), Cat Boost (CB), and Gradient Boosting (GB), along with Synthetic Minority Over-sampling Technique (SMOTE) algorithm used for dealing with the problem class imbalance within the data set. SMOTE algorithm is utilized for the dataset balancing process. The handling system involves refining data preprocessing with the help of feature engineering and robust data cleaning which makes sure that anomalies do not erode the reliability of the predictive model. The existing methods [1] used RF (90%), DT (87%), XGB (85%), CB (86%), and GB (81%) algorithms and were compared with the accuracies of the proposed models like Logistic Regression (LR), Ensemble Learning Bagging (ELB), Ensemble Learning Stacking (ELS), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU). The existing methods used only imbalance dataset. The accuracies of the proposed models with using SMOTE algorithm (balanced dataset) are LR (61.33%), KNN (81%), ELB (92.33%), ELS (90.66%) CNN (40.67%), RNN (59.67%), LSTM (54%), GRU (56%) respectively. Among these methods, ELB achieved 92.33% of accuracy with using SMOTE algorithm using imbalanced dataset. Whereas the accuracies of the proposed models without using SMOTE algorithm (imbalanced dataset) are LR (66.09%), KNN (68.47%)

关键词： Convolutional neural networks

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：