检索结果-内蒙古大学图书馆

Transferable Feature Selection for Unsupervised Domain Adaptation

IEEE TRANSACTIONS ON KNOWLEDGE AND data ENGINEERING 2022年第11期34卷 5536-5551页

作者： Yan, Yuguang Wu, Hanrui Ye, Yuzhong Bi, Chaoyang Lu, Min Liu, Dapeng Wu, Qingyao Ng, Michael K. Univ Hong Kong Dept Math Hong Kong Peoples R China South China Univ Technol Sch Software Engn Guangzhou 200131 Peoples R China Minist Educ Key Lab Big Data & Intelligent Robot Guangzhou 200131 Peoples R China Tencent Shenzhen 518052 Peoples R China Fuzhou Lab Guangzhou 200131 Peoples R China

Domain adaptation aims at extracting knowledge from auxiliary source domains to assist the learning task in a target domain. In classification problems, since the distributions of the source and target domains are different, directly using source data to build a classifier for the target domain may hamper the classification performance on the target data. Fortunately, in many tasks, there can be some features that are transferable, i.e., the source and target domains share similar properties. On the other hand, it is common that the source data contain noisy features which may degrade the learning performance in the target domain. This issue, however, is barely studied in existing works. In this paper, we propose to find a feature subset that is transferable across the source and target domains. As a result, the domain discrepancy measured on the selected features can be reduced. Moreover, we seek to find the most discriminative features for classification. To achieve the above goals, we formulate a new sparse learning model that is able to jointly reduce the domain discrepancy and select informative features for classification. We develop two optimization algorithms to address the derived learning problem. Extensive experiments on real-world data sets demonstrate the effectiveness of the proposed method.

关键词： Feature extraction Adaptation models Training Training data Optimization data models Unsupervised learning Domain adaptation transfer learning feature selection sparse learning model

来源：评论

学校读者我要写书评

暂无评论

Contrastive Learning for Robust Android Malware Familial Classification

引用

IEEE Transactions on Dependable and Secure Computing 2022年 1-14页

作者： Wu, Yueming Dou, Shihan Zou, Deqing Yang, Wei Qiang, Weizhong Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai China University of Texas at Dallas Dallas USA National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

Due to its open-source nature, Android operating system has been the main target of attackers to exploit. Malware creators always perform different code obfuscations on their apps to hide malicious activities. Features extracted from these obfuscated samples through program analysis contain many useless and disguised features, which leads to many false negatives. To address the issue, in this paper, we demonstrate that obfuscation-resilient malware family analysis can be achieved through contrastive learning. The key insight behind our analysis is that contrastive learning can be used to reduce the difference introduced by obfuscation while amplifying the difference between malware and other types of malware. Based on the proposed analysis, we design a system that can achieve robust and interpretable classification of Android malware. To achieve robust classification, we perform contrastive learning on malware samples to learn an encoder that can automatically extract robust features from malware samples. To achieve interpretable classification, we transform the function call graph of a sample into an image by centrality analysis. Then the corresponding heatmaps can be obtained by visualization techniques. These heatmaps can help users understand why the malware is classified as this family. We implement IFDroid and perform extensive evaluations on two datasets. Experimental results show that IFDroid is superior to state-of-the-art Android malware familial classification systems. Moreover, IFDroid is capable of maintaining a 98.4% F1 on classifying 69,421 obfuscated malware samples. IEEE

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Energy Consumption Prediction of Public Buildings Based on MEA-BP Neural Network 33

Energy Consumption Prediction of Public Buildings Based on M...

引用

第33届中国控制与决策会议

作者： Shuai Wang Hongyan Ma Jiaming Dou Yongxue Ye Jingjian Yang Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing University of Civil Engineering and Architecture National Virtual Simulation Experimental Center for Smart City Education Institute of Distributed Energy Storage Safety Big Data

ISBN: (纸本)9781665431293

data mining technology is often adopted in construction engineering to provide relevant information and reference basis for public building energy consumption *** paper proposes an optimization algorithm applying back propagation(BP) neural network and mind evolutionary algorithm(MEA) to establish a model to predict building energy *** main weather data are used as inputs to the BP neural network and daily electricity consumption is used as an *** MEA is employed to optimise the structure of the network and to predict the energy consumption of *** results demonstrate that the optimized BP neural network has higher fitting accuracy,and the predicted load value is more consistent with the actual value.

