检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Zhao, Lin Chen, Changsheng Huang, Jiwu the Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security National Engineering Laboratory for Big Data System Computing Technology College of Electronics and Information Engineering Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society China

With the ongoing popularization of online services, the digital document images have been used in various applications. Meanwhile, there have emerged some deep learning-based text editing algorithms which alter the textual information of an image in an end-to-end fashion. In this work, we present a low-cost document forgery algorithm by the existing deep learning-based technologies to edit practical document images. To achieve this goal, the limitations of existing text editing algorithms towards complicated characters and complex background are addressed by a set of network design strategies. First, the unnecessary confusion in the supervision data is avoided by disentangling the textual and background information in the source images. Second, to capture the structure of some complicated components, the text skeleton is provided as auxiliary information and the continuity in texture is considered explicitly in the loss function. Third, the forgery traces induced by the text editing operation are mitigated by some post-processing operations which consider the distortions from the print-and-scan channel. Quantitative comparisons of the proposed method and the exiting approach have shown the advantages of our design by reducing the about 2/3 reconstruction error measured in MSE, improving reconstruction quality measured in PSNR and in SSIM by 4 dB and 0.21, respectively. Qualitative experiments have confirmed that the reconstruction results of the proposed method are visually better than the existing approach in both complicated characters and complex texture. More importantly, we have demonstrated the performance of the proposed document forgery algorithm under a practical scenario where an attacker is able to alter the textual information in an identity document using only one sample in the target domain. The forged-and-recaptured samples created by the proposed text editing attack and recapturing operation have successfully fooled some existing document authenticat

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Landscape dynamic network biomarker analysis reveals the tipping point of transcriptome reprogramming to prevent skin photodamage

引用

Journal of Molecular Cell Biology 2021年第11期13卷 822-833页

作者： Chengming Zhang Hong Zhang Jing Ge Tingyan Mi Xiao Cui Fengjuan Tu Xuelan Gu Tao Zeng Luonan Chen State Key Laboratory of Cell Biology Shanghai Institute of Biochemistry and Cell BiologyCenter for Excellence in Molecular Cell ScienceChinese Academy of SciencesShanghai 200031China University of the Chinese Academy of Sciences Chinese Academy of SciencesBeijing 100049China Unilever Research&Development Centre Shanghai Shanghai 200335China Bio-Med Big Data Center Shanghai Institute of Nutrition and HealthUniversity of Chinese Academy of SciencesChinese Academy of SciencesShanghai 200031China School of Life Science and Technology ShanghaiTech UniversityShanghai 201210China Key Laboratory of Systems Health Science of Zhejiang Province Hangzhou Institute for Advanced StudyUniversity of Chinese Academy of SciencesChinese Academy of SciencesHangzhou 310024China Guangdong Institute of Intelligence Science and Technology Zhuhai 519031China

Skin,as the outmost layer of human body,is frequently exposed to environmental stressors including pollutants and ultraviolet(UV),which could lead to skin ***,skin response process to ultraviolet B(UVB)irradiation is a nonlinear dynamic process,with unknown underlying molecular mechanism of critical ***,the landscape dynamic network biomarker(lDNB)analysis of time series transcriptome data on 3D skin model was conducted to reveal the complicated process of skin response to UV irradiation at both molecular and network *** advanced l-DNB analysis approach showed that:(i)there was a tipping point before critical transition state during pigmentation process,validated by 3D skin model;(ii)13 core DNB genes were identified to detect the tipping point as a network biomarker,supported by computational assessment;(iii)core DNB genes such as COL7A1 and CTNNB1 can effectively predict skin lightening,validated by independent human skin ***,this study provides new insights for skin response to repetitive UVB irradiation,including dynamic pathway pattern,biphasic response,and DNBs for skin lightening change,and enables us to further understand the skin resilience process after external stress.

关键词： single-sample network tipping point UVB irradiation living skin equivalent model time series data skin lightening

来源：评论

学校读者我要写书评

暂无评论

Quantum-Behaved Particle Swarm Optimization Algorithm Based on the Two-Body Problem

引用

Chinese Journal of Electronics 2019年第3期28卷 569-576页

作者： YAN Tao LIU Fengxian Institute of Big Data Science and Industry Shanxi University School of Computer and Information Technology Shanxi University Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education Guangzhou Institute of Electronic Technology Chinese Academy of Sciences University of Chinese Academy of Sciences

