检索结果-内蒙古大学图书馆

DBSSL: A Scheme to Detect Backdoor Attacks in Self-Supervised Learning Models

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Huang, Yuxian Yang, Geng Yuan, Dong Yu, Shui Nanjing University of Posts and Telecommunication College of Computer Science and Software China Jiangsu Key Laboratory of Big Data Security and Intelligent Processing China University of Sydney School of Electrical and Information Engineering Australia University of Technology Sydney School of Computer Science Australia

Recently, self-supervised learning has garnered significant attention for its ability to extract high-quality features from unlabeled data. However, existing research indicates that backdoor attacks can pose significant threats to self-supervised learning. Additionally, due to the substantial training overhead, traditional backdoor detection methods in supervised learning, such as meta-learning, are not well-suited for self-supervised learning. Current backdoor detection methods for self-supervised learning can only defend against backdoor attacks triggered by patch. To address this challenge, we proposes DBSSL, a scheme that can efficiently detect backdoor attacks in self-supervised learning models. In DBSSL, we connect backdoor attacks with adversarial attacks and use adversarial perturbations for detection. Specifically, we first conduct targeted adversarial attacks on the samples, classifying them into different classes. Then, we employ the Z-Score method to analyze these adversarial perturbations. If outliers are present, we can infer that the self-supervised learning model has been backdoored. Unlike previous works, our scheme is better suited for downstream users with constrained computation resources and exhibits excellent detection capabilities for backdoor attacks caused by patch -type or global triggers. Abundant theoretical analysis has demonstrated the feasibility of our scheme. Moreover, extensive experiments show that our method performs well in detecting prevalent backdoor attacks in self-supervised learning, achieving detection accuracy exceeding 95%. © 2004-2012 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

D-FGNAE: Decentralized Federated Graph Normalized AutoEncoder 19th

D-FGNAE: Decentralized Federated Graph Normalized AutoEncode...

引用

19th CCF Conference on Computer Supported Cooperative Work and Social Computing, ChineseCSCW 2024

作者： Liang, Yuting Cai, Weixin Guo, Kun College of Computer and Data Science Fuzhou University Fuzhou350108 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou350108 China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350108 China

ISBN: (纸本)9789819623723

Graphs widely exist in real-world, and Graph Neural Networks (GNNs) have exhibited exceptional efficacy in graph learning in diverse fields. With the strengthening of data privacy protection worldwide in recent years, Federated graph neural networks (FedGNNs) have gained increasing attention in academia and industry owing to their ability to train the model in a collaborative manner while complying with the privacy protection regulations. However, in federated learning, the non-independent and identically distributed (non-IID) problem of local data possessed by multiple participants can significantly undermine model accuracy. We propose a new Decentralized Federated Graph Normalized AutoEncoder (D-FGNAE). First, the model is designed as a decentralized federated learning framework with dynamically assigned tripartite roles. This design eliminates the fixed server role found in traditional federated learning, enhances system fault tolerance, avoids single points of failure, and protects model privacy. Second, the splitting and correcting of calculation by layer in the model, along with the special design of the normalization layer, effectively tackle the non-IID problem in both the structural and attribute aspects. Experimental results on real-world networks demonstrate the effectiveness of D-FGNAE, which can achieve nearly the same accuracy as the centralized model. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

UGCM-LU: A Unified Stream and Batch Graph Computing Model with Local Update for Community Detection 19th

UGCM-LU: A Unified Stream and Batch Graph Computing Model w...