关键词： Building energy consumption BP neural network Mind evolutionary algorithm

来源：评论

学校读者我要写书评

暂无评论

A Prompt-Based Representation Individual Enhancement Method for Chinese Idiom Reading Comprehension 28th

A Prompt-Based Representation Individual Enhancement Method ...

引用

28th International Conference on database Systems for Advanced Applications, DASFAA 2023

作者： Sha, Ying Wu, Mingmin Zeng, Zhi Ge, Xing Huang, Zhongqiang Wang, Huan College of Informatics Huazhong Agricultural University Wuhan China Key Laboratory of Smart Farming for Agricultural Animals Wuhan China Hubei Engineering Technology Research Center of Agricultural Big Data Wuhan China Engineering Research Center of Intelligent Technology for Agriculture Ministry of Education Wuhan China

ISBN: (纸本)9783031306747

Chinese idiom is a distinctive language phenomenon, which usually consists of four Chinese characters and expresses a non-compositional and metaphorical meaning. Therefore, Chinese idioms pose unique challenges for Chinese machine reading comprehension. To address this issue, researchers proposed a Chinese idiom cloze task and a large-scale Chinese idioms dataset ChID. Existing methods have proposed a number of models and achieved reasonable performance on ChID. However, they fall short of fully exploring the precise representations and distinctions of the meanings of idioms, especially idioms with similar meanings. In this paper, we propose a prompt-based representation individual enhancement method (PRIEM). This method fuses the context-specific representation and the generic definition representation of the idioms, and uses the prompt method to guide the model in learning the metaphorical meanings of idioms purposefully. To further improve the distinction representations of idioms with similar meanings, PRIEM adopts a method of idiom representation mapping and decomposing based on orthogonal projection to obtain the common and individual representations of idioms respectively. Experimental results on ChID show that our model outperforms state-of-the-art models. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

A2Nav: Action-Aware Zero-Shot robot Navigation by Exploiting Vision-and-Language Ability of Foundation Models

arXiv

引用

arXiv 2023年

作者： Chen, Peihao Sun, Xinyu Zhi, Hongyan Zeng, Runhao Li, Thomas H. Liu, Gaowen Tan, Mingkui Gan, Chuang South China University of Technology China Shenzhen University China Pazhou Laboratory China Key Laboratory of Big Data and Intelligent Robot Ministry of Education China Shenzhen Graduate School Peking University China Cisco Research China

We study the task of zero-shot vision-and-language navigation (ZS-VLN), a practical yet challenging problem in which an agent learns to navigate following a path described by language instructions without requiring any path-instruction annotation data. Normally, the instructions have complex grammatical structures and often contain various action descriptions (e.g., "proceed beyond", "depart from"). How to correctly understand and execute these action demands is a critical problem, and the absence of annotated data makes it even more challenging. Note that a well-educated human being can easily understand path instructions without the need for any special training. In this paper, we propose an action-aware zero-shot VLN method (A2Nav) by exploiting the vision-and-language ability of foundation models. Specifically, the proposed method consists of an instruction parser and an action-aware navigation policy. The instruction parser utilizes the advanced reasoning ability of large language models (e.g., GPT-3) to decompose complex navigation instructions into a sequence of action-specific object navigation sub-tasks. Each sub-task requires the agent to localize the object and navigate to a specific goal position according to the associated action demand. To accomplish these sub-tasks, an action-aware navigation policy is learned from freely collected action-specific datasets that reveal distinct characteristics of each action demand. We use the learned navigation policy for executing sub-tasks sequentially to follow the navigation instruction. Extensive experiments show A2Nav achieves promising ZS-VLN performance and even surpasses the supervised learning methods on R2R-Habitat and RxR-Habitat datasets. Copyright © 2023, The Authors. All rights reserved.