The present study proposes an improved Quantum-behaved particle swarm optimization algorithm based on the two-body problem model(QTPSO) for solving the problem that other quantum-behaved particle swarm optimization algorithms easily converge on local optimal solutions when solving complex nonlinear problems. In the proposed QTPSO algorithm, particles are categorised as core particles and edge particles. Once the position of the core particle is determined, the edge particle appears in the vicinity of the attractor exhibiting a high probability, and the attractor is obtained through the random weighted sum of the core particle and the optimal mean position. Through simulation of the motion of these two particles by applying the interaction of the particles in the two-body problem, this mechanism not only improves the diversity of the population, but also enhances the local search capacity. To validate the proposed algorithm, three groups of experimental results were obtained to compare the proposed algorithm with other swarm intelligence algorithms. The experimental results indicate the superiority of the QTPSO algorithm.

关键词： Quantum-behaved particle swarm optimization Two-body problem Quantum potential well Wave function Nonlinear optimization problems

来源：评论

学校读者我要写书评

暂无评论

Simplifying approach to node classification in graph neural networks

arXiv

引用

arXiv 2021年

作者： Maurya, Sunil Kumar Liu, Xin Murata, Tsuyoshi Department of Computer Science Tokyo Institute of Technology Tokyo Japan Artificial Intelligence Research Center AIST Tokyo Japan AIST-Tokyo Tech Real World Big-Data Computation Open Innovation Laboratory Tokyo Japan

Graph Neural Networks (GNNs) have become one of the indispensable tools to learn from graph-structured data, and their usefulness has been shown in wide variety of tasks. In recent years, there have been tremendous improvements in architecture design, resulting in better performance on various prediction tasks. In general, these neural architectures combine node feature aggregation and feature transformation using learnable weight matrix in the same layer. This makes it challenging to analyze the importance of node features aggregated from various hops and the expressiveness of the neural network layers. As different graph datasets show varying levels of homophily and heterophily in features and class label distribution, it becomes essential to understand which features are important for the prediction tasks without any prior information. In this work, we decouple the node feature aggregation step and depth of graph neural network, and empirically analyze how different aggregated features play a role in prediction performance. We show that not all features generated via aggregation steps are useful, and often using these less informative features can be detrimental to the performance of the GNN model. Through our experiments, we show that learning certain subsets of these features can lead to better performance on wide variety of datasets. Based on our observations, we introduce several key design strategies for graph neural networks. More specifically, we propose to use softmax as a regularizer and "soft-selector" of features aggregated from neighbors at different hop distances;and L2-Normalization over GNN layers. Combining these techniques, we present a simple and shallow model, Feature Selection Graph Neural Network (FSGNN), and show empirically that the proposed model achieves comparable or even higher accuracy than state-of-the-art GNN models in nine benchmark datasets for the node classification task, with remarkable improvements up to 51.1%. Source code avai

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Privileged graph distillation for cold start recommendation

arXiv

引用

arXiv 2021年

作者： Wang, Shuai Zhang, Kun Wu, Le Ma, Haiping Hong, Richang Wang, Meng Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology China School of Computer Science and Information Engineering Hefei University of Technology China Institute of Artificial Intelligence Hefei Comprehensive National Science Center China Anhui University China

The cold start problem in recommender systems is a long-standing challenge, which requires recommending to new users (items) based on attributes without any historical interaction records. In these recommendation systems, warm users (items) have privileged collaborative signals of interaction records compared to cold start users (items), and these Collaborative Filtering (CF) signals are shown to have competing performance for recommendation. Many researchers proposed to learn the correlation between collaborative signal embedding space and the attribute embedding space to improve the cold start recommendation, in which user and item categorical attributes are available in many online platforms. However, the cold start recommendation is still limited by two embedding spaces modeling and simple assumptions of space transformation. As user-item interaction behaviors and user (item) attributes naturally form a heterogeneous graph structure, in this paper, we propose a privileged graph distillation model (PGD). The teacher model is composed of a heterogeneous graph structure for warm users and items with privileged CF links. The student model is composed of an entity-attribute graph without CF links. Specifically, the teacher model can learn better embeddings of each entity by injecting complex higher-order relationships from the constructed heterogeneous graph. The student model can learn the distilled output with privileged CF embeddings from the teacher embeddings. Our proposed model is generally applicable to different cold start scenarios with new user, new item, or new user-new item. Finally, extensive experimental results on the real-world datasets clearly show the effectiveness of our proposed model on different types of cold start problems, with average 6.6%, 5.6%, and 17.1% improvement over state-of-the-art baselines on three datasets, respectively. © 2021, CC BY.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

