检索结果-内蒙古大学图书馆

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Ran Qiu Hu Liang Yuchen Liu Shengrong Zhao Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

Image inpainting, which aims to reconstruct reasonably clear and realistic images from known pixel information, is one of the core problems in computer vision. However, due to the complexity and variability of the underwater environment, the inability to extract valid pixel points and insufficient correlation between feature information in existing image inpainting techniques lead to blurring in the generated images. Therefore, a novel gated attention feature fusion image inpainting network based on generative adversarial networks (GAF-GAN) is proposed. The accuracy of feature similarity matching depends heavily on the validity of the information contained in the features. On the one hand, gating values are dynamically generated by gated convolution to reduce the interference of invalid information. On the other hand, semantic information at distant locations in an image is accurately acquired by the attention mechanism. For these reasons, we designed an improved gated attention mechanism. Gated attention mechanism make the network focus on effective information such as high-frequency texture and color fidelity of restored images. In addition, the dense feature fusion module is added to expand the overall receptive field of the network to fully learn the image features. Experimental results show that the proposed method can effectively repair defective images with complex texture structures and improve the reality and integrity of image details and structures.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reference Matters: Benchmarking Factual Error Correction for Dialogue Summarization with Fine-grained Evaluation Framework

arXiv

引用

arXiv 2023年

作者： Gao, Mingqi Wan, Xiaojun Su, Jia Wang, Zhefeng Huai, Baoxing Wangxuan Institute of Computer Technology Peking University China Center for Data Science Peking University China The MOE Key Laboratory of Computational Linguistics Peking University China Huawei Cloud China

Factuality is important to dialogue summarization. Factual error correction (FEC) of model-generated summaries is one way to improve factuality. Current FEC evaluation that relies on factuality metrics is not reliable and detailed enough. To address this problem, we are the first to manually annotate a FEC dataset for dialogue summarization containing 4000 items and propose FERRANTI, a fine-grained evaluation framework based on reference correction that automatically evaluates the performance of FEC models on different error categories. Using this evaluation framework, we conduct sufficient experiments with FEC approaches under a variety of settings and find the best training modes and significant differences in the performance of the existing approaches on different factual error categories. Copyright © 2023, 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

Robust Nitrogen-Rich Covalent Polymeric Networks for Ultra-Efficient and Selective Palladium Capture Under Harsh Conditions

SSRN

引用

SSRN 2023年

作者： Yang, Yuxiang Wang, Ying Zhang, Zeqian Jiang, Yongjie Li, Qing Yang, Pinghua Li, Jin Cai, Yimin Yuan, Lihua Feng, Wen Key Laboratory of Radiation Physics and Technology The Ministry of Education Institute of Nuclear Science and Technology College of Chemistry Sichuan University Chengdu610064 China School of Chemistry Southwest Jiaotong University Chengdu610031 China Biotechnology and Nuclear Technology Research Institute Sichuan Academy of Agricultural Sciences Chengdu610061 China

Selective capture of palladium (Pd) from high-level liquid waste (HLLW) is one of the frontier issues in materials science in order to alleviate the Pd resource scarcity and guarantee the safe disposal of radioactive wastes. However, this task remains a great challenge in HLLW treatment associated with low capacity, poor selectivity, and limited stability of materials in strongly acidic and radioactive environments. Here we conquer this challenge by designing covalent polymeric networks (CPNs) equipped with abundant bidentate (CPN-1) or tridentate (CPN-2) nitrogen-rich moieties as specific nano-traps for Pd(II). These CPNs are constructed through efficient and facile click reactions, among which CPN-1 bearing plentiful pyridinyl-triazolyl moieties sets a new record for Pd(II) uptake capacity (535 mg g-1), notably surpassing all the reported materials for Pd(II) separation from HNO3 solutions to date. Moreover, CPN-1 features additional attractive merits including good reusability, feasible dynamic column separation, outstanding Pd(II) selectivity over 17 coexisting cations, and excellent stability under highly acidic and radioactive conditions, making it highly promising for practical applications. This work provides a facile way to customize CPN adsorbents with superior performance and highlights the great potential of the prepared materials for metal capture applications. © 2023, The Authors. All rights reserved.