引用

19th CCF Conference on Computer Supported Cooperative Work and Social Computing, ChineseCSCW 2024

作者： Li, Hong Wu, Ling Guo, Kun College of Computer and Data Science Fuzhou University Fuzhou350108 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou350108 China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350108 China

ISBN: (纸本)9789819623723

Unified stream and batch computing (USBC) aims to incorporate stream and batch computation into a unified framework, thereby enabling the development of a one-stop solution for stream and batch data processing and enhancing the generalization of the framework. However, research on unified graph computing models (UGCMs) faces several challenges. First, existing UGCMs need to consider all graph information in the cache during the incremental update phase, thus leading to decreased execution efficiency. Second, existing UGCMs use fixed bytes to store nodes without considering the actual space occupied by nodes resulting in wasted memory when dealing with large graphs. This paper proposes a UGCM with Local Updates for community detection (UGCM-LU). We first implement a local update strategy to consider partial information of the graph to achieve incremental updates. Secondly, we also designed a byte-compression-based module to store graph data according to the space occupied by nodes. The experimental results show the effectiveness and efficiency of the model in real-world and artificial networks. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Lutetium alloys

来源：评论

学校读者我要写书评

暂无评论

An Encoder-Decoder Model Based On Spiking Neural Networks For Address Event Representation Object Recognition

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Du, Sichun Zhu, Haodi Zhang, Yang Hong, Qinghui Hunan University College of Computer Science and Electronic Engineering Changsha418002 China Shenzhen University Computer Vision Institute School of Computer Science and Software Engineering National Engineering Laboratory for Big Data System Computing Technology Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China

Address event representation (AER) object recognition task has attracted extensive attention in neuromorphic vision processing. The spike-based and event-driven computation inherent in the spiking neural network (SNN) provides an energy-saving solution for AER object recognition. However, SNN with spike timing dependent plasticity (STDP) learning rule has not achieved satisfying AER object recognition performance. This work proposes an SNN-based encoder-decoder model to improve the recognition performance of AER objects. An STDP-based locally connected spiking neural network (LC-SNN) is proposed as an encoder to extract rich spatiotemporal features from AER event flows more flexibly. After the encoder extracts and learns primary features, we propose a fully connected spiking neural network (FC-SNN) based on the reward-modulated spike-timing-dependent plasticity (R-STDP) learning rule as a decoder to learn higher-level features for classification. In addition, we improved the winner-take-all (WTA) mechanisms and R-STDP learning rule in the decoder based on the reward and punish decision, enabling the network to perform better. The experiments are performed on the N-MNIST, MNIST-DVS, and the DVS Gesture datasets, improving the accuracy of the best existing plasticity-based SNN by 0.19%, 0.27% and 1.35%, respectively. © 2016 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

LSU-NET: LIGHTWEIGHT AUTOMATIC ORGANS SEGMENTATION NETWORK FOR MEDICAL IMAGES

arXiv

引用

arXiv 2025年

作者： Ding, Yujie Teng, Shenghua Li, Zuoyong Chen, Xiao College of Electronic and Information Engineering Shandong University of Science and Technology Qingdao266590 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control School of Computer and Big Data Minjiang University Fuzhou350121 China

UNet and its variants have widespread applications in medical image segmentation. However, the substantial number of parameters and computational complexity of these models make them less suitable for use in clinical settings with limited computational resources. To address this limitation, we propose a novel Lightweight Shift U-Net (LSU-Net). We integrate the Light Conv Block and the Tokenized Shift Block in a lightweight manner, combining them with a dynamic weight multi-loss design for efficient dynamic weight allocation. The Light Conv Block effectively captures features with a low parameter count by combining standard convolutions with depthwise separable convolutions. The Tokenized Shift Block optimizes feature representation by shifting and capturing deep features through a combination of the Spatial Shift Block and depthwise separable convolutions. Dynamic adjustment of the loss weights at each layer approaches the optimal solution and enhances training stability. We validated LSU-Net on the UWMGI and MSD Colon datasets, and experimental results demonstrate that LSU-Net outperforms most state-of-the-art segmentation architectures. Copyright © 2025, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

EDSep: An Effective Diffusion-Based Method for Speech Source Separation

EDSep: An Effective Diffusion-Based Method for Speech Source...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Dong, Jinwei Wang, Xinsheng Mao, Qirong School of Computer Science and Communication Engineering Jiangsu University China Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications China Provincial Key Laboratory of Computational Intelligence and New Technologies in Low-Altitude Digital Agriculture Zhenjiang China Audio Speech and Language Processing Group School of Computer Science Northwestern Polytechnical University Xi'an China

