检索结果-内蒙古大学图书馆

Design, Automation and Test in Europe Conference and Exhibition

作者： Hongfei Wang Chenliang Luo Deqing Zou Hai Jin Wenjie Cai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Wuhan China Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security School of Cyber Science and Engineering Wuhan China Huazhong University of Science and Technology Wuhan China Cluster and Grid Computing Lab School of Computer Science and Technology Wuhan China College of Public Administration Wuhan China

ISBN: (数字)9783981926385

ISBN: (纸本)9798350348606

Logic diagnosis is a key step in yield learning. Multiple faults diagnosis is challenging because of several reasons, including error masking, fault reinforcement, and huge search space for possible fault combinations. This work proposes a two-phase method for multiple-fault diagnosis. The first phase efficiently reduces the potential number of fault candidates through machine learning. The second phase obtains the final diagnosis results, by formulating the task as an combinational optimization problem that is later iteratively solved using binary evolution computation. Experiments shows that our method outperforms two existing methods for multiple-fault diagnosis, and achieves better diagnosability (improved by $1.87\times$ ) and resolution (improved by $1.42\times$ ) compared with a state-of-the-art commercial diagnosis tool.

关键词： Fault diagnosis Adaptation models Computational modeling Fitting Filtering algorithms Boosting Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Multi-level Feature Fusion Network for Shadow Removal Detection

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Fu, Xiwen Zhu, Guopu Zhang, Hongli Zhang, Xinpeng Ho, Anthony T. S. Kwong, Sam Harbin Institute of Technology School of Cyberspace Science Harbin150001 China Fudan University School of Computer Science Shanghai200433 China University of Surrey Faculty of Engineering and Physical Sciences Guildford SurreyGU2 7XH United Kingdom Lingnan University School of Data Science Hong Kong

By now, many works have been done on shadow removal for image manipulation. As a result, detecting shadow removal has become a critical part to reveal the traces of image manipulation. However, there are only a few works conducted on shadow removal detection, and these works cannot accurately localize the image regions where the shadows have been removed. In this paper, we present a novel model called Multi-level Feature Fusion Network (MFF-Net) for shadow removal detection. MFF-Net consists of two parts: a dual-branch feature extraction encoder and a dense prediction decoder. The encoder anchors the approximate position of the manipulated regions, while the decoder progressively fills in the details of the estimated shadow masks by integrating multi-level information. In the encoder part, a global modeling branch is constructed to capture long-range dependencies, while a local feature extraction branch is designed to extract local structural information. The features extracted by these two branches are integrated using a feature fusion module. In the decoder part, a multi-scale feature upsampling module is proposed to upsample the input features and integrate them with the low-level features obtained from the encoder part. Meanwhile, the cross attention mechanism is introduced to guide the multi-level feature fusion process. Finally, the features of different resolutions are employed to estimate the shadow masks in a coarse-to-fine manner. Extensive experiments on shadow removal detection demonstrate the superiority of MFF-Net over the state-of-the-art methods. © 1991-2012 IEEE.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

SpaceSeg: A High-Precision Intelligent Perception Segmentation Method for Multi-Spacecraft On-Orbit Targets

arXiv

引用

arXiv 2025年

作者： Liu, Hao Guo, Pengyu Yang, Siyuan Jiang, Zeqing Hu, Qinglei Li, Dongyu Hangzhou International Innovation Institute Beihang University Hangzhou311115 China School of Cyber Science and Technology Beihang University Beijing100191 China College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore Ant Group Shanghai200122 China School of Automation Science and Electrical Engineering Beihang University Beijing100191 China

