检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing systems, NeurIPS 2024

作者： Li, Pengxiang Gao, Zhi Zhang, Bofei Yuan, Tao Wu, Yuwei Harandi, Mehrtash Jia, Yunde Zhu, Song-Chun Li, Qing Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology China State Key Laboratory of General Artificial Intelligence BIGAI China State Key Laboratory of General Artificial Intelligence Peking University China Department of Electrical and Computer System Engineering Monash University Australia Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University China Department of Automation Tsinghua University China

Vision language models (VLMs) have achieved impressive progress in diverse applications, becoming a prevalent research direction. In this paper, we build FIRE, a feedback-refinement dataset, consisting of 1.1M multi-turn conversations that are derived from 27 source datasets, empowering VLMs to spontaneously refine their responses based on user feedback across diverse tasks. To scale up the data collection, FIRE is collected in two components: FIRE-100K and FIRE-1M, where FIRE-100K is generated by GPT-4V, and FIRE-1M is freely generated via models trained on FIRE-100K. Then, we build FIRE-Bench, a benchmark to comprehensively evaluate the feedback-refining capability of VLMs, which contains 11K feedback-refinement conversations as the test data, two evaluation settings, and a model to provide feedback for VLMs. We develop the FIRE-LLaVA model by fine-tuning LLaVA on FIRE-100K and FIRE-1M, which shows remarkable feedback-refining capability on FIRE-Bench and outperforms untrained VLMs by 50%, making more efficient user-agent interactions and underscoring the significance of the FIRE dataset. © 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

Towards Stricter Black-box Integrity Verification of Deep Neural Network Models 24

Towards Stricter Black-box Integrity Verification of Deep Ne...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： He, Chaoxiang Bai, Xiaofan Ma, Xiaojing Zhu, Bin B. Hu, Pingyi Fu, Jiayun Jin, Hai Zhang, Dongmei Huazhong University of Science and Technology Hubei Wuhan China Shanghai Jiao Tong University Shanghai China Microsoft Corporation Beijing China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security School of Cyber Science and Engineering Huazhong University of Science and Technology China 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 China

ISBN: (纸本)9798400706868

Cloud-based machine learning services offer significant advantages but also introduce the risk of tampering with cloud-deployed deep neural network (DNN) models. Black-box integrity verification (BIV) allows model owners and end-users to determine if a cloud-deployed DNN model has been tampered with by examining only the top-1 label responses. Fingerprinting generates fingerprint samples to query the model, achieving BIV with no impact on the model's accuracy. In this paper, we present BIVBench, the first comprehensive benchmark for BIV of DNN models. BIVBench covers 16 types of model modifications, providing extensive coverage of practical modification scenarios. Our analysis reveals that existing fingerprinting methods, which are typically focused on significant tampering, lack the sensitivity needed to effectively detect subtle yet common and potentially severe modifications. To address this limitation, we propose MiSentry (Model Integrity Sentry), a novel fingerprinting method that leverages meta-learning. MiSentry strategically incorporates a few subtly modified models into the meta-learning model zoo and maximizes the divergence of output predictions between the target model and the modified models in the model zoo to generate highly sensitive, generalizable, and effective fingerprint samples. Extensive evaluations using BIVBench demonstrate that MiSentry outperforms existing state-of-the-art methods overall and significantly surpasses them in detecting subtle modifications. The BIVBench and supplementary materials are available at: https://***/CGCL-codes/BIVBench. © 2024 ACM.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Infrared Small Target Detection with Feature Refinement and Context Enhancement 31st

Infrared Small Target Detection with Feature Refinement and...

引用

31st International Conference on Multimedia Modeling, MMM 2025

作者： Li, Xiuhong Zhu, Xinyue Li, Boyuan Li, Songlin Wang, Luyao Jia, Zhenhong School of Computer Science and Technology Xinjiang University Urumgi China Key Laboratory of Signal Detection and Processing Xinjiang University Urumqi China College of Mathematics and System Science Xinjiang University Urumqi China