ISBN: (纸本)9798350368741

Generative models have attracted considerable attention for speech separation tasks, and among these, diffusion-based methods are being explored. Despite the notable success of diffusion techniques in generation tasks, their adaptation to speech separation has encountered challenges, notably slow convergence and suboptimal separation outcomes. To address these issues and enhance the efficacy of diffusion-based speech separation, we introduce EDSep, a novel single-channel method grounded in score matching via stochastic differential equation (SDE). This method enhances generative modeling for speech source separation by optimizing training and sampling efficiency. Specifically, a novel denoiser function is proposed to approximate data distributions, which obtains ideal denoiser outputs. Additionally, a stochastic sampler is carefully designed to resolve the reverse SDE during the sampling process, gradually separating speech from mixtures. Extensive experiments on databases such as WSJ0-2mix, LRS2-2mix, and VoxCeleb2-2mix demonstrate our proposed method's superior performance over existing diffusion and discriminative models, validating its efficacy. © 2025 IEEE.

关键词： diffusion score matching speech separation stochastic differential equation

来源：评论

学校读者我要写书评

暂无评论

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Kaijun Deng Dezhi Zheng Jindong Xie Jinbao Wang Weicheng Xie Linlin Shen Siyang Song Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing Department of Computer Science University of Exeter

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Accurately synthesizing talking face videos and capturing fine facial features for individuals with long hair presents a significant challenge. To tackle these challenges in existing methods, we propose a decomposed per-embedding Gaussian fields (DEGSTalk), a 3D Gaussian Splatting (3DGS)-based talking face synthesis method for generating realistic talking faces with long hairs. Our DEGSTalk employs Deformable Pre-Embedding Gaussian Fields, which dynamically adjust pre-embedding Gaussian primitives using implicit expression coefficients. This enables precise capture of dynamic facial regions and subtle expressions. Additionally, we propose a Dynamic Hair-Preserving Portrait Rendering technique to enhance the realism of long hair motions in the synthesized videos. Results show that DEGSTalk achieves improved realism and synthesis quality compared to existing approaches, particularly in handling complex facial dynamics and hair preservation. Our code is available at https://***/CVI-SZU/DEGSTalk.

关键词： Hair Training Three-dimensional displays Dynamics Signal processing Rendering (computer graphics) Noise measurement Speech processing Faces Videos

来源：评论

学校读者我要写书评

暂无评论

A comprehensive survey on shadow removal from document images: datasets, methods, and opportunities

引用

Vicinagearth 2025年第1期2卷 1-18页

作者： Wang, Bingshu Li, Changping Zou, Wenbin Zhang, Yongjun Chen, Xuhang Chen, C.L. Philip School of Software Northwestern Polytechnical University Xi’an China Guangdong Provincial Key Laboratory of Intelligent Information Processing & Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering Shenzhen University Shenzhen China Yongjun Zhang is with the State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang China School of Computer Science and Engineering Huizhou University Huizhou China School of Computer Science and Engineering South China University of Technology and Pazhou Lab Guangzhou China

With the rapid development of document digitization, people have become accustomed to capturing and processing documents using electronic devices such as smartphones. However, the captured document images often suffer from issues like shadows and noise due to environmental factors, which can affect their readability. To improve the quality of captured document images, researchers have proposed a series of models or frameworks and applied them in distinct scenarios such as image enhancement, and document information extraction. In this paper, we primarily focus on shadow removal methods and open-source datasets. We concentrate on recent advancements in this area, first organizing and analyzing nine available datasets. Then, the methods are categorized into conventional methods and neural network-based methods. Conventional methods use manually designed features and include shadow map-based approaches and illumination-based approaches. Neural network-based methods automatically generate features from data and are divided into single-stage approaches and multi-stage approaches. We detail representative algorithms and briefly describe some typical techniques. Finally, we analyze and discuss experimental results, identifying the limitations of datasets and methods. Future research directions are discussed, and nine suggestions for shadow removal from document images are proposed. To our knowledge, this is the first survey of shadow removal methods and related datasets from document images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhanced Contrastive Learning with Multi-view Longitudinal data for Chest X-ray Report Generation

