检索结果-内蒙古大学图书馆

Cross-Modality Perturbation Synergy Attack for Person Re-identification

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Gong, Yunpeng Zhong, Zhun Qu, Yansong Luo, Zhiming Ji, Rongrong Jiang, Min School of Informatics Xiamen University China School of Computer Science and Information Engineering Hefei University of Technology China Department of Artificial Intelligence Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China School of Informatics Key Laboratory of Digital Protection and Intelligent Processing of Intangible CulturalHeritage of Fujian and Taiwan Ministry of Culture and Tourism Xiamen University Fujian Xiamen361005 China

In recent years, there has been significant research focusing on addressing security concerns in single-modal person re-identification (ReID) systems that are based on RGB images. However, the safety of cross-modality scenarios, which are more commonly encountered in practical applications involving images captured by infrared cameras, has not received adequate attention. The main challenge in cross-modality ReID lies in effectively dealing with visual differences between different modalities. For instance, infrared images are typically grayscale, unlike visible images that contain color information. Existing attack methods have primarily focused on the characteristics of the visible image modality, overlooking the features of other modalities and the variations in data distribution among different modalities. This oversight can potentially undermine the effectiveness of these methods in image retrieval across diverse modalities. This study represents the first exploration into the security of cross-modality ReID models and proposes a universal perturbation attack specifically designed for cross-modality ReID. This attack optimizes perturbations by leveraging gradients from diverse modality data, thereby disrupting the discriminator and reinforcing the differences between modalities. We conducted experiments on three widely used cross-modality datasets, namely RegDB, SYSU, and LLCM. The results not only demonstrate the effectiveness of our method but also provide insights for future improvements in the robustness of cross-modality ReID systems. © 2024, CC BY-NC-ND.

关键词： Infrared imaging

Efficiently Tackling Million-Dimensional Multiobjective Problems: A Direction Sampling and Fine-Tuning Approach

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Hong, Haokai Jiang, Min Lin, Qiuzhen Tan, Kay Chen Department of Artificial Intelligence Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan Ministry of Culture and Tourism School of Informatics Xiamen University Fujian361005 China College of Computer Science and Software Engineering Shenzhen University China Department of Computing Hong Kong Polytechnic University Hong Kong

We define very large-scale multiobjective optimization problems as optimizing multiple objectives (VLSMOPs) with more than 100,000 decision variables. These problems hold substantial significance, given the ubiquity of real-world scenarios necessitating the optimization of hundreds of thousands, if not millions, of variables. However, the larger dimension in VLSMOPs intensifies the curse of dimensionality and poses significant challenges for existing large-scale evolutionary multiobjective algorithms, rendering them more difficult to solve within the constraints of practical computing resources. To overcome this issue, we propose a novel approach called the very large-scale multiobjective optimization framework (VMOF). The method efficiently samples general yet suitable evolutionary directions in the very large-scale space and subsequently fine-tunes these directions to locate the Pareto-optimal solutions. To sample the most suitable evolutionary directions for different solutions, Thompson sampling is adopted for its effectiveness in recommending from a very large number of items within limited historical evaluations. Furthermore, a technique is designed for fine-tuning directions specific to tracking Pareto-optimal solutions. To understand the designed framework, we present our analysis of the framework and then evaluate VMOF using widely recognized benchmarks and real-world problems spanning dimensions from 100 to 1,000,000. Experimental results demonstrate that our method exhibits superior performance not only on LSMOPs but also on VLSMOPs when compared to existing algorithms. Copyright © 2023, The Authors. All rights reserved.

