检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Wu, Tian-Shuang Lyu, Shen-Huan Chen, Ning Qu, Zhihao Ye, Baoliu Key Laboratory of Water Big Data Technology Ministry of Water Resources College of Computer Science and Software Engineering Hohai University Nanjing China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China

In recent years, as a compromise between privacy and performance, few-sample model compression has been widely adopted to deal with limited data resulting from privacy and security concerns. However, when the number of available samples is extremely limited, class imbalance becomes a common and tricky problem. Achieving an equal number of samples across all classes is often costly and impractical in real-world applications, and previous studies on few-sample model compression have mostly ignored this significant issue. Our experiments comprehensively demonstrate that class imbalance negatively affects the overall performance of few-sample model compression methods. To address this problem, we propose a novel and adaptive framework named OOD-Enhanced Few-Sample Model Compression (OE-FSMC). This framework integrates easily accessible out-of-distribution (OOD) data into both the compression and fine-tuning processes, effectively rebalancing the training distribution. We also incorporate a joint distillation loss and a regularization term to reduce the risk of the model overfitting to the OOD data. Extensive experiments on multiple benchmark datasets show that our framework can be seamlessly incorporated into existing few-sample model compression methods, effectively mitigating the accuracy degradation caused by class imbalance. Copyright © 2025, The Authors. All rights reserved.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Stitching, Fine-tuning, Re-training: A SAM-enabled Framework for Semi-supervised 3D Medical Image Segmentation

引用

IEEE Transactions on Medical Imaging 2025年 PP卷 PP页

作者： Li, Shumeng Qi, Lei Yu, Qian Huo, Jing Shi, Yinghuan Gao, Yang Nanjing University State Key Laboratory for Novel Software Technology China Nanjing University National Institute of Healthcare Data Science China School of Computer Science and Engineering China Shandong Women's University School of Data and Computer Science China

Segment Anything Model (SAM) fine-tuning has shown remarkable performance in medical image segmentation in a fully supervised manner, but requires precise annotations. To reduce the annotation cost and maintain satisfactory performance, in this work, we leverage the capabilities of SAM for establishing semi-supervised medical image segmentation models. Rethinking the requirements of effectiveness, efficiency, and compatibility, we propose a three-stage framework, i.e., Stitching, Fine-tuning, and Re-training (SFR). The current fine-tuning approaches mostly involve 2D slice-wise fine-tuning that disregards the contextual information between adjacent slices. Our stitching strategy mitigates the mismatch between natural and 3D medical images. The stitched images are then used for fine-tuning SAM, providing robust initialization of pseudo-labels. Afterwards, we train a 3D semi-supervised segmentation model while maintaining the same parameter size as the conventional segmenter such as V-Net. Our SFR framework is plug-and-play, and easily compatible with various popular semi-supervised methods. We also develop an extended framework SFR+ with selective fine-tuning and re-training through confidence estimation. Extensive experiments validate that our SFR and SFR+ achieve significant improvements in both moderate annotation and scarce annotation across five datasets. In particular, SFR framework improves the Dice score of Mean Teacher from 29.68% to 74.40% with only one labeled data of LA dataset. The code is available at https://***/ShumengLI/SFR. © 1982-2012 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

On Optimizing Inter-and Intra-Chiplet Interconnection Topologies for Robust Multi-Chiplet Systems

引用

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 2025年

作者： Wang, Xiaohang Xu, Miao Singh, Amit Kumar Jiang, Yingtao Yang, Mei Zhejiang University State Key Laboratory of Blockchain and Data Security China Hangzhou China South China University of Technology School of Software Engineering China University of Essex School of Computer Science and Electronic Engineering United Kingdom University of Nevada Department of Electrical and Computer Engineering Las Vegas United States

Inter-and intra-chiplet interconnection networks play a vital role in the operation of many core systems made of multiple chiplets. However, these networks are susceptible to faults caused by manufacturing defects and attacks resulting from the malicious insertion of hardware Trojans and backdoors. Unlike conventional fault-tolerant or countermeasure methods, this paper focuses on optimizing network robustness to withstand both faults and attacks, while considering the constraints of chiplet area and power budget. To achieve this, this paper first defines network robustness as a quantifiable measure based on various network parameters, after which an optimization problem is formulated to optimize the robustness of the network topology. To efficiently solve this problem, a reinforcement learning algorithm is proposed. Experimental results demonstrate that the proposed method is capable of generating inter-and intra-chiplet interconnection networks that are significantly more robust than existing topology generation methods. Specifically, the proposed method improves robustness over ButterDonut and Kite, respectively by an average of 10.88% and 14.06% under random faults and by 9.37% and 7.81% under targeted attacks. These experimental results confirm that the proposed method is capable of generating robust inter-and intra-chiplet interconnection networks that can withstand both faults and attacks. By optimizing the network topology’s robustness, it provides a valuable contribution to the design and security of chiplet-based core systems. © 2025 IEEE. All rights reserved

