检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Chen, Yadang Chen, Sihan Yang, Zhi-Xin Wu, Enhua Engineering Research Center of Digital Forensics Ministry of Education Nanjing University of Information Science and Technology Nanjing210044 China School of Computer Science Nanjing University of Information Science and Technology Nanjing210044 China State Key Laboratory of Internet of Things for Smart City Department of Electromechanical Engineering University of Macau 999078 China State Key Laboratory of Computer Science Institute of Software University of Chinese Academy of Sciences Beijing100190 China

Few-shot semantic segmentation uses a few annotated data of a specific class in the support set to segment the target of the same class in the query set. Most existing approaches fail to perform well when there are significant intra-class variances. This paper alleviates the problem by concentrating on mining the query image and using the support set as supplementary information. First, it proposes a Query Prototype Generation Module to generate a query foreground prototype from the query features. Specifically, we use both prototype-level and pixel-level similarity matching to generate two complementary initial prototypes, which we then integrate to create a discriminative query foreground prototype. Second, we propose a Support Auxiliary Refinement Module to further guide the final precise prediction of the query image by leveraging the target category information of the support set through step-by-step mining. Specifically, we generate a query-support mixture prototype based on the support prototype representation obtained using the attention mechanism. Then we generate a support supplement prototype to complement the missing information by encoding over the foreground regions that the query-support mixture prototype fails to segment out. Extensive experiments on PASCAL-5i and COCO-20i demonstrate that our model outperforms the prior works of few-shot segmentation. © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

PREIM3D: 3D Consistent Precise Image Attribute Editing from a Single Image

PREIM3D: 3D Consistent Precise Image Attribute Editing from ...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Jianhui Li Jianmin Li Haoji Zhang Shilong Liu Zhengyi Wang Zihao Xiao Kaiwen Zheng Jun Zhu Department of Computer Science and Technology Institute for AI BNRist Tsinghua University State Key Laboratory of Astronautic dynamics Xi'an Satellite Control Center RealAI

We study the 3D-aware image attribute editing problem in this paper, which has wide applications in practice. Recent methods solved the problem by training a shared encoder to map images into a 3D generator's latent space or by per-image latent code optimization and then edited images in the latent space. Despite their promising results near the input view, they still suffer from the 3D inconsistency of produced images at large camera poses and imprecise image attribute editing, like affecting unspecified attributes during editing. For more efficient image inversion, we train a shared encoder for all images. To alleviate 3D inconsistency at large camera poses, we propose two novel methods, an alternating training scheme and a multi-view identity loss, to maintain 3D consistency and subject identity. As for imprecise image editing, we attribute the problem to the gap between the latent space of real images and that of generated images. We compare the latent space and inversion manifold of GAN models and demonstrate that editing in the inversion manifold can achieve better results in both quantitative and qualitative evaluations. Extensive experiments show that our method produces more 3D consistent images and achieves more precise image editing than previous work. Source code and pretrained models can be found on our project page: https://***/Preim3D/.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DifAttack++: Query-Efficient Black-Box Adversarial Attack via Hierarchical Disentangled Feature Space in Cross Domain

arXiv

引用

arXiv 2024年

作者： Liu, Jun Zhou, Jiantao Zeng, Jiandian Tian, Jinyu Li, Zheng State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science University of Macau China Institute of Artificial Intelligence and Future Networks Beijing Normal University China School of Computer Science and Engineering Macau University of Science and Technology China

This work investigates efficient score-based black-box adversarial attacks with a high Attack Success Rate (ASR) and good generalizability. We design a novel attack method based on a hierarchical DIsentangled Feature space, called DifAttack++, which differs significantly from the existing ones operating over the entire feature space. Specifically, DifAttack++ firstly disentangles an image’s latent feature into an Adversarial Feature (AF) and a Visual Feature (VF) via an autoencoder equipped with our specially designed Hierarchical Decouple-Fusion (HDF) module, where the AF dominates the adversarial capability of an image, while the VF largely determines its visual appearance. We train such two autoencoders for the clean and adversarial image domains (i.e., cross-domain) respectively to achieve image reconstructions and feature disentanglement, by using pairs of clean images and their Adversarial Examples (AEs) generated from available surrogate models via white-box attack methods. Eventually, in the black-box attack stage, DifAttack++ iteratively optimizes the AF according to the query feedback from the victim model until a successful AE is generated, while keeping the VF unaltered. Extensive experimental results demonstrate that our DifAttack++ leads to superior ASR and query efficiency than state-of-the-art methods, meanwhile exhibiting much better visual quality of AEs. The code is available at https://***/csjunjun/***. © 2024, CC BY-NC-ND.