关键词： Nitrogen

来源：评论

学校读者我要写书评

暂无评论

Characterizing the set of quantum correlations in prepare-and-measure quantum chain-shaped networks

arXiv

引用

arXiv 2024年

作者： Jia, Yanning Guo, Fenzhuo Wang, YuKun Dong, Haifeng Gao, Fei School of Science Beijing University of Posts and Telecommunications Beijing100876 China Key Laboratory of Mathematics and Information Networks Beijing University of Posts and Telecommunications Ministry of Education China State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China Beijing Key Laboratory of Petroleum Data Mining China University of Petroleum-Beijing Beijing102249 China School of Instrumentation Science and Opto-Electronics Engineering Beihang University Beijing100191 China

We introduce a hierarchy of tests satisfied by any probability distribution P that represents the quantum correlations generated in prepare-and-measure (P&M) quantum multi-chain-shaped networks, assuming only the inner-product information of prepared states. The P&M quantum multi-chain-shaped networks involve multiple measurement parties, with each measurement party potentially having multiple sequential receivers. We adapt the original NPA-hierarchy by incorporating a finite number of linear and positive semi-definite constraints to characterize the quantum correlations in P&M quantum multi-chain-shaped networks. These constraints in each hierarchy are derived from sequential measurements and the inner-product matrix of prepared states. The adapted NPA-hierarchy is further applied to tackle some quantum information tasks, including sequential quantum random access codes (QRACs) and semi-device-independent randomness certification. First, we derive the optimal trade-off between the two sequential receivers in the 2 → 1 sequential QRACs, and investigate randomness certification in its double violation region. Second, considering the presence of an eavesdropper in actual communication, we show how much local and global randomness can be certified using the optimal trade-off of 2 → 1 sequential QRACs. We also quantify the amount of local and global randomness that can be certified from the complete set of probabilities generated by the two sequential receivers. Our conclusion is that utilizing the full set of probabilities certifies more randomness than relying solely on the optimal trade-off relationship. Copyright © 2024, The Authors. All rights reserved.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

CoGAP: A Personalized Federated Learning Method Using Collaborative Optimization for Medical Image Classification

CoGAP: A Personalized Federated Learning Method Using Collab...

引用

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

作者： Shenhai Zheng Congyu Li Sian Wen Xi Gao Lei Yu College of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing China Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing China Emergency Department The Second Affiliated Hospital of Chongqing Medical University Chongqing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Federated learning (FL) has been widely used in medical image processing to protect data privacy, but it has issues with data heterogeneity. Personalized federated learning have emerged to tackle these issues but often focuses too much on personalized models at the expense of global models. To address these problem, we propose a personalized federated learning method CoGAP, using collaborative optimization to enhance both personalized and global model performance. On the client side, it employs adaptive weight aggregation to initialize personalized models and uses a training strategy based on L 2 regularization. On the server side, it implements a gradient accumulation-based aggregation method. These modules facilitate a collaborative optimization process where the global model guides the personalized models, and the personalized models provide positive feedback to the global model, ultimately leading to mutual improvement for both. We conducted extensive comparative experiments on the OCT2017 dataset, as well as the BloodMnist and PathMnist (subsets from MedMnist), to evaluate both global and personalized models. Results show that CoGAP own a unique strength which not only outperforms other personalized federated learning methods in personalization capability while also remarkably achieving satisfying global generalization. Code is available at https://***/lcyCQUPT/CoGAP.

关键词： Training Adaptation models Federated learning Collaboration Signal processing Servers Speech processing Optimization Image classification Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Scribble-supervised semantic segmentation with prototype-based feature augmentation 24

Scribble-supervised semantic segmentation with prototype-bas...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Guiyang Chan Pengcheng Zhang Hai Dong Shunhui Ji Bainian Chen Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China and College of Computer Science and Software Engineering Hohai University Nanjing China School of Computing Technologies RMIT University Melbourne Australia

Scribble-supervised semantic segmentation presents a cost-effective training method that utilizes annotations generated through scribbling. It is valued in attaining high performance while minimizing annotation costs, which has made it highly regarded among researchers. Scribble supervision propagates information from labeled pixels to the surrounding unlabeled pixels, enabling semantic segmentation for the entire image. However, existing methods often ignore the features of classified pixels during feature propagation. To address these limitations, this paper proposes a prototype-based feature augmentation method that leverages feature prototypes to augment scribble supervision. Experimental results demonstrate that our approach achieves state-of-the-art performance on the PASCAL VOC 2012 dataset in scribble-supervised semantic segmentation tasks. The code is available at https://***/TranquilChan/PFA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Style Transformer for Image Inversion and Editing

arXiv

引用

arXiv 2022年

作者： Hu, Xueqi Huang, Qiusheng Shi, Zhengyi Li, Siyuan Gao, Changxin Sun, Li Li, Qingli Shanghai Key Laboratory of Multidimensional Information Processing China Key Laboratory of Advanced Theory and Application in Statistics and Data Science East China Normal University Shanghai China Huazhong University of Science and Technology Wuhan China