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Location Privacy Preservation Crowdsensing With Federated Reinforcement Learning

引用

IEEE Transactions on Dependable and Secure Computing 2025年第3期22卷 1877-1894页

作者： You, Zhichao Dong, Xuewen Liu, Ximeng Gao, Sheng Wang, Yongzhi Shen, Yulong Xidian University School of Computer Science and Technology The Engineering Research Center of Blockchain Technology Application and Evaluation Ministry of Education Xi'an710071 China Shaanxi Key Laboratory of Blockchain and Secure Computing Xi'an710071 China Fuzhou University College of Computer and Data Science Fuzhou350025 China Central University of Finance and Economics School of Information Beijing102206 China California State Polytechnic University Pomona Department of Computer Information Systems PomonaCA91768 United States Xidian University School of Computer Science and Technology Xi'an710071 China Shaanxi Key Laboratory of Network and System Security Xi'an710071 China

Crowdsensing has become a popular method of sensing data collection while facing the problem of protecting participants' location privacy. Existing location-privacy crowdsensing mechanisms focus on static tasks and participants without considering sensing tasks' time requirements and participants' mobility, which cannot achieve satisfactory collected data quality and task completion in crowdsensing with dynamic tasks and participants. Inspired by this, we proposed a location-preservation crowdsensing mechanism, FedSense, considering dynamic tasks and participants based on federated learning (FL) and reinforcement learning (RL). In FedSense, through RL's outstanding decision-making ability, participants select sensing tasks to perform by well-trained RL models without uploading location information to servers for task allocation. We propose an independent tasks selection environment that defines actions, states, and rewards of RL to enable FedSense to achieve satisfactory task completion and data quality while preserving location privacy. Besides, FedSense applies an asynchronous FL aggregation algorithm that reduces participants' network stabilization and device computing ability requirements. Analysis proves that participants' location information does not leave the local device during the model training and task selection process, effectively avoiding privacy leakage. Simulation shows that compared with existing location-preservation crowdsensing mechanisms, FedSense achieves the highest task completion and sensing accuracy for dynamic tasks and participants. © 2024 IEEE.

关键词： data privacy

来源：评论

学校读者我要写书评

暂无评论

GKG-LLM: A Unified Framework for Generalized knowledge Graph Construction

arXiv

引用

arXiv 2025年

作者： Zhang, Jian Wei, Bifan Qi, Shihao Zhu, Haiping Liu, Jun Lin, Qika School of Computer Science and Technology Xi’an Jiaotong University Xi’an China School of Continuing Education Xi’an Jiaotong University Xi’an China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University Xi’an China National University of Singapore Singapore

The construction of Generalized knowledge Graph (GKG), including knowledge graph, event knowledge graph and commonsense knowledge graph, is fundamental for various natural language processing tasks. Current studies typically construct these types of graph separately, overlooking holistic insights and potential unification that could be beneficial in computing resources and usage perspectives. However, a key challenge in developing a unified framework for GKG is obstacles arising from task-specific differences. In this study, we propose a unified framework for constructing generalized knowledge graphs to address this challenge. First, we collect data from 15 sub-tasks in 29 datasets across the three types of graphs, categorizing them into in-sample, counter-task, and out-of-distribution (OOD) data. Then, we propose a three-stage curriculum learning fine-tuning framework, by iteratively injecting knowledge from the three types of graphs into the Large Language Models. Extensive experiments show that our proposed model improves the construction of all three graph types across in-domain, OOD and counter-task data. Copyright © 2025, The Authors. All rights reserved.