ISBN: (纸本)9789819620609

Infrared small target detection has received widespread application and attention in both civilian and military fields. However, due to the very small size and lack of unique features of these targets, existing methods often suffer from inaccurate edge localization, and the targets are easily overwhelmed by complex backgrounds. To effectively address these issues, we designed a Feature Refinement and Context Enhancement Network (FCNet). The network consists of a multi-branch feature extraction module (MFEM), which integrates ordinary convolution and center difference convolution for diversified feature extraction, and further refines features through attention mechanism to enhance feature expression ability. In addition, in order to better capture the contextual information of the target, we have introduced the Context Enhancement Module (CEM). The CEM improves the robustness and detection accuracy of the network in complex backgrounds by preserving and enhancing important information in the image. Especially when processing infrared images with complex backgrounds and low signal-to-noise ratios, CEM can effectively highlight the target area and reduce false positives and false negatives. The experimental results on the SIRST dataset show that our FCNet performs well on multiple evaluation metrics. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

Up to 320-GBaud Coherent Optical system Based on Broadband Segmented TFLN I/Q Modulator

Up to 320-GBaud Coherent Optical System Based on Broadband S...

引用

2024 Asia Communications and Photonics Conference, ACP 2024 and International Conference on Information Photonics and Optical Communications, IPOC 2024

作者： Zhou, Lingjun Fang, Xiansong Zhu, Yixiao Zhu, Junbo Li, Yunchen Nie, Xiaomin Zhou, Xian Yang, Chuanchuan Wang, Lei Hu, Weisheng Li, Ke He, Zhixue Zhang, Fan School of Electronic and Computer Engineering Peking University Shenzhen China Peng Cheng Laboratory Shenzhen China State Key Laboratory of Advanced Optical Communication System and Networks School of Electronics Peking University Beijing China State Key Laboratory of Advanced Optical Communication System and Networks Shanghai Jiao Tong University Shanghai China School of Computer & Communication Engineering University of Science and Technology Beijing Beijing China

We demonstrate the record 320-GBd single-polarization QPSK and 300-GBd dual-polarization QPSK signal generation and intradyne coherent detection. This result is achieved with a novel broadband segmented TFLN I/Q modul... 详细信息

ISBN: (纸本)9798350379266

关键词： Quadrature phase shift keying

来源：评论

学校读者我要写书评

暂无评论

Position Measurement Based Slave Torque Feedback Control for Teleoperation systems With Time-Varying Communication Delays

引用

IEEE/CAA Journal of Automatica Sinica 2023年第2期10卷 388-402页

作者： Xian Yang Jing Yan Changchun Hua Xinping Guan the Institute of Information Science and Engineering Yanshan University the Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao 066004China IEEE the Institute of Electrical Engineering Yanshan UniversityQinhuangdao 066004China the Department of Automation Shanghai Jiao Tong UniversityShanghai 200240China

Bilateral teleoperation system is referred to as a promising technology to extend human actions and intelligence to manipulating objects *** the tracking control of teleoperation systems,velocity measurements are necessary to provide feedback ***,due to hardware technology and cost constraints,the velocity measurements are not always *** addition,the time-varying communication delay makes it challenging to achieve tracking *** paper provides a solution to the issue of real-time tracking for teleoperation systems,subjected to unavailable velocity signals and time-varying communication *** order to estimate the velocity information,immersion and invariance(I&I)technique is employed to develop an exponential stability velocity *** the proposed velocity observer,a linear relationship between position and observation state is constructed,through which the need of solving partial differential and certain integral equations can be ***,the mean value theorem is exploited to separate the observation error terms,and hence,all functions in our observer can be analytically *** the estimated velocity information,a slave-torque feedback control law is presented.A novel Lyapunov-Krasovskii functional is constructed to establish asymptotic tracking *** particular,the relationship between the controller design parameters and the allowable maximum delay values is ***,simulation and experimental results reveal that the proposed velocity observer and controller can guarantee that the observation errors and tracking error converge to zero.

关键词： Asymptotic stability bilateral teleoperation time-varying delay velocity observer

来源：评论

学校读者我要写书评

暂无评论

Multi-Label Text Classification for Judicial Texts via Dual Graph and Label Feature Fusion 10

Multi-Label Text Classification for Judicial Texts via Dual ...