关键词： Navigation

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Enhanced Scene Graph Generation with Multimodal Relation Alignment (Student Abstract) 36

Knowledge-Enhanced Scene Graph Generation with Multimodal Re...

引用

36th AAAI Conference on Artificial Intelligence / 34th Conference on Innovative Applications of Artificial Intelligence / 12th Symposium on Educational Advances in Artificial Intelligence

作者： Fu, Ze Feng, Junhao Zheng, Changmeng Cai, Yi South China Univ Technol Sch Software Engn Guangzhou Peoples R China Minist Educ Key Lab Big Data & Intelligent Robot SCUT Beijing Peoples R China Hong Kong Polytech Univ Dept Comp Hong Kong Peoples R China

ISBN: (纸本)9781577358763

Existing scene graph generation methods suffer the limitations when the image lacks of sufficient visual contexts. To address this limitation, we propose a knowledge-enhanced scene graph generation model with multimodal relation alignment, which supplements the missing visual contexts by well-aligned textual knowledge. First, we represent the textual information into contextualized knowledge which is guided by the visual objects to enhance the contexts. Furthermore, we align the multimodal relation triplets by co-attention module for better semantics fusion. The experimental results show the effectiveness of our method.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Multimodal Brain Tumor Segmentation Method: Parallel Fusion of Transformer and CNN

A Multimodal Brain Tumor Segmentation Method: Parallel Fusio...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Zheng, Fang Zhou, Hang Li, Guoliang Ni, Fuchuan Huazhong Agricultural University Engineering Research Center of Intelligent Technology for Agriculture Ministry of Education Key Laboratory of Smart Farming Technology for Agricultural Animals Ministry of Agriculture and Rural Affairs College of Informatics Wuhan China Huazhong Agricultural University College of Informatics Wuhan China Hubei Engineering Technology Research Center of Agricultural Big Data Engineering Research Center of Intelligent Technology for Agriculture Ministry of Education Wuhan China

ISBN: (纸本)9798350386226

While convolutional neural network(CNN) have historically achieved significant success in 3D medical image segmentation, recent advancements in Vision Transformer (ViT) have led to increased popularity of Transformer architectures in this field. Leveraging the global information extraction capabilities of Transformers, we propose a novel parallel structure combining CNN and Transformer for multimodal brain tumor segmentation, named PTCNet. We introduce two key improvements to enhance multimodal segmentation:1) Introducing a novel channel attention module that replaces spatial self-attention in the Transformer to improve cross-modal information extraction.2) Enhancing the reversible feature extraction module based on residual structures to better detect small lesions. We evaluated our method on the BraTS 2023 brain metastasis dataset, achieving an average DSC of 61.42%, which is 1.12% higher than the second place. The innovative structure and improved modules of PTCNet significantly enhance performance in multimodal brain tumor segmentation tasks. Code and models are available at https://***/naiqizh/PTCNet. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Fully Deformable Network for Multiview Face Image Synthesis

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2024年第7期35卷 8854-8868页

作者： Xu, Cheng Li, Keke Luo, Xuandi Xu, Xuemiao He, Shengfeng Zhang, Kun South China Univ Technol Sch Comp Sci & Engn Guangzhou 510640 Peoples R China Guangzhou Univ Inst Artificial Intelligence & Blockchain Guangzhou 510006 Peoples R China Minist Educ State Key Lab Subtrop Bldg Sci Key Lab Big Data & Intelligent Robot Guangzhou 510640 Peoples R China Guangdong Prov Key Lab Computat Intelligence & Cy Guangzhou 510640 Peoples R China Singapore Management Univ Sch Comp & Informat Syst Singapore 188065 Singapore Carnegie Mellon Univ Dept Philosophy Pittsburgh PA 15213 USA Mohamed bin Zayed Univ Artificial Intelligence Dept Machine Learning Abu Dhabi U Arab Emirates