关键词： knowledge graph

来源：评论

学校读者我要写书评

暂无评论

DeepSeek: Paradigm Shifts and Technical Evolution in Large AI Models

引用

IEEE/CAA Journal of Automatica Sinica 2025年第5期12卷 841-858页

作者： Xiong, Luolin Wang, Haofen Chen, Xi Sheng, Lu Xiong, Yun Liu, Jingping Xiao, Yanghua Chen, Huajun Han, Qing-Long Tang, Yang Ministry of Education Engineering Research Center of Process System Engineering East China University of Science and Technology Key Laboratory of Smart Manufacturing in Energy Chemical Process Shanghai 200237 China College of Design and Innovation Tongji University Shanghai 200092 China School of Computer Science Fudan University Shanghai Key Laboratory of Data Science Shanghai 200433 China School of Software Beihang University Beijing 100191 China School of Information Science and Engineering East China University of Science and Technology Shanghai 200237 China College of Computer Science and Technology Zhejiang University AZFT Joint Laboratory for Knowledge Engine Hangzhou Innovation Center Hangzhou 310058 China School of Science Computing and Engineering Technologies Swinburne University of Technology Melbourne 3122 VIC Australia

DeepSeek, a Chinese artificial intelligence (AI) startup, has released their V3 and R1 series models, which attracted global attention due to their low cost, high performance, and open-source advantages. This paper begins by reviewing the evolution of large AI models focusing on paradigm shifts, the mainstream large language model (LLM) paradigm, and the DeepSeek paradigm. Subsequently, the paper highlights novel algorithms introduced by DeepSeek, including multi-head latent attention (MLA), mixture-of-experts (MoE), multi-token prediction (MTP), and group relative policy optimization (GRPO). The paper then explores DeepSeek's engineering breakthroughs in LLM scaling, training, inference, and system-level optimization architecture. Moreover, the impact of DeepSeek models on the competitive AI landscape is analyzed, comparing them to mainstream LLMs across various fields. Finally, the paper reflects on the insights gained from DeepSeek's innovations and discusses future trends in the technical and engineering development of large AI models, particularly in data, training, and reasoning. © 2014 Chinese Association of Automation.

关键词： DeepSeek large AI models reasoning capability reinforcement learning test-time scaling

来源：评论

学校读者我要写书评

暂无评论

Rethinking Polyp Segmentation from the Perspectives of Matching Views and Seeking Camouflage

引用

Multimedia Systems 2025年第3期31卷 1-17页

作者： Jiang, Zhengfang Chen, Haipeng Yang, Yongping Liu, Xianzhu Lyu, Yingda College of Software Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China College of Computer Science and Technology Jilin University Changchun130012 China Department of Colorectal Anal Surgery The Second Hospital of Jilin University Changchun130022 China National and Local Joint Engineering Research Center of Space Optoelectronics Technology Changchun University of Science and Technology Changchun130022 China College of Opto-Electronic Engineering Changchun University of Science and Technology Changchun130022 China Public Computer Education and Research Center Jilin University Changchun130012 China

Accurate segmentation of polyps from colonoscopy images is of great significance for the prevention of colorectal cancer. Despite notable progress, polyp segmentation remains a challenging task due to the diversity of polyp size and shape, as well as the camouflage property of polyps caused by their high similarity to surrounding tissues. To address these challenges, inspired by human perceptual experience in finding objects, we propose a multi-perspective collaborative network (MPCNet), innovatively identifying the potential polyps from the perspectives of matching views and seeking camouflage. Firstly, from the former perspective, a global–local aware module is proposed to provide various feature receptive fields to match suitable views for polyps of different sizes and shapes. Then, from the latter perspective, a texture enhancement module (TEM) and an interaction refinement module (IRM) are proposed to mine and complement clues essential for breaking the camouflage. Specifically, TEM mines texture-related clues and amplifies the subtle texture differences between polyps and their background, while IRM complements boundary clues and further optimizes feature representation through the interaction between boundaries and regions, thereby generating accurate segmentation results with complete regions and fine boundaries. Extensive experiments on five benchmark polyp datasets show that our MPCNet outperforms other state-of-the-art methods. In particular, we achieve a mean Dice of 81.7% and 82.4% on the most challenging datasets CVC-ColonDB and ETIS, respectively, which are significantly higher than competing methods. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

VIPNet: Combining Viewpoint Information and Shape Priors for Instant Multi-view 3D Reconstruction 17th

VIPNet: Combining Viewpoint Information and Shape Priors fo...