With the continuous advancement of human exploration into deep space, intelligent perception and high-precision segmentation technology for on-orbit multi-spacecraft targets have become critical factors for ensuring the success of modern space missions. However, the complex deep space environment, diverse imaging conditions, and high variability in spacecraft morphology pose significant challenges to traditional segmentation methods. This paper proposes SpaceSeg, an innovative vision foundation model-based segmentation framework with four core technical innovations: First, the Multi-Scale Hierarchical Attention Refinement Decoder (MSHARD) achieves high-precision feature decoding through cross-resolution feature fusion via hierarchical attention. Second, the Multi-spacecraft Connected Component Analysis (MS-CCA) effectively resolves topological structure confusion in dense targets. Third, the Spatial Domain Adaptation Transform framework (SDAT) eliminates cross-domain disparities and resist spatial sensor perturbations through composite enhancement strategies. Finally, a custom Multi-Spacecraft Segmentation Task Loss Function is created to significantly improve segmentation robustness in deep space scenarios. To support algorithm validation, we construct the first multi-scale on-orbit multi-spacecraft semantic segmentation dataset SpaceES, which covers four types of spatial backgrounds and 17 typical spacecraft targets. In testing, SpaceSeg achieves state-of-the-art performance with 89.87% mIoU and 99.98% mAcc, surpassing existing best methods by 5.71 percentage points. The dataset and code are open-sourced at https://***/Akibaru/SpaceSeg to provide critical technical support for next-generation space situational awareness systems. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Chiral spin liquid on a Shastry-Sutherland Heisenberg antiferromagnet

引用

Physical Review B 2024年第20期109卷 205111-205111页

作者： Jian-Wei Yang Wei-Wei Luo W. Zhu L. Wang Bo Yang Pinaki Sengupta School of Microelectronics and Data Science Anhui University of Technology Maanshan 243002 China Institute of Natural Sciences Westlake Institute for Advanced Study Hangzhou 310024 China School of Science Westlake University Hangzhou 310024 China Department of Physics Zhejiang University Hangzhou 310000 China School of Physical and Mathematical Sciences Nanyang Technological University Singapore 637371

We demonstrate the existence of a topological chiral spin liquid in the frustrated Shastry-Sutherland Heisenberg model with an additional spin chirality interaction, using numerically unbiased exact diagonalization and density matrix renormalization group methods. We establish a quantum phase diagram where conventional phases, including dimer singlet, plaquette singlet, Néel, and collinear phase, can be clearly identified by suitable local order parameters. Among them, an SU(2)1 chiral spin liquid emerges in the highly frustrated region, which is unambiguously identified by two topologically degenerate ground states, a modular matrix, and characteristic level counting in an entanglement spectrum, featuring the same topological order of the ν=1/2 bosonic Laughlin state. The phase boundaries among the different orders are determined by the energy level crossing analysis and wave-function fidelity susceptibility.

关键词： Magnetic order Magnetic phase transitions Phase transitions by order Quantum phase transitions Topological phases of matter 2-dimensional systems Antiferromagnets Density matrix methods Exact solutions for many-body systems Heisenberg model Lattice models in condensed matter Many-body techniques

来源：评论

学校读者我要写书评

暂无评论

Shared adversarial unlearning: backdoor mitigation by unlearning shared adversarial examples 23

Shared adversarial unlearning: backdoor mitigation by unlear...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Shaokui Wei Mingda Zhang Hongyuan Zha Baoyuan Wu School of Data Science The Chinese University of Hong Kong Shenzhen (CUHK-Shenzhen) China School of Data Science The Chinese University of Hong Kong Shenzhen (CUHK-Shenzhen) China and Shenzhen Institute of Artificial Intelligence and Robotics for Society China

Backdoor attacks are serious security threats to machine learning models where an adversary can inject poisoned samples into the training set, causing a backdoored model which predicts poisoned samples with particular triggers to particular target classes, while behaving normally on benign samples. In this paper, we explore the task of purifying a backdoored model using a small clean dataset. By establishing the connection between backdoor risk and adversarial risk, we derive a novel upper bound for backdoor risk, which mainly captures the risk on the shared adversarial examples (SAEs) between the backdoored model and the purified model. This upper bound further suggests a novel bi-level optimization problem for mitigating backdoor using adversarial training techniques. To solve it, we propose Shared Adversarial Unlearning (SAU). Specifically, SAU first generates SAEs, and then, unlearns the generated SAEs such that they are either correctly classified by the purified model and/or differently classified by the two models, such that the backdoor effect in the backdoored model will be mitigated in the purified model. Experiments on various benchmark datasets and network architectures show that our proposed method achieves state-of-the-art performance for backdoor defense. The code is available at https://***/SCLBD/BackdoorBench (PyTorch) and https://***/shawkui/MindTrojan (MindSpore).