arXiv

引用

arXiv 2025年

作者： Liu, Kang Ma, Zhuoqi Kang, Xiaolu Li, Yunan Xie, Kun Jiao, Zhicheng Miao, Qiguang School of Computer Science and Technology Xidian University Xi’an China Xi’an Key Laboratory of Big Data and Intelligent Vision Xi’an China Key Laboratory of Collaborative Intelligence Systems Ministry of Education Xidian University Xi’an China Warren Alpert Medical School Brown University Providence United States

Automated radiology report generation offers an effective solution to alleviate radiologists’ workload. However, most existing methods focus primarily on single or fixed-view images to model current disease conditions, which limits diagnostic accuracy and overlooks disease progression. Although some approaches utilize longitudinal data to track disease progression, they still rely on single images to analyze current visits. To address these issues, we propose enhanced contrastive learning with Multi-view Longitudinal data to facilitate chest X-ray Report Generation, named MLRG. Specifically, we introduce a multi-view longitudinal contrastive learning method that integrates spatial information from current multi-view images and temporal information from longitudinal data. This method also utilizes the inherent spatiotemporal information of radiology reports to supervise the pre-training of visual and textual representations. Subsequently, we present a tokenized absence encoding technique to flexibly handle missing patient-specific prior knowledge, allowing the model to produce more accurate radiology reports based on available prior knowledge. Extensive experiments on MIMIC-CXR, MIMIC-ABN, and Two-view CXR datasets demonstrate that our MLRG outperforms recent state-of-the-art methods, achieving a 2.3% BLEU-4 improvement on MIMIC-CXR, a 5.5% F1 score improvement on MIMIC-ABN, and a 2.7% F1 RadGraph improvement on Two-view CXR. Copyright © 2025, The Authors. All rights reserved.

关键词： Radiology

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Alignment-enhanced Adaptive Grounding Network for Generalized Referring Expression Comprehension

arXiv

引用

arXiv 2025年

作者： Wang, Yaxian Ding, Henghui He, Shuting Jiang, Xudong Wei, Bifan Liu, Jun School of Computer Science and Technology Xi'an Jiaotong University China Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi'an Jiaotong University China Institute of Big Data Fudan University China Shanghai University of Finance and Economics China Nanyang Technological University Singapore School of Continuing Education Xi'an Jiaotong University China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University China

In this work, we address the challenging task of Generalized Referring Expression Comprehension (GREC). Compared to the classic Referring Expression Comprehension (REC) that focuses on single-target expressions, GREC extends the scope to a more practical setting by further encompassing notarget and multi-target expressions. Existing REC methods face challenges in handling the complex cases encountered in GREC, primarily due to their fixed output and limitations in multi-modal representations. To address these issues, we propose a Hierarchical Alignment-enhanced Adaptive Grounding Network (HieA2G) for GREC, which can flexibly deal with various types of referring expressions. First, a Hierarchical Multi-modal Semantic Alignment (HMSA) module is proposed to incorporate three levels of alignments, including word-object, phrase-object, and text-image alignment. It enables hierarchical cross-modal interactions across multiple levels to achieve comprehensive and robust multi-modal understanding, greatly enhancing grounding ability for complex cases. Then, to address the varying number of target objects in GREC, we introduce an Adaptive Grounding Counter (AGC) to dynamically determine the number of output targets. Additionally, an auxiliary contrastive loss is employed in AGC to enhance object-counting ability by pulling in multi-modal features with the same counting and pushing away those with different counting. Extensive experimental results show that HieA2G achieves new state-of-the-art performance on the challenging GREC task and also the other 4 tasks, including REC, Phrase Grounding, Referring Expression Segmentation (RES), and Generalized Referring Expression Segmentation (GRES), demonstrating the remarkable superiority and generalizability of the proposed HieA2G. Copyright © 2025, The Authors. All rights reserved.

关键词： Electric grounding

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：