引用

17th Asian Conference on Computer Vision, ACCV 2024

作者： Ye, Weining Li, Zhixuan Jiang, Tingting School of Computer Science Peking University Beijing100871 China College of Computing and Data Science Nanyang Technological University Singapore Singapore National Engineering Research Center of Visual Technology National Key Laboratory for Multimedia Information Processing School of Computer Science National Biomedical Imaging Center Peking University Beijing100871 China

ISBN: (纸本)9789819609680

While the multi-view 3D reconstruction task has made significant progress, existing methods simply fuse multi-view image features without effectively leveraging available auxiliary information, especially the viewpoint information for guiding and associating features of different views. To this end, we propose to enhance multi-view 3D reconstruction with the power of viewpoint information. Specifically, a simple-yet-effective viewpoint estimator is designed to learn and provide comprehensive viewpoint knowledge for locating and associating learned features from different views. Moreover, to improve the 3D reconstruction quality when 2D images of only very few viewpoints are available, we propose to learn the shape prior knowledge to provide sufficient shape information for compensating the limited 2D observations. Overall, we present VIPNet, benefiting from Viewpoint Information and Shape Prior learning for high-quality multi-view 3D reconstruction. Extensive experiments validate the effectiveness of the proposed VIPNet, which achieves state-of-the-art performance on challenging datasets and shows well generalization ability in real-world scenarios. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

ARMOR: Shielding Unlearnable Examples against data Augmentation

arXiv

引用

arXiv 2025年

作者： Gong, Xueluan Wang, Yuji Chen, Yanjiao Dong, Haocheng Li, Yiming Sun, Mengyuan Li, Shuaike Wang, Qian Chen, Chen Nanyang Technological University Singapore College of Electrical Engineering Zhejiang University China School of Cyber Science and Engineering Wuhan University China China State Key Laboratory of Blockchain and Data Security Zhejiang University China

Private data, when published online, may be collected by unauthorized parties to train deep neural networks (DNNs). To protect privacy, defensive noises can be added to original samples to degrade their learnability by DNNs. Recently, unlearnable examples [19] are proposed to minimize the training loss such that the model learns almost nothing. However, raw data are often pre-processed before being used for training, which may restore the private information of protected data. In this paper, we reveal the data privacy violation induced by data augmentation, a commonly used data pre-processing technique to improve model generalization capability, which is the first of its kind as far as we are concerned. We demonstrate that data augmentation can significantly raise the accuracy of the model trained on unlearnable examples from 21.3% to 66.1%. To address this issue, we propose a defense framework, dubbed ARMOR, to protect data privacy from potential breaches of data augmentation. To overcome the difficulty of having no access to the model training process, we design a non-local module-assisted surrogate model that better captures the effect of data augmentation. In addition, we design a surrogate augmentation selection strategy that maximizes distribution alignment between augmented and non-augmented samples, to choose the optimal augmentation strategy for each class. We also use a dynamic step size adjustment algorithm to enhance the defensive noise generation process. Extensive experiments are conducted on 4 datasets and 5 data augmentation methods to verify the performance of ARMOR. Comparisons with 6 state-of-the-art defense methods have demonstrated that ARMOR can preserve the unlearnability of protected private data under data augmentation. ARMOR reduces the test accuracy of the model trained on augmented protected samples by as much as 60% more than baselines. We also show that ARMOR is robust to adversarial training. We will open-source our codes upon publicat

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Using Depth-Enhanced Spatial Transformation for Student Gaze Target Estimation in Dual-View Classroom Images

Using Depth-Enhanced Spatial Transformation for Student Gaze...

引用

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

作者： Haonan Miao Peizheng Zhao Yuqi Sun Fang Nan Xiaolong Zhang Yaqiang Wu Feng Tian School of Computer Science and Technology Xi’an Jiaotong University Xi’an China Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an China School of Advanced Technology Xi’an Jiaotong-Liverpool University Suzhou China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University Xi’an China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Dual-view gaze target estimation in classroom environments has not been thoroughly explored. Existing methods lack consideration of depth information, primarily focusing on 2D image information and neglecting the latent 3D spatial context, which could lead to suboptimal transformation and cause the gaze cone to intersect with an incorrect object. This paper introduces a novel dual-view gaze target estimation method tailored for classroom settings, leveraging depth-enhanced spatial transformations. By formulating a depth-enhanced 2D space, our method uses depth-enhanced spatial transformation to accurately project students’ gaze cones to the teacher-oriented image. Additionally, we collected a dataset named DVSGE, specifically for student gaze target estimation in dual-view classroom images. Experimental results demonstrate significant performance improvements of 9.8% in AUC and 19.9% in L2-Distance for our method, surpassing existing methods.

关键词： Three-dimensional displays Estimation Focusing Signal processing Acoustics Speech processing

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：