引用

10th IEEE Smart World Congress, SWC 2024

作者： Gu, Qiliang Lu, Qin Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Industrial Network and Information System Security Jinan China

ISBN: (纸本)9798331520861

The legal judgement prediction (LJP) of judicial texts represents a multi-label text classification (MLTC) problem, which in turn involves three distinct tasks: the prediction of charges, legal articles, and terms of penalty. Nevertheless, extant multi-label text classification models tend to eschew the consideration of multiple correlations and semantic information between labels when predicting judicial texts, which may result in the loss of pertinent information. Furthermore, these models do not take full advantage of the local and overall information of the labels in the process of selecting appropriate labels for the text using the multi-head attention mechanism. To address these issues, we propose a new model, BGFLFF, which explores label correlation and semantics among the three tasks by employing Graph Convolutional Network (GCN) and multi-head attention mechanisms. In particular, we propose a Bi-Graph Fusion GCN (BGF-GCN), which fuses the co-occurrence matrix of labels with the cosine similarity matrix, thereby fully exploiting the multiple correlations between labels. Furthermore, prior to embedding the tags, the interpretations of the labels are obtained via Google in order to enhance the semantic information between the labels. To further reinforce the interconnections between labels and text and more effectively comprehend the interrelationships between the three tasks, we propose a Multi-Head Label Feature Fusion Attentional Mechanism (MH-LFFAtt), which assigns distinct weights to the pertinent label information in the text by fusing the local and overall features of the labels. The experimental results demonstrate that the F1 score exhibits an improvement of up to 2. 2 8 % and a minimum of 1. 2 9 % across the various tasks of the two datasets. This evidence substantiates the assertion that BGFLFF outperforms the existing baseline model. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Node Confidence Determination Based Moving Target Defense Strategy for SDN 15

A Node Confidence Determination Based Moving Target Defense ...

引用

15th International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2023

作者： Sun, Shimin Xu, Guowei Han, Li Tianjin Key Laboratory of Autonomous Intelligent Technology and System School of Software Tiangong Tianjin China Tianjin Univ. of Technol. Natl. Eng. Laboratory for Computer Virus Prevention and Control Technology School of Computer Science and Engineering Tianjin China

ISBN: (纸本)9798350308693

With the rapid development of Internet technology, network assets have become an indispensable part of modern society. Especially in the face of high-value network assets, the attacker is faced with paying a greater cost to study the network structure. Due to the unknown attacker and attack means, the attacker has an advantage in the attack and defense situation. The moving target defense technique can flexibly change the static characteristics of the network attack surface and increase the difficulty for the attacker to detect the network, thus achieving the purpose of enhancing network security. Based on this technique, this paper proposes a defense strategy based on node confidence. It puts forward stricter constraints on the differential selection of address/port hopping paths, dynamically selects the hopping objects according to the node's confidence, and implements the defense strategy of differential complexity. This further increases the network's uncertainty and the difficulty for the attacker to detect the network structure. The experimental results show that in the path differentiation comparison, the maximum improvement is about 18% compared to the Dynamic Random Route Hopping strategy. In the CPU load experiment, the CPU load rate is reduced by about 4.625% on average compared to the Double Address Hopping strategy. Moreover, for larger hopping period, the proposed strategy also performs well in terms of CPU load rate. The proposed strategy also exhibits good performance in terms of CPU load ratio for large hopping cycles. © 2023 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

OpenDrift: Online Evolving Fraud Detection for Open-Category and Concept-Drift Transactions

OpenDrift: Online Evolving Fraud Detection for Open-Category...

引用

2023 IEEE International Conference on Web Services, ICWS 2023

作者： Wang, Cheng Chai, Songyao Zhu, Hangyu Department of Computer Science and Technology Tongji University Shanghai China Key Laboratory of Embedded System and Service Computing Ministry of Education China Shanghai Artificial Intelligence Laboratory Shanghai China