关键词：

来源：评论

学校读者我要写书评

暂无评论

3D printing of osteocytic Dll4 integrated with PCL for cell fate determination towards osteoblasts in vitro

引用

Bio-Design and Manufacturing 2022年第3期5卷 497-511页

作者： Pengtao Wang Xiaofang Wang Bo Wang Xian Li Zhengsong Xie Jie Chen Tasuku Honjo Xiaolin Tu Laboratory of Skeletal Development and Regeneration Institute of Life SciencesChongqing Medical UniversityChongqing 400016China Medical Data Science Academy Chongqing Medical UniversityChongqing 400016China Department of Immunology and Genomic Medicine Graduate School of MedicineKyoto UniversityYoshida Konoe-choSakyo-kuKyoto 606-8501Japan

Since 3D printed hard materials could match the shape of bone,cell survival and fate determination towards osteoblasts in such materials have become a popular research *** this study,a scaffold of hardmaterial for 3D fabrication was designed to regulate developmental signal(Notch)transduction guiding osteoblast *** established a polycaprolactone(PCL)and cell-integrated 3D printing system(PCI3D)to reciprocally print the beams of PCL and cell-laden hydrogel for a *** PCI3D module holds good cell viability of over 87%,whereas cells show about sixfold proliferation in a 7-day *** osteocytic MLO-Y4 was engineered to overexpress Notch ligand Dll4,making up 25%after mixing with 75%stromal cells in the PCI3D *** Dll4,unlike other delta-like family members such as Dll1 or Dll3,promotes osteoblast differentiation and themineralization of primary mouse and a cell line of bone marrow stromal cells when cultured in a PCI3D module for up to 28 ***,osteocytic Dll4 could not promote osteogenic differentiation of the primary bone marrow stromal cells(BMSCs)after conditional deletion of the Notch transcription factor RBPjκby Cre *** data indicate that osteocytic Dll4 activates RBPjκ-dependent canonical Notch signaling in BMSCs for their oriented differentiation towards ***,osteocytic Dll4 holds a great potential for angiogenesis in human umbilical vein endothelial cells within *** study reveals that osteocytic Dll4 could be the osteogenic niche determining cell fate towards *** will open a new avenue to overcome the current limitation of poor cell viability and low bioactivity of traditional orthopedic implants.

关键词： Integrated 3D printing PCL scaffold Cell-laden hydrogel Osteocytic Dll4 Bone marrow stromal cell Osteoblast differentiation Cell viability in hard material RBPjκ Notch signaling

来源：评论

学校读者我要写书评

暂无评论

Dual-Teacher Ensemble Models with Double-Copy-Paste for 3d Semi-Supervised Medical Image Segmentation

SSRN

引用

SSRN 2024年

作者： Fa, Zhan Li, Shumeng Zhang, Jian Qi, Lei Yu, Qian Shi, Yinghuan State Key Laboratory for Novel Software Technology Nanjing University Nanjing China National Institute of Healthcare Data Science Nanjing University Nanjing China Southeast University Nanjing China School of Data and Computer Science Shandong Women’s University Jinan China

Semi-supervised learning (SSL) techniques address the high labeling costs in 3D medical image segmentation, with the teacher-student model being a common approach. However, using an exponential moving average (EMA) in single-teacher models may cause coupling issue, where the weights of the student and teacher models become similar, limiting the teacher’s ability to provide additional knowledge for the student. Dual-teacher models were introduced to address this problem but often neglected the importance of maintaining teacher model diversity, leading to coupling issue among teachers. To address the coupling issue, we incorporate a double-copy-paste (DCP) technique to enhance the diversity among the teachers. Additionally, we introduce the Staged Selective Ensemble (SSE) module, which selects different ensemble methods based on the characteristics of the samples and enables more accurate segmentation of label boundaries, thereby improving the quality of pseudo-labels. Experimental results demonstrate the effectiveness of our proposed method in 3D medical image segmentation tasks. © 2024, The Authors. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Neural polarizer: a lightweight and effective backdoor defense via purifying poisoned features 23