关键词： Codes (symbols)

来源：评论

学校读者我要写书评

暂无评论

SGBA: A Stealthy Scapegoat Backdoor Attack against Deep Neural Networks

arXiv

引用

arXiv 2021年

作者： He, Ying Shen, Zhili Xia, Chang Hua, Jingyu Tong, Wei Zhong, Sheng The Computer Science and Technology Department Nanjing University Nanjing210023 China The State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China

Outsourced deep neural networks have been demonstrated to suffer from patch-based trojan attacks, in which an adversary poisons the training sets to inject a backdoor in the obtained model so that regular inputs can be still labeled correctly while those carrying a specific trigger are falsely given a target label. Due to the severity of such attacks, many backdoor detection and containment systems have recently, been proposed for deep neural networks. One major category among them are various model inspection schemes, which hope to detect backdoors before deploying models from non-trusted third-parties. In this paper, we show that such state-of-the-art schemes can be defeated by a so-called Scapegoat Backdoor Attack, which introduces a benign scapegoat trigger in data poisoning to prevent the defender from reversing the real abnormal trigger. In addition, it confines the values of network parameters within the same variances of those from clean model during training, which further significantly enhances the difficulty of the defender to learn the differences between legal and illegal models through machine-learning approaches. Our experiments on 3 popular datasets show that it can escape detection by all five state-of-the-art model inspection schemes. Moreover, this attack brings almost no side-effects on the attack effectiveness and guarantees the universal feature of the trigger compared with original patch-based trojan attacks. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

novel Personalized Multimedia Recommendation Systems Using Tensor Singular-Value-Decomposition

Novel Personalized Multimedia Recommendation Systems Using T...

引用

2023 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting, BMSB 2023

作者： Chang, Shih Yu Wu, Hsiao-Chun Yan, Kun Chen, Xinjia Wu, Yiyan San Jose State University Department of Applied Data Science San JoseCA95192 United States Louisiana State University School of Electrical Engineering and Computer Science Baton RougeLA70803 United States Guilin University of Electronic Technology Guangxi Key Laboratory of Wireless Wideband Communication and Signal Processing Guilin541004 China Guilin University of Electronic Technology Department of Information and Telecommunication Guilin541004 China Northwestern State University of Louisiana Department of Engineering Technology NatchitochesLA71497 United States Communications Research Centre Canada OttawaONK2H 8S2 Canada

ISBN: (纸本)9798350321524

Nowadays, multimedia data are often produced by various sources, e.g., Internet of Things (IoT), social media, customer databases, etc. As tremendous multimedia data are produced every day, users or E-commerce customers cannot infer information from such data by themselves and therefore recommender systems have been developed to help users to select the products or services which better fit users' preferences or requirements. Nonetheless, there exists few works on the incorporation of side information or multiple attributes about items into the design of a more robust recommender system. In this work, we propose a novel approach based on the third-order tensor singular-value-decomposition (T3-SVD) to design new personalized multimedia recommender systems (PMRSs) for internet users. A PMRS can dynamically adjust its recommendation strategy subject to a particular user's on-line transaction behavior. To evaluate the effectiveness of our proposed PMRS based on T3-SVD, we compare the performances of our proposed new PMRS and two other existing tensor-based recommendation systems over realworld data in terms of normalized root-mean-square error (NRMSE). As a result, our proposed new PMRS greatly outperforms the other two existing systems. © 2023 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

A genetic programming method for classifier construction and cost learning in high-dimensional unbalanced classification 20

A genetic programming method for classifier construction and...