ISBN: (纸本)9798350304855

The rapid growth of electronic commerce brings convenience to modern life but comes with security risks by various cybercrimes in online payment services. Most existing security methods for fraud detection depend on the static learning paradigm, which trains a model over a static training dataset and deploys the trained model for inference with the frozen model parameters under the i.i.d. assumption. Unfortunately, this paradigm becomes incommensurate with the increasingly complicated and varying fraud patterns due to the untimely and delayed responses in the offline environment. Without sensing the evolution of fraud timely, it is challenging to train and deploy targeted countermeasures. The emerging means of fraud are not only reflected in the openness of their category, but also in the drift of their superimposed risk features. The interweaving of open-category and concept drift accelerates the process of existing methods becoming powerless. In this paper, we propose EvoFD, an online evolving fraud detection framework to enable continual learning to cope with undercurrent surges of evolving fraud. The core idea of EvoFD is to weaken the bias caused by the anchoring effect on the learned information. It learns in an online streaming fashion by using instructive representations as anchors. Specially, we maintain the progressively updatable class anchors and optimize the representation network to embed features and class anchors into a unified normalized space, where the training and predicting can be conducted simultaneously or independently. In the framework, we preserve the balanced replay memory for each class to accumulate knowledge and avoid forgetting. The advantages of our method are validated by extensive experiments over the real-world dataset from a prestigious bank. © 2023 IEEE.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

Improved Density Peaking Algorithm for Community Detection Based on Graph Representation Learning

引用

computer systems Science & Engineering 2022年第12期43卷 997-1008页

作者： Jiaming Wang Xiaolan Xie Xiaochun Cheng Yuhan Wang Guangxi Key Laboratory of Embedded Technology and Intelligent System Guilin541006GuangxiChina School of Information Science and Engineering Guilin University of TechnologyGuilin541006GuangxiChina Department of Computer Science Middlesex UniversityLondon

There is a large amount of information in the network data that we canexploit. It is difficult for classical community detection algorithms to handle network data with sparse topology. Representation learning of network data is usually paired with clustering algorithms to solve the community detection ***, there is always an unpredictable distribution of class clusters outputby graph representation learning. Therefore, we propose an improved densitypeak clustering algorithm (ILDPC) for the community detection problem, whichimproves the local density mechanism in the original algorithm and can betteraccommodate class clusters of different shapes. And we study the communitydetection in network data. The algorithm is paired with the benchmark modelGraph sample and aggregate (GraphSAGE) to show the adaptability of ILDPCfor community detection. The plotted decision diagram shows that the ILDPCalgorithm is more discriminative in selecting density peak points compared tothe original algorithm. Finally, the performance of K-means and other clusteringalgorithms on this benchmark model is compared, and the algorithm is proved tobe more suitable for community detection in sparse networks with the benchmarkmodel on the evaluation criterion F1-score. The sensitivity of the parameters ofthe ILDPC algorithm to the low-dimensional vector set output by the benchmarkmodel GraphSAGE is also analyzed.

关键词： Representation learning data mining low-dimensional embedding community detection density peaking algorithm

来源：评论

学校读者我要写书评

暂无评论

Research on Image Captioning Based on Vision-language Pre-trained Models 9

Research on Image Captioning Based on Vision-language Pre-tr...

引用

9th International Conference on Big Data and Information Analytics, BigDIA 2023

作者： Zou, Shiwei Xie, Yuxiang Yan, Jie Wei, Yingmei Luan, Xidao National University of Defense Technology Department of System Engineering Hunan China National University of Defense Technology Key Laboratory of Big Data Department of System Engineering Changsha Hunan China Changsha University Department of Computer Science Hunan China

ISBN: (纸本)9798350330076

Image captioning is a vision-language task that targets at describing an image by generating a coherent sentence automatically. This technology allows computers to understand and describe images like humans, enabling further processing of images. It combines computer vision and natural language processing, which has broad applications. This paper investigates the use of vision-language pre-trained models for image captioning. In this article, an encoder-decoder hybrid model based on PVT and BERT is pre-trained on a large number of image-text pairs, possessing both understanding and generation capabilities. It consists of three components: 1) an image encoder and a text encoder to extract image and text features respectively;2) a multi-modal encoder to align the two modalities;and 3) a text decoder to generate text descriptions. This paper focuses on enhancing the image encoder of the model, which is crucial for image captioning models as it extracts high-resolution image features. Reducing training time and computational costs can also improve the applicability of pre-trained models. Improvements are made to the original model by modifying the ViT model architecture of the image encoding module. A feature pyramid structure and a spatial reduction attention mechanism is introduced to extract high-resolution image features while reducing computational complexity and memory usage, thereby enhancing the universality of the model. The model adopts a pure Transformer architecture, discarding the convolutional structure, and achieves excellent performance. © 2023 IEEE.

关键词： Image enhancement

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：