关键词： Multiobjective optimization

Fea-Accu cascade for face detection

学校读者我要写书评

暂无评论

Fea-Accu cascade for face detection

IEEE International Conference on Image processing

作者： Shengye Yan Shiguang Shan Xilin Chen Wen Gao Chinese Academy and Sciences Beijing China Institute of Computing Technology Digital Media Research Center Chinese Academy and Sciences Beijing China Chinese Academy of Sciences Beijing Beijing CN Key Laboratory of Intelligent Information Processing Chinese Academy and Sciences Beijing China School of EE & CS Peking University Beijing China

Aiming at unloading the high training time burden of the popular cascaded classifier, in this paper, a novel cascade structure called Fea-Accu cascade is proposed. In Fea-Accu cascade training, the times of feature selection are largely reduced by enhancing the correlation among different stage classifiers of the cascaded classifier. In detail, for each stage classifier, before selecting new features out, the features selected out by previous stage classifiers are reused through creating new corresponding weak classifiers. To verify the efficiency and effectiveness of the proposed method, experiment is designed on frontal face detection problem. The experimental results show that it can largely reduce the training time. A frontal face detector with state-of-the-art classification performance can be learned in less than 10 hours.

关键词： Face detection Detectors Content addressable storage Design methodology Information processing Computer vision Cameras Robustness Boosting Computer architecture

An Interpretable MRI Reconstruction Network with Two-grid-cycle Correction and Geometric Prior Distillation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Fan, Xiaohong Yang, Yin Chen, Ke Zhang, Jianping Dong, Ke The School of Mathematics and Computational Science Xiangtan University Key Laboratory of Intelligent Computing & Information Processing of Ministry of Education Xiangtan411105 China The School of Mathematics and Computational Science Xiangtan University Hunan National Applied Mathematics Center Hunan Key Laboratory for Computation and Simulation in Science and Engineering Xiangtan411105 China Centre for Mathematical Imaging Techniques Department of Mathematical Sciences The University of Liverpool Merseyside LiverpoolL6972L United Kingdom The School of Mathematics and Computational Science Xiangtan University Hunan National Applied Mathematics Center Key Laboratory of Intelligent Computing & Information Processing of Ministry of Education Xiangtan411105 China Department of Radiation Oncology Xiangtan Central Hospital Xiangtan411101 China

Although existing deep learning compressed-sensing-based Magnetic Resonance imaging (CS-MRI) methods have achieved considerably impressive performance, explainability and generalizability continue to be challenging for such methods since the transition from mathematical analysis to network design not always natural enough, often most of them are not flexible enough to handle multi-sampling-ratio reconstruction assignments. In this work, to tackle explainability and generalizability, we propose a unifying deep unfolding multi-sampling-ratio interpretable CS-MRI framework. The combined approach offers more generalizability than previous works whereas deep learning gains explainability through a geometric prior module. Inspired by the multigrid algorithm, we first embed the CSMRI-based optimization algorithm into correction-distillation scheme that consists of three ingredients: pre-relaxation module, correction module and geometric prior distillation module. Furthermore, we employ a condition module to learn adaptively step-length and noise level, which enables the proposed framework to jointly train multi-ratio tasks through a single model. The proposed model not only compensates for the lost contextual information of reconstructed image which is refined from low frequency error in geometric characteristic k-space, but also integrates the theoretical guarantee of model-based methods and the superior reconstruction performances of deep learning-based methods. Therefore, it can give us a novel perspective to design biomedical imaging networks. Numerical experiments show that our framework outperforms state-of-the-art methods in terms of qualitative and quantitative evaluations. Our method achieves 3.18 dB improvement at low CS ratio 10% and average 1.42 dB improvement over other comparison methods on brain dataset using Cartesian sampling mask. Copyright © 2022, The Authors. All rights reserved.