Existing GAN inversion methods fail to provide latent codes for reliable reconstruction and flexible editing simultaneously. This paper presents a transformer-based image inversion and editing model for pretrained StyleGAN which is not only with less distortions, but also of high quality and flexibility for editing. The proposed model employs a CNN encoder to provide multi-scale image features as keys and values. Meanwhile it regards the style code to be determined for different layers of the generator as queries. It first initializes query tokens as learnable parameters and maps them into W+ space. Then the multi-stage alternate selfand cross-attention are utilized, updating queries with the purpose of inverting the input by the generator. Moreover, based on the inverted code, we investigate the referenceand label-based attribute editing through a pretrained latent classifier, and achieve flexible image-to-image translation with high quality results. Extensive experiments are carried out, showing better performances on both inversion and editing tasks within StyleGAN. Codes are available at https://***/sapphire497/style-transformer. Copyright © 2022, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

UniCell:Universal Cell Nucleus Classification via Prompt Learning

arXiv

引用

arXiv 2024年

作者： Huang, Junjia Li, Haofeng Wan, Xiang Li, Guanbin School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen China GuangDong Province Key Laboratory of Information Security Technology China

The recognition of multi-class cell nuclei can significantly facilitate the process of histopathological diagnosis. Numerous pathological datasets are currently available, but their annotations are inconsistent. Most existing methods require individual training on each dataset to deduce the relevant labels and lack the use of common knowledge across datasets, consequently restricting the quality of recognition. In this paper, we propose a universal cell nucleus classification framework (UniCell), which employs a novel prompt learning mechanism to uniformly predict the corresponding categories of pathological images from different dataset domains. In particular, our framework adopts an end-to-end architecture for nuclei detection and classification, and utilizes flexible prediction heads for adapting various datasets. Moreover, we develop a Dynamic Prompt Module (DPM) that exploits the properties of multiple datasets to enhance features. The DPM first integrates the embeddings of datasets and semantic categories, and then employs the integrated prompts to refine image representations, efficiently harvesting the shared knowledge among the related cell types and data sources. Experimental results demonstrate that the proposed method effectively achieves the state-of-the-art results on four nucleus detection and classification benchmarks. Code and models are available at https://***/lhaof/UniCell Copyright © 2024, The Authors. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Stability and Generalization of p-Regularized Stochastic Learning for GCN

arXiv

引用

arXiv 2023年

作者： Liu, Shiyu Wei, Linsen Lv, Shaogao Li, Ming University of Electronic Science and Technology of China China School of Astronautics Northwestern Polytechnical University China Department of Statistics and Data Science Nanjing Audit University China Key Laboratory of Intelligent Education Technology Application of Zhejiang Province Zhejiang Normal University China

Graph convolutional networks (GCN) are viewed as one of the most popular representations among the variants of graph neural networks over graph data and have shown powerful performance in empirical experiments. That 2-based graph smoothing enforces the global smoothness of GCN, while (soft) 1-based sparse graph learning tends to promote signal sparsity to trade for discontinuity. This paper aims to quantify the trade-off of GCN between smoothness and sparsity, with the help of a general p-regularized (1 p-regularized learning scheme does not satisfy such a smooth condition. To tackle this issue, we propose a novel SGD proximal algorithm for GCNs with an inexact operator. For a single-layer GCN, we establish an explicit theoretical understanding of GCN with the p-regularized stochastic learning by analyzing the stability of our SGD proximal algorithm. We conduct multiple empirical experiments to validate our theoretical findings. © 2023, CC BY-NC-SA.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Tiny noise, big mistakes: adversarial perturbations induce errors in brain–computer interface spellers

引用

National science Review 2021年第4期8卷 78-90页

作者： Xiao Zhang Dongrui Wu Lieyun Ding Hanbin Luo Chin-Teng Lin Tzyy-Ping Jung Ricardo Chavarriaga Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and AutomationHuazhong University of Science and Technology School of Civil Engineering and Mechanics Huazhong University of Science and Technology Centre of Artificial Intelligence Faculty of Engineering and Information Technology University of Technology Sydney Swartz Center for Computational Neuroscience Institute for Neural ComputationUniversity of California San Diego Center for Advanced Neurological Engineering Institute of Engineering in Medicine University of California San Diego ZHAW Data Lab Zürich University of Applied Sciences

An electroencephalogram(EEG)-based brain–computer interface(BCI) speller allows a user to input text to a computer by thought. It is particularly useful to severely disabled individuals, e.g. amyotrophic lateral sclerosis patients, who have no other effective means of communication with another person or a *** studies so far focused on making EEG-based BCI spellers faster and more reliable; however, few have considered their security. This study, for the first time, shows that P300 and steady-state visual evoked potential BCI spellers are very vulnerable, i.e. they can be severely attacked by adversarial perturbations,which are too tiny to be noticed when added to EEG signals, but can mislead the spellers to spell anything the attacker wants. The consequence could range from merely user frustration to severe misdiagnosis in clinical applications. We hope our research can attract more attention to the security of EEG-based BCI spellers, and more broadly, EEG-based BCIs, which has received little attention before.

关键词： electroencephalogram brain-computer interfaces BCI spellers adversarial examples

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：