Photorealistic multiview face synthesis from a single image is a challenging problem. Existing works mainly learn a texture mapping model from the source to the target faces. However, they rarely consider the geometric constraints on the internal deformation arising from pose variations, which causes a high level of uncertainty in face pose modeling, and hence, produces inferior results for large pose variations. Moreover, current methods typically suffer from undesired facial details loss due to the adoption of the de-facto standard encoder-decoder architecture without any skip connections (SCs). In this article, we directly learn and exploit geometric constraints and propose a fully deformable network to simultaneously model the deformations of both landmarks and faces for face synthesis. Specifically, our model consists of two parts: a deformable landmark learning network (DLLN) and a gated deformable face synthesis network (GDFSN). The DLLN converts an initial reference landmark to an individual-specific target landmark as delicate pose guidance for face rotation. The GDFSN adopts a dual-stream structure, with one stream estimating the deformation of two views in the form of convolution offsets according to the source pose and the converted target pose, and the other leveraging the predicted deformation offsets to create the target face. In this way, individual-aware pose changes are explicitly modeled in the face generator to cope with geometric transformation, by adaptively focusing on pertinent regions of the source face. To compensate for offset estimation errors, we introduce a soft-gating mechanism for adaptive fusion between deformable features and primitive features. Additionally, a pose-aligned SC (PASC) is tailored to propagate low-level input features to the appropriate positions in the output features for further enhancing the facial details and identity preservation. Extensive experiments on six benchmarks show that our approach performs favorably a

关键词： Faces Face recognition Strain Deformable models Electronic mail Convolution Standards Deformable convolution gating multiview face synthesis pose-invariant face recognition

来源：评论

学校读者我要写书评

暂无评论

A Causal Disentangled Multi-Granularity Graph Classification Method

arXiv

引用

arXiv 2023年

作者： Li, Yuan Liu, Li Chen, Penggang Zhang, Youmin Wang, Guoyin Chongqing Key Laboratory of Computational Intelligence China Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing University of Posts and Telecommunications Chongqing400065 China

Graph data widely exists in real life, with large amounts of data and complex structures. It is necessary to map graph data to low-dimensional embedding. Graph classification, a critical graph task, mainly relies on identifying the important substructures within the graph. At present, some graph classification methods do not combine the multi-granularity characteristics of graph data. This lack of granularity distinction in modeling leads to a conflation of key information and false correlations within the model. So, achieving the desired goal of a credible and interpretable model becomes challenging. This paper proposes a causal disentangled multi-granularity graph representation learning method (CDM-GNN) to solve this challenge. The CDM-GNN model disentangles the important substructures and bias parts within the graph from a multi-granularity perspective. The disentanglement of the CDM-GNN model reveals important and bias parts, forming the foundation for its classification task, specifically, model interpretations. The CDM-GNN model exhibits strong classification performance and generates explanatory outcomes aligning with human cognitive patterns. In order to verify the effectiveness of the model, this paper compares the three real-world datasets MUTAG, PTC, and IMDM-M. Six state-of-the-art models, namely GCN, GAT, Top-k, ASAPool, SUGAR, and SAT are employed for comparison purposes. Additionally, a qualitative analysis of the interpretation results is conducted. Copyright © 2023, The Authors. 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

Preface: Brain-Inspired AI Research

引用

Science China(Technological Sciences) 2024年第8期67卷 2281-2281页

作者： GONG YiHong WANG GuoYin College of Artificial Intelligence Xi’an Jiaotong UniversityXi’an 710049China Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and TelecommunicationsChongqing400065China Key Laboratory of Cyberspace Big Data Intelligent Security Chongqing University of Posts and TelecommunicationsChongqing400065China College of Computer and Information Science Chongqing Normal UniversityChongqing401331China

Large AGI (artificial general intelligence) models, represented by OpenAI’s GPT-4, DALL-E, Sora, etc., have amazed the world by exhibiting superior capabilities on a variety of NLP and text-to-image/video generation tasks. The success of these models was achieved by exploiting ultra-scale training data, ultra-scale computational models, and unlimited computing *** brute force approach, however, is not only making an adverse impact on global warming prevention, but also raising skepticism on whether such a development path can really achieve true AGI systems. Recently, there have been increasing scientific studies that report the delusion phenomenon of the AGI models, mainly caused by their inability to learn correct knowledge and correct world models.

关键词： artificial Open knowledge

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：