检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Hou, Wenzheng Xu, Qianqian Yang, Zhiyong Bao, Shilong He, Yuan Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China State Key Laboratory of Information Security Institute of Information Engineering CAS Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Alibaba Group Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China Artificial Intelligence Research Center Peng Cheng Laboratory Shenzhen China

It is well-known that deep learning models are vulnerable to adversarial examples. Existing studies of adversarial training have made great progress against this challenge. As a typical trait, they often assume that the class distribution is overall balanced. However, long-tail datasets are ubiquitous in a wide spectrum of applications, where the amount of head class instances is larger than the tail classes. Under such a scenario, AUC is a much more reasonable metric than accuracy since it is insensitive toward class distribution. Motivated by this, we present an early trial to explore adversarial training methods to optimize AUC. The main challenge lies in that the positive and negative examples are tightly coupled in the objective function. As a direct result, one cannot generate adversarial examples without a full scan of the dataset. To address this issue, based on a concavity regularization scheme, we reformulate the AUC optimization problem as a saddle point problem, where the objective becomes an instance-wise function. This leads to an end-to-end training protocol. Furthermore, we provide a convergence guarantee of the proposed algorithm. Our analysis differs from the existing studies since the algorithm is asked to generate adversarial examples by calculating the gradient of a min-max problem. Finally, the extensive experimental results show the performance and robustness of our algorithm in three long-tail datasets. © 2022, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Domain generalization for document authentication against practical recapturing attacks

arXiv

引用

arXiv 2021年

作者： Chen, Changsheng Zhang, Shuzheng Lan, Fengbo Huang, Jiwu The Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security National Engineering Laboratory for Big Data System Computing Technology College of Electronics and Information Engineering Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society China

Recapturing attack can be employed as a simple but effective anti-forensic tool for digital document images. Inspired by the document inspection process that compares a questioned document against a reference sample, we proposed a document recapture detection scheme by employing Siamese network to compare and extract distinct features in a recapture document image. The proposed algorithm takes advantages of both metric learning and image forensic techniques. Instead of adopting Euclidean distance-based loss function, we integrate the forensic similarity function with a triplet loss and a normalized softmax loss. After training with the proposed triplet selection strategy, the resulting feature embedding clusters the genuine samples near the reference while pushes the recaptured samples apart. In the experiment, we consider practical domain generalization problems, such as the variations in printing/imaging devices, substrates, recapturing channels, and document types. To evaluate the robustness of different approaches, we benchmark some popular off-the-shelf machine learning-based approaches, a state-of-the-art document image detection scheme, and the proposed schemes with different network backbones under various experimental protocols. Experimental results show that the proposed schemes with different network backbones have consistently outperformed the state-of-the-art approaches under different experimental settings. Specifically, under the most challenging scenario in our experiment, i.e., evaluation across different types of documents that produced by different devices, we have achieved less than 5.00% APCER (Attack Presentation Classification Error Rate) and 5.56% BPCER (Bona Fide Presentation Classification Error Rate) by the proposed network with ResNeXt101 backbone at 5% BPCER decision *** Codes 94A08 Copyright © 2021, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

MedBLIP: A multimodal method of medical question-answering based on fine-tuning large language model

引用

Computerized Medical Imaging and Graphics 2025年 124卷

作者： Lejun Gong Jiaming Yang Shengyuan Han Yimu Ji Jiangsu Key Lab of Big Data Security & Intelligent Processing School of Computer Science Nanjing University of Posts and Telecommunications Nanjing 210023 China Institute of High Performance Computing and Bigdata Nanjing University of Posts and Telecommunications Nanjing 210023 China

Medical visual question answering is crucial for effectively interpreting medical images containing clinically relevant information. This study proposes a method called MedBLIP (Medical Treatment Bootstrapping Language-Image Pretraining) to tackle visual language generation tasks related to chest X-rays in the medical field. The method combine an image encoder with a large-scale language model, and effectively generates medical question-answering text through a strategy of freezing the image encoder based on the BLIP-2 model. Firstly, chest X-ray images are preprocessed, and an image sample generation algorithm is used to enhance the text data of doctor-patient question-answering, thereby increasing data diversity. Then, a multi-layer convolutional image feature extractor is introduced to better capture the feature representation of medical images. During the fine-tuning process of the large language generation model, a new unfreezing strategy is proposed, which is to unfreeze different proportions of the weights of the fully connected layer to adapt to the data in the medical field. The image feature extractor is responsible for extracting key features from images, providing the model with rich visual information, while the text feature extractor accurately captures the essential requirements of the user's question. Through their synergistic interaction, the model can more effectively integrate medical images and user inquiries, thereby generating more accurate and relevant output content. The experimental results show that unfreezing 31.25 % of the weights of the fully connected layer can significantly improve the performance of the model, with ROUGE-L reaching 66.12 %, and providing a more accurate and efficient answer generation solution for the medical field. The method of this study has potential applications in the field of medical language generation tasks. Although the proposed model cannot yet fully replace human radiologists, it plays an indispensable rol