关键词： Distillation

SurgicalGaussian: Deformable 3D Gaussians for High-Fidelity Surgical Scene Reconstruction

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xie, Weixing Yao, Junfeng Cao, Xianpeng Lin, Qiqin Tang, Zerui Dong, Xiao Guo, Xiaohu Center for Digital Media Computing School of Film School of Informatics Xiamen University Xiamen China National Institute for Data Science in Health and Medicine Xiamen University China Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan Ministry of Culture and Tourism China Guangdong Provincial Key Laboratory IRADS Department of Computer Science BNU-HKBU United International College Zhuhai China Department of Computer Science The University of Texas at Dallas Dallas United States

Dynamic reconstruction of deformable tissues in endoscopic video is a key technology for robot-assisted surgery. Recent reconstruction methods based on neural radiance fields (NeRFs) have achieved remarkable results in the reconstruction of surgical scenes. However, based on implicit representation, NeRFs struggle to capture the intricate details of objects in the scene and cannot achieve real-time rendering. In addition, restricted single view perception and occluded instruments also propose special challenges in surgical scene reconstruction. To address these issues, we develop SurgicalGaussian, a deformable 3D Gaussian Splatting method to model dynamic surgical scenes. Our approach models the spatio-temporal features of soft tissues at each time stamp via a forward-mapping deformation MLP and regularization to constrain local 3D Gaussians to comply with consistent movement. With the depth initialization strategy and tool mask-guided training, our method can remove surgical instruments and reconstruct high-fidelity surgical scenes. Through experiments on various surgical videos, our network outperforms existing method on many aspects, including rendering quality, rendering speed and GPU usage. The project page can be found at https://***. © 2024, CC BY-SA.

关键词： Tissue

DRSM: EFFICIENT NEURAL 4D DECOMPOSITION FOR DYNAMIC RECONSTRUCTION IN STATIONARY MONOCULAR CAMERAS

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xie, Weixing Dong, Xiao Yang, Yong Lin, Qiqin Chen, Jingze Yao, Junfeng Guo, Xiaohu Center for Digital Media Computing School of Film School of Informatics Xiamen University China National Institute for Data Science in Health and Medicine Xiamen University China Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan Ministry of Culture and Tourism Department of Computer Science BNU-HKBU United International College China Department of Computer Science The University of Texas Dallas United States

With the popularity of monocular videos generated by video sharing and live broadcasting applications, reconstructing and editing dynamic scenes in stationary monocular cameras has become a special but anticipated technology. In contrast to scene reconstructions that exploit multi-view observations, the problem of modeling a dynamic scene from a single view is significantly more under-constrained and ill-posed. Inspired by recent progress in neural rendering, we present a novel framework to tackle 4D decomposition problem for dynamic scenes in monocular cameras. Our framework utilizes decomposed static and dynamic feature planes to represent 4D scenes and emphasizes the learning of dynamic regions through dense ray casting. Inadequate 3D clues from a single-view and occlusion are also particular challenges in scene reconstruction. To overcome these difficulties, we propose deep supervised optimization and ray casting strategies. With experiments on various videos, our method generates higher-fidelity results than existing methods for single-view dynamic scene representation. © 2024, CC BY.

关键词： Cameras

Risk analysis of system security based on evidence theory

学校读者我要写书评

暂无评论

Risk analysis of system security based on evidence theory

International Conference on Computer Design and Applications (ICCDA)

作者： Peida Xu Yong Deng Jianling Xu Xiaoyan Su Key Laboratory of Digital Agricultural Early-warning Technology Ministry of Agriculture of China Beijing China Key Laboratory of Intelligent Computing & Information Processing of Ministry of Education Xiangtan University China School of Electronics & Information Technology Shanghai Jiaotong University China School of Electronics & Information Technology Shanghai Jiaotong University Shanghai China Hangzhou Key Laboratory of E-Business and Information Security Hangzhou Normal University Shanghai Zhejiang China Grain Economics Institute Nanjing University of Finance and Economics Nanjing China

ISBN: (纸本)9781424471645;9781424471638

Risk evaluation is very important to the design and improvement of physical protection systems. In this paper, an evaluation method of multi-source information fusion is proposed based on the D-S evidence theory. In the proposed method, each individual component of the protection system in the simulated plane is modeled. Then, the threat report of each component according to the specific tactics is determined based on its real environment. Finally, the comprehensive threat distribution is obtained based on through the D-S evidence theory to combine multi-sources information. The proposed method can easily applied to the evaluation of the effectiveness of the protection system. We make the total threat of the protection system lowest through changes of the protection resources allocation. A numerical example is used to illustrate the efficiency of the proposed method.