引用

2020 Genetic and Evolutionary Computation Conference, GECCO 2020

作者： Pei, Wenbin Xue, Bing Shang, Lin Zhang, Mengjie School of Engineering and Computer Science Victoria University of Wellington New Zealand State Key Laboratory for Novel Software Technology Nanjing University China

ISBN: (纸本)9781450371278

Cost-sensitive learning has been widely used to address the problem of class imbalance. However, cost matrices are often manually designed. In many real-world applications, cost values are often unknown because of the limited domain knowledge. This paper proposes a new genetic programming method to construct cost-sensitive classifiers, which do not require the manually designed cost values. The experimental results show that the proposed method often outperforms existing GP methods. © 2020 Owner/Author.

关键词： Genetic programming

来源：评论

学校读者我要写书评

暂无评论

Temporal Feature Matters: A Framework for Diffusion Model Quantization

arXiv

引用

arXiv 2024年

作者： Huang, Yushi Gong, Ruihao Liu, Xianglong Liu, Jing Li, Yuhang Lu, Jiwen Tao, Dacheng Electrical and Computer Engineering Department Hong Kong University of Science and Technology Hong Kong State Key Laboratory of Software Development Environment Beihang University China Department of Data Science and AI Faculty of IT Monash University Australia Electrical Engineering Department Yale University United States Department of Automation Tsinghua University China School of Computer Science and Engineering Nanyang Technological University Singapore

The Diffusion models, widely used for image generation, face significant challenges related to their broad applicability due to prolonged inference times and high memory demands. Efficient Post-Training Quantization (PTQ) is crucial to address these issues. However, unlike traditional models, diffusion models critically rely on the time-step for the multi-round denoising. Typically, each time-step is encoded into a hypersensitive temporal feature by several modules. Despite this, existing PTQ methods do not optimize these modules individually. Instead, they employ unsuitable reconstruction objectives and complex calibration methods, leading to significant disturbances in the temporal feature and denoising trajectory, as well as reduced compression efficiency. To address these challenges, we introduce a novel quantization framework that includes three strategies: 1) TIB-based Maintenance: Based on our innovative Temporal Information Block (TIB) definition, Temporal Information-aware Reconstruction (TIAR) and Finite Set Calibration (FSC) are developed to efficiently align original temporal features. 2) Cache-based Maintenance: Instead of indirect and complex optimization for the related modules, pre-computing and caching quantized counterparts of temporal features are developed to minimize errors. 3) Disturbance-aware Selection: Employ temporal feature errors to guide a fine-grained selection between the two maintenance strategies for further disturbance reduction. This framework preserves most of the temporal information and ensures high-quality end-to-end generation. Extensive testing on various datasets, diffusion models and hardware confirms our superior performance and acceleration. © 2024, CC BY.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Multi-block-Single-probe Variance Reduced Estimator for Coupled Compositional Optimization

arXiv

引用

arXiv 2022年

作者： Jiang, Wei Li, Gang Wang, Yibo Zhang, Lijun Yang, Tianbao National Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Computer Science the University of Iowa Iowa City United States Department of Computer Science and Engineering Texas A&M University College Station United States

Variance reduction techniques such as SPIDER/SARAH/STORM have been extensively studied to improve the convergence rates of stochastic non-convex optimization, which usually maintain and update a sequence of estimators for a single function across iterations. What if we need to track multiple functional mappings across iterations but only with access to stochastic samples of O(1) functional mappings at each iteration? There is an important application in solving an emerging family of coupled compositional optimization problems in the form of Pmi=1 fi(gi(w)), where gi is accessible through a stochastic oracle. The key issue is to track and estimate a sequence of g(w) = (g1(w), . . ., gm(w)) across iterations, where g(w) has m blocks and it is only allowed to probe O(1) blocks to attain their stochastic values and Jacobians. To improve the complexity for solving these problems, we propose a novel stochastic method named Multi-block-Single-probe Variance Reduced (MSVR) estimator to track the sequence of g(w). It is inspired by STORM but introduces a customized error correction term to alleviate the noise not only in stochastic samples for the selected blocks but also in those blocks that are not sampled. With the help of the MSVR estimator, we develop several algorithms for solving the aforementioned compositional problems with improved complexities across a spectrum of settings with non-convex/convex/strongly convex/Polyak-Lojasiewicz (PL) objectives. Our results improve upon prior ones in several aspects, including the order of sample complexities and dependence on the strong convexity parameter. Empirical studies on multi-task deep AUC maximization demonstrate the better performance of using the new estimator. Copyright © 2022, The Authors. All rights reserved.