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based forgery attack on document images

arXiv

引用

arXiv 2021年

作者： Zhao, Lin Chen, Changsheng Huang, Jiwu the Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security National Engineering Laboratory for Big Data System Computing Technology College of Electronics and Information Engineering Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society China

With the ongoing popularization of online services, the digital document images have been used in various applications. Meanwhile, there have emerged some deep learning-based text editing algorithms which alter the textual information of an image in an end-to-end fashion. In this work, we present a low-cost document forgery algorithm by the existing deep learning-based technologies to edit practical document images. To achieve this goal, the limitations of existing text editing algorithms towards complicated characters and complex background are addressed by a set of network design strategies. First, the unnecessary confusion in the supervision data is avoided by disentangling the textual and background information in the source images. Second, to capture the structure of some complicated components, the text skeleton is provided as auxiliary information and the continuity in texture is considered explicitly in the loss function. Third, the forgery traces induced by the text editing operation are mitigated by some post-processing operations which consider the distortions from the print-and-scan channel. Quantitative comparisons of the proposed method and the exiting approach have shown the advantages of our design by reducing the about 2/3 reconstruction error measured in MSE, improving reconstruction quality measured in PSNR and in SSIM by 4 dB and 0.21, respectively. Qualitative experiments have confirmed that the reconstruction results of the proposed method are visually better than the existing approach in both complicated characters and complex texture. More importantly, we have demonstrated the performance of the proposed document forgery algorithm under a practical scenario where an attacker is able to alter the textual information in an identity document using only one sample in the target domain. The forged-and-recaptured samples created by the proposed text editing attack and recapturing operation have successfully fooled some existing document authenticat

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

The Minority Matters: A Diversity-Promoting Collaborative Metric Learning Algorithm

arXiv

引用

arXiv 2022年

作者： Bao, Shilong Xu, Qianqian Yang, Zhiyong He, Yuan Cao, Xiaochun Huang, Qingming State Key Laboratory of Information Security Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China School of Computer Science and Tech. University of Chinese Academy of Sciences China Alibaba Group China School of Cyber Science and Technology Shenzhen Campus Sun Yat-sen University China Key Laboratory of Big Data Mining and Knowledge Management CAS China Peng Cheng Laboratory China

Collaborative Metric Learning (CML) has recently emerged as a popular method in recommendation systems (RS), closing the gap between metric learning and Collaborative Filtering. Following the convention of RS, existing methods exploit unique user representation in their model design. This paper focuses on a challenging scenario where a user has multiple categories of interests. Under this setting, we argue that the unique user representation might induce preference bias, especially when the item category distribution is imbalanced. To address this issue, we propose a novel method called Diversity-Promoting Collaborative Metric Learning (DPCML), with the hope of considering the commonly ignored minority interest of the user. The key idea behind DPCML is to include a multiple set of representations for each user in the system. Based on this embedding paradigm, user preference toward an item is aggregated from different embeddings by taking the minimum item-user distance among the user embedding set. Furthermore, we observe that the diversity of the embeddings for the same user also plays an essential role in the model. To this end, we propose a diversity control regularization term to accommodate the multi-vector representation strategy better. Theoretically, we show that DPCML could generalize well to unseen test data by tackling the challenge of the annoying operation that comes from the minimum value. Experiments over a range of benchmark datasets speak to the efficacy of DPCML. © 2022, CC BY-NC-SA.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Research on SDN Multi Controller Deployment based on K-means++

Research on SDN Multi Controller Deployment based on K-means...

引用

2020 International Conference on 5G Mobile Communication and Information Science, MCIS-5G 2020

作者： Yue, Li Junyan, Chen Chuxin, Liang Xiaochun, Lei School of Computer and Information Security Guilin University of Electronic Technology Guilin541004 China Guangxi Cloud Computing and Big Data Collaborative Innovation Center Guilin541001 China Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin541004 China

In large-scale SDN network, a single centralized controller can not meet the demand, and multiple controllers are needed to deal with the problem, which leads to the problem of multi control balanced deployment. In this paper, the topology of SDN switches and links is known. The main research contents are as follows: The mathematical model of SDN multi controller deployment is established, and the appropriate network topology is selected and the multi controller deployment problem is solved. In the research, the number of controllers needed in the network and the switches managed by each controller is determined by the algorithm results, and the mapping relationship between controllers and switches is established. By analyzing the deployment results of the same network topology under different algorithms, the influence of different clustering algorithms on the experimental results is obtained. At the same time, the better deployment experiment results are simulated. © 2020 Published under licence by IOP Publishing Ltd.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Community-based message forwarding in mobile social networks

Community-based message forwarding in mobile social networks

引用

2019 International Conference on Advances in Computer Technology, Information Science and Communications, CTISC 2019

作者： Chen, Zhiming Xiang, Yang School of Computer Nanjing University of Posts and Telecommunications Nanjing210023 China Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing210023 China