关键词： Risk analysis Protection Information security Information technology Computer security Laboratories Environmental economics Educational technology Agriculture Finance

Super-resolving Compressed Images via Parallel and Series Integration of Artifact Reduction and Resolution Enhancement

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Luo, Hongming Zhou, Fei Liao, Guangsen Qiu, Guoping College of Electronics and Information Engineering Shenzhen University China Peng Cheng Laboratory Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen China Shenzhen Key Laboratory of Digital Creative Technology China Shenzhen Institute for Artificial Intelligence and Robotics for Society Shenzhen China School of Computer Science University of Nottingham NottinghamNG8 1BB United Kingdom Guangdong-Hong Kong Joint Laboratory for Big Data Imaging and Communication Guangdong Shenzhen China

In real-world applications, such as sharing photos on social media platforms, images are always not only sub-sampled but also heavily compressed thus often containing various artefacts. Simple methods for enhancing the resolution of such images will exacerbate the artefacts, rendering them visually objectionable. In spite of its high practical values, super-resolving compressed images is not well studied in the literature. In this paper, we propose a novel compressed image super resolution (CISR) framework based on parallel and series integration of artefacts removal and resolution enhancement. Based on a mathematical inference model for estimating a clean low-resolution (LR) image and a clean high-resolution (HR) image from a down-sampled and compressed observation, we have designed a CISR architecture consisting of two deep neural network modules: the artefacts removal module (ARM) and the resolution enhancement module (REM). The ARM and the REM work in parallel with both taking the compressed LR image as their inputs, at the same time they also work in series with the REM taking the output of the ARM as one of its inputs and the ARM taking the output of the REM as its other input. A technique called unfolding is introduced to recursively suppress the compression artefacts and restore the image resolution. A unique feature of our CISR system is that it exploits the parallel and series connections between the ARM and the REM, and recursive optimization to reduce the model's dependency on specific types of degradation thus making it possible to train a single model to super-resolve images compressed by different methods to different qualities. Experiments are conducted on a mixture of JPEG and WebP compressed images without assuming apriori compression type and compression quality factor. To demonstrate our technique's real-world application value, we have also applied the trained models directly to restore social media images which have undergone scaling and compre

关键词： Deep neural networks

Dense Invariant Feature Based Support Vector Ranking for Person Re-identification

学校读者我要写书评

暂无评论

Dense Invariant Feature Based Support Vector Ranking for Per...

IEEE Global Conference on Signal and Information processing

作者： Shoubiao Tan Feng Zheng Ling Shao Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei 230039 China Department of Electronic and Electrical Engineering The University of Sheffield Mappin Street Sheffield S1 3JD UK Department of Computer Science and Digital Technologies Northumbria University Newcastle upon Tyne NE1 8ST UK

ISBN: (纸本)9781479975921

Recently, support vector ranking has been adopted to address the challenging person re-identification problem. However, the ranking model based on ordinary global features cannot represent the significant variation of pose and viewpoint across camera views. Thus, a novel ranking method which fuses the dense invariant features is proposed in this paper to model the variation of images across camera views. By maximizing the margin and minimizing the error score for the fused features, an optimal space for ranking has been learned. Due to the invariance of the dense invariant features and the fusion of the bidirectional features, the proposed method significantly outperforms the original support vector ranking algorithm and is competitive with state-of-the-art techniques on two challenging datasets, showing its potential for real-world person re-identification.

关键词： Person Re-identification Dense Invariant Feature Support Vector Ranking Feature Fusion