FASTEN: Fuzzy Neural Support Vector Machine for Classification

引用

IEEE Transactions on Fuzzy Systems 2025年

作者： Yuan, Zhian Qian, Yuhua Liang, Xinyan Kou, Yi Hou, Chenping Hu, Qinghua Shanxi University Institute of Big Data Science and Industry Key laboratory of Evolutionary Science Intelligence of Shanxi Province Shanxi Taiyuan030006 China National University of Defense Technology College of Science Hunan Changsha410073 China Tianjin University College of Intelligence and Computing Tianjin Key Laboratory of Machine Learning Tianjin300350 China

Classification tasks have long been a central concern in the field of machine learning. Although deep neural network-based approaches offer a novel, versatile and highly precise solution for classification tasks, the intrinsic ambiguity and uncertainty present in the data continue to pose a significant challenge, impeding the potential for further advancements in classification accuracy. To address this issue, we propose a Fuzzy neurAl SupporT vEctor machiNe (FASTEN) which mitigates the fuzziness and uncertainty inherent in the data and enhances the classification performance. FASTEN mainly consists of two parts: the fuzzy feature extraction unit and the multi-path classifier aggregation unit. The fuzzy feature extraction unit is designed to precisely capture the fuzzy features of the uncertainty data by embedding membership functions and fuzzy rules within the neural network. In this process, fuzzy parameters are dynamically updated on a task-driven basis, ensuring that the model can adaptively handle data with different degrees of fuzziness. The multi-path classifier aggregation unit is designed to integrate the outputs of multiple neural network classifiers through dynamic linear combination. Meanwhile, we introduce the maximum margin theory of support vector machines to optimize the feature representation and improve classification accuracy. Our experimental results show that FASTEN can improve the classification performance on image and signal datasets. Through ablation experiments, the contributions of each unit to performance enhancement have been further validated, thereby establishing a foundation for subsequent model optimization. © 2025 IEEE.

关键词： Membership functions

来源：评论

学校读者我要写书评

暂无评论

PA-Seg: Learning from Point Annotations for 3D Medical Image Segmentation using Contextual Regularization and Cross Knowledge Distillation

arXiv

引用

arXiv 2022年

作者： Zhai, Shuwei Wang, Guotai Luo, Xiangde Yue, Qiang Li, Kang Zhang, Shaoting The School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China Chengdu611731 China Shanghai Artificial Intelligence Laboratory Shanghai200030 China Department of Radiology West China Hospital Sichuan University Chengdu610041 China West China Biomedical Big Data Center West China Hospital Sichuan University Chengdu610041 China

The success of Convolutional Neural Networks (CNNs) in 3D medical image segmentation relies on massive fully annotated 3D volumes for training that are time-consuming and labor-intensive to acquire. In this paper, we propose to annotate a segmentation target with only seven points in 3D medical images, and design a two-stage weakly supervised learning framework PA-Seg. In the first stage, we employ geodesic distance transform to expand the seed points to provide more supervision signal. To further deal with unannotated image regions during training, we propose two contextual regularization strategies, i.e., multi-view Conditional Random Field (mCRF) loss and Variance Minimization (VM) loss, where the first one encourages pixels with similar features to have consistent labels, and the second one minimizes the intensity variance for the segmented foreground and background, respectively. In the second stage, we use predictions obtained by the model pre-trained in the first stage as pseudo labels. To overcome noises in the pseudo labels, we introduce a Self and Cross Monitoring (SCM) strategy, which combines self-training with Cross Knowledge Distillation (CKD) between a primary model and an auxiliary model that learn from soft labels generated by each other. Experiments on public datasets for Vestibular Schwannoma (VS) segmentation and Brain Tumor Segmentation (BraTS) demonstrated that our model trained in the first stage outperformed existing state-of-the-art weakly supervised approaches by a large margin, and after using SCM for additional training, the model’s performance was close to its fully supervised counterpart on the BraTS dataset. © 2022, CC BY.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

MetaMask: Revisiting Dimensional Confounder for Self-Supervised Learning

arXiv

引用

arXiv 2022年

作者： Li, Jiangmeng Qiang, Wenwen Zhang, Yanan Mo, Wenyi Zheng, Changwen Su, Bing Xiong, Hui University of Chinese Academy of Sciences Institute of Software Chinese Academy of Sciences Southern Marine Science and Engineering Guangdong Laboratory Guangzhou China Gaoling School of Artificial Intelligence Renmin University of China China Institute of Software Chinese Academy of Sciences Southern Marine Science and Engineering Guangdong Laboratory Guangzhou China Gaoling School of Artificial Intelligence Renmin University of China Beijing Key Laboratory of Big Data Management and Analysis Methods China Thrust of Artificial Intelligence The Hong Kong University of Science and Technology Guangzhou China Guangzhou HKUST Fok Ying Tung Research Institute China