Neural polarizer: a lightweight and effective backdoor defen...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Mingli Zhu Shaokui Wei Hongyuan Zha Baoyuan Wu School of Data Science The Chinese University of Hong Kong Shenzhen (CUHK-Shenzhen) China School of Data Science The Chinese University of Hong Kong Shenzhen (CUHK-Shenzhen) China and Shenzhen Institute of Artificial Intelligence and Robotics for Society China

Recent studies have demonstrated the susceptibility of deep neural networks to backdoor attacks. Given a backdoored model, its prediction of a poisoned sample with trigger will be dominated by the trigger information, though trigger information and benign information coexist. Inspired by the mechanism of the optical polarizer that a polarizer could pass light waves with particular polarizations while filtering light waves with other polarizations, we propose a novel backdoor defense method by inserting a learnable neural polarizer into the back-doored model as an intermediate layer, in order to purify the poisoned sample via filtering trigger information while maintaining benign information. The neural polarizer is instantiated as one lightweight linear transformation layer, which is learned through solving a well designed bi-level optimization problem, based on a limited clean dataset. Compared to other fine-tuning-based defense methods which often adjust all parameters of the backdoored model, the proposed method only needs to learn one additional layer, such that it is more efficient and requires less clean data. Extensive experiments demonstrate the effectiveness and efficiency of our method in removing backdoors across various neural network architectures and datasets, especially in the case of very limited clean data. Codes are available at https://***/SCLBD/BackdoorBench (PyTorch) and https://***/JulieCarlon/NPD-MindSpore (MindSpore).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neural Networks Remember More: The Power of Parameter Isolation and Combination

arXiv

引用

arXiv 2025年

作者： Zeng, Biqing Li, Zehan Ayesh, Aladdin Aberdeen Institute of Data Science and Artificial Intelligence South China Normal University China School of Artificial Intelligence South China Normal University China

Catastrophic forgetting is a pervasive issue for pre-trained language models(PLMs) during continual learning, where models lose previously acquired knowledge when sequentially trained on a series of tasks. The model’s ability to remain old tasks is referred to as stability, while its adaptability to new tasks is called plasticity. Therefore, the key to solving this problem is to find a trade-off between the plasticity and stability of the model. To address this issue, in this paper, we propose a novel method to achieve a balance between model stability and plasticity, thereby mitigating catastrophic forgetting. More specific, our proposed approach leverages parameter isolation and subsequent combination strategy. Initially, in training stage, the model adapts on each downstream task via parameter isolation method to prevent potential inference among different tasks. We then combine all trained parameters which containing acquired knowledge by the task arithmetic method and finally apply to the backbone model. Empirical evaluations on continual language learning benchmarks substantiate the effectiveness of our approach, revealing a marked enhancement over existing state-of-the-art approaches. Copyright © 2025, The Authors. All rights reserved.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Causal discovery from subsampled time series with proxy variables 23

Causal discovery from subsampled time series with proxy vari...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Mingzhou Liu Xinwei Sun Lingjing Hu Yizhou Wang School of Computer Science Peking University and Center on Frontiers of Computing Studies (CFCS) Peking University School of Data Science Fudan University Yanjing Medical College Capital Medical University School of Computer Science Peking University and Center on Frontiers of Computing Studies (CFCS) Peking University and Institute for Artificial Intelligence Peking University

Inferring causal structures from time series data is the central interest of many scientific inquiries. A major barrier to such inference is the problem of subsampling, i.e., the frequency of measurement is much lower than that of causal influence. To overcome this problem, numerous methods have been proposed, yet either was limited to the linear case or failed to achieve identifiability. In this paper, we propose a constraint-based algorithm that can identify the entire causal structure from subsampled time series, without any parametric constraint. Our observation is that the challenge of subsampling arises mainly from hidden variables at the unobserved time steps. Meanwhile, every hidden variable has an observed proxy, which is essentially itself at some observable time in the future, benefiting from the temporal structure. Based on these, we can leverage the proxies to remove the bias induced by the hidden variables and hence achieve identifiability. Following this intuition, we propose a proxy-based causal discovery algorithm. Our algorithm is nonparametric and can achieve full causal identification. Theoretical advantages are reflected in synthetic and real-world experiments. Our code is available at https://***/lmz123321/proxy_causal_discovery.

关键词：

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：