ISBN: (纸本)9789897583575

With the popularity of various smart devices and the application of sensor network technology, message transmission using mobile devices is becoming widespread. This paper focuses on the forwarding in mobile social network (MSN). The MSN is a special Delay Tolerant Network (DTN) consisting of mobile nodes. In MSN, nodes move and share information with each other through carried short-range wireless communication devices. Mobile nodes in the MSN typically access some building areas more frequently, such as schools, companies, or apartments, while visiting other areas, such as the roads between buildings, less frequently. The building areas that nodes frequently visit are called communities. To increase delivery ratio and reduce transmission time in MSN, this paper proposes a novel zero-knowledge multi-copy routing algorithm, Mixed Message Forwarding (MMF) which exploits and improves the metric, namely centrality. Centrality reflects the importance of a node in the network. MMF improves copy diffusion by using different directions of node movement as well. Special facilities called boundary boxes are added to the network scenario. Boundary boxes are special throw boxes. Throw boxes are relays with large storage space and fixed position. MMF is designed and evaluated, which utilizes the aforementioned boundary boxes to reduce transmission delay. The simulation results show that the MMF can improve the delivery ratio and reduce the transmission delay, compared with other algorithms. © 2019 by SCITEPRESS - Science and Technology Publications, Lda.

关键词： Delay tolerant networks

来源：评论

学校读者我要写书评

暂无评论

Harnessing Low-Fidelity data to Accelerate Bayesian Optimization via Posterior Regularization

Harnessing Low-Fidelity Data to Accelerate Bayesian Optimiza...

引用

International Conference on big data and Smart Computing (bigCOMP)

作者： Bin Liu School of Computer Science Jiangsu Key Lab of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (数字)9781728160344

ISBN: (纸本)9781728160351

Bayesian optimization (BO) is a powerful paradigm for derivative-free global optimization of a black-box objective function (BOF) that is expensive to evaluate. However, the overhead of BO can still be prohibitive for problems with highly expensive function evaluations. In this paper, we investigate how to reduce the required number of function evaluations for BO without compromise in solution quality. We explore the idea of posterior regularization to harness low fidelity (LF) data within the Gaussian process upper confidence bound (GP-UCB) framework. The LF data can arise from previous evaluations of an LF approximation of the BOF or a related optimization task. An extra GP model called LF-GP is trained to fit the LF data. We develop an operator termed dynamic weighted product of experts (DW-POE) fusion. The regularization is induced by this operator on the posterior of the BOF. The impact of the LF GP model on the resulting regularized posterior is adaptively adjusted via Bayesian formalism. Extensive experimental results on benchmark BOF optimization tasks demonstrate the superior performance of the proposed algorithm over state-of-the-art.

关键词： Optimization Hafnium Adaptation models Bayes methods Heuristic algorithms data models Acceleration

来源：评论

学校读者我要写书评

暂无评论

Congestion Relief in Downlink OFDMA Cellular System Using Inter-Cell Relay

引用

China Communications 2019年第4期16卷 35-46页

作者： Weifeng Lu Mingqi Zhu Jia Xu Siguang Chen Lijun Yang Jian Xu School of Computer Science Nanjing University of Posts and Telecommunications Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications College of Internet of Things Nanjing University of Posts and Telecommunications School of Computer Science and Engineering Nanjing University of Science and Technology

This paper proposes the concept of inter-cell relay for downlink orthogonal frequency division multiple access(OFDMA) cellular systems, which uses multi-hop to relay calls from overloaded cells to light-load neighboring cells. It is shown that when using inter-cell relay, the number of calls in the congestion cell can be significantly increased. The congestion cell is divided into two parts. One is called non-relay area(NRA), in which a call directly communicates with the base station(BS) of a congested cell. The other is called relay area(RA), in which a call communicates with the BS of a neighboring cell through a relay station(RS). The two parts have different user-call densities. By adjusting the densities of two parts, we will maximize the number of supported calls inside a congested cell. The results show the benefits gained from inter-cell relay in congestion relief, which can reduce cell congestion by fully utilizing the available resources in the neighboring cells.

关键词： OFDMA cellular system congestion relief optimization problem inter-cell relay

来源：评论

学校读者我要写书评

暂无评论

Size-Invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection

arXiv

引用

arXiv 2024年

作者： Li, Feiran Xu, Qianqian Bao, Shilong Yang, Zhiyong Cong, Runmin Cao, Xiaochun Huang, Qingming Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Science Beijing Jiaotong University Beijing China School of Control Science and Engineering Shandong University Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Cyber Science and Tech. Sun Yat-Sen University Shenzhen Campus China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method. The code is available at https://***/Ferry-Li/SI-SOD. Copyright © 2024, The Authors. All rights reserved.

关键词： Object detection

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：