As a successful approach to self-supervised learning, contrastive learning aims to learn invariant information shared among distortions of the input sample. While contrastive learning has yielded continuous advancements in sampling strategy and architecture design, it still remains two persistent defects: the interference of task-irrelevant information and sample inefficiency, which are related to the recurring existence of trivial constant solutions. From the perspective of dimensional analysis, we find out that the dimensional redundancy and dimensional confounder are the intrinsic issues behind the phenomena, and provide experimental evidence to support our viewpoint. We further propose a simple yet effective approach MetaMask, short for the dimensional Mask learned by Meta-learning, to learn representations against dimensional redundancy and confounder. MetaMask adopts the redundancy-reduction technique to tackle the dimensional redundancy issue and innovatively introduces a dimensional mask to reduce the gradient effects of specific dimensions containing the confounder, which is trained by employing a meta-learning paradigm with the objective of improving the performance of masked representations on a typical self-supervised task. We provide solid theoretical analyses to prove MetaMask can obtain tighter risk bounds for downstream classification compared to typical contrastive methods. Empirically, our method achieves state-of-the-art performance on various benchmarks. Copyright © 2022, The Authors. All rights reserved.

关键词： Redundancy

来源：评论

学校读者我要写书评

暂无评论

A multipoint guidance mechanism for ß-barrel folding on the SAM complex (vol 30, pg 176, 2023)

引用

NATURE STRUCTURAL & MOLECULAR BIOLOGY 2023年第2期30卷 233-233页

作者： Takeda, Hironori Busto, Jon V. Lindau, Caroline Tsutsumi, Akihisa Tomii, Kentaro Imai, Kenichiro Yamamori, Yu Hirokawa, Takatsugu Motono, Chie Ganesan, Iniyan Wenz, Lena-Sophie Becker, Thomas Kikkawa, Masahide Pfanner, Nikolaus Wiedemann, Nils Endo, Toshiya Faculty of Life Sciences Kyoto Sangyo University Kyoto Japan Institute of Biochemistry and Molecular Biology Centre for Biochemistry and Molecular Cell Research Faculty of Medicine University of Freiburg Freiburg Germany Department of Cell Biology and Anatomy Graduate School of Medicine The University of Tokyo Tokyo Japan Artificial Intelligence Research Center National Institute of Advanced Industrial Science and Technology (AIST) Tokyo Japan Cellular and Molecular Biotechnology Research Institute AIST Tokyo Japan Division of Biomedical Science Faculty of Medicine University of Tsukuba Tsukuba Japan Transborder Medical Research Center University of Tsukuba Tsukuba Japan Computational Bio Big-Data Open Innovation Laboratory AIST Waseda University Tokyo Japan Institute of Biochemistry and Molecular Biology Faculty of Medicine University of Bonn Bonn Germany CIBSS Centre for Integrative Biological Signalling Studies University of Freiburg Freiburg Germany BIOSS Centre for Biological Signalling Studies University of Freiburg Freiburg Germany Institute for Protein Dynamics Kyoto Sangyo University Kyoto Japan

Mitochondrial β-barrel proteins are essential for the transport of metabolites, ions and proteins. The sorting and assembly machinery (SAM) mediates their folding and membrane insertion. We report the cryo-electron microscopy structure of the yeast SAM complex carrying an early eukaryotic β-barrel folding intermediate. The lateral gate of Sam50 is wide open and pairs with the last β-strand (β-signal) of the substrate—the 19-β-stranded Tom40 precursor—to form a hybrid barrel in the membrane plane. The Tom40 barrel grows and curves, guided by an extended bridge with Sam50. Tom40’s first β-segment (β1) penetrates into the nascent barrel, interacting with its inner wall. The Tom40 amino-terminal segment then displaces β1 to promote its pairing with Tom40’s last β-strand to complete barrel formation with the assistance of Sam37’s dynamic α-protrusion. Our study thus reveals a multipoint guidance mechanism for mitochondrial β-barrel folding.

关键词： Cryoelectron microscopy Protein transport

来源：评论

学校读者我要写书评

暂无评论

Sample hardness based gradient loss for long-tailed cervical cell detection

arXiv

引用

arXiv 2022年

作者： Liu, Minmin Li, Xuechen Gao