关键词： Error correction

来源：评论

学校读者我要写书评

暂无评论

CI-Based Block-Level Precoding for ISAC System

CI-Based Block-Level Precoding for ISAC System

引用

International Conference on Wireless Communications and Signal Processing (WCSP)

作者： Yiran Wang Xiaoyan Hu Ang Li Kai-Kit Wong Kun Yang School of Information and Communications Engineering Xi'an Jiaotong University Xi'an China Department of Electronic and Electrical Engineering University College London London UK School of Intelligent Software and Engineering Nanjing University (Suzhou Campus) Suzhou China State Key Laboratory of Novel Software Technology Nanjing University Nanjing China

ISBN: (数字)9798350390643

ISBN: (纸本)9798350390650

In this paper, we propose a constructive interference (CI)-based precoding scheme and extend the proposed precoding scheme from the symbol level to the block level for multiple-input multiple-output (MIMO) integrated sensing and communication (ISAC) systems. The illumination power of radar is maximized under communication CI constraint. Since the optimization objective function is not convex, we use succesive convex ap-proximation (SCA) method to solve the proposed optimization problem. Furthermore, we formulate the dual problem of the convex subproblem in SCA method. It is a simple quadratic programming (QP) problem and can be efficiently solved. The simulation results show that the proposed CI-based precoding design has significant advantages in enhancing the ISAC performance with acceptable computational complexity.

关键词： Wireless communication Precoding Simulation Lighting Symbols Radar Interference Integrated sensing and communication Radar signal processing Optimization

来源：评论

学校读者我要写书评

暂无评论

Plasma proteomics identifies proteins and pathways associated with incident depression in 46,165 adults

引用

science Bulletin 2025年第4期70卷 573-586页

作者： Jujiao Kang Liu Yang Tianye Jia Wei Zhang Lin-Bo Wang Yu-Jie Zhao Jia You Yue-Ting Deng Yi-Jun Ge Wei-Shi Liu Yi Zhang Yi-Lin Chen Xiao-Yu He Barbara J.Sahakian Yucheng TYang Xing-Ming Zhao Jin-Tai Yu Jianfeng Feng Wei Cheng Institute of Science and Technology for Brain-Inspired Intelligence(ISTBI) Fudan UniversityShanghai 200433China Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence Fudan UniversityMinistry of EducationShanghai 200433China Department of Neurology and National Center for Neurological Disorders Huashan HospitalState Key Laboratory of Medical Neurobiology and MOE Frontiers Center for Brain ScienceShanghai Medical CollegeFudan UniversityShanghai 200433China Department of Psychiatry University of CambridgeCambridge CB20SZUK Department of Computer Science University of WarwickCoventry CV47ALUK School of Data Science Fudan UniversityShanghai 200438China

Proteomic alterations preceding the onset of depression offer valuable insights into its development and potential *** data from 46,165 UK Biobank participants and 2920 plasma proteins profiled at baseline,we conducted a longitudinal analysis with a median follow-up of 14.5 years to explore the relationship between plasma proteins and incident *** regression was then used to assess associations between depression-related proteins and brain structures,genetic factors,and stress-related *** analysis identified 157 proteins associated with incident depression(P<1.71×10^(-5)),including novel associations with proteins such as GAST,PLAUR,LRRN1,BCAN,and ***,higher expression levels of GDF15(P=6.18×10-26)and PLAUR(P=2.88×10^(-14))were linked to an increased risk of depression,whereas higher levels of LRRN1(P=4.28×10^(-11))and ITGA11(P=3.68×10^(-9))were associated with a decreased *** of the 157 proteins is correlated with brain regions implicated in depression,including the hippocampus and middle temporal ***,these protein alterations were strongly correlated with stress-related events,including self-harm events,adult,and childhood *** pathway enrichment analysis highlighted the critical roles of the immune *** and TNF emerged as key proteins in the protein-protein interaction ***3A2,newly linked to incident depression(P=4.35×10^(-10)),was confirmed as a causal factor through Mendelian randomization *** summary,our research identified the proteomic signatures associated with the onset of depression,highlighting its potential for early intervention and tailored therapeutic avenues.

关键词： Plasma proteins Depression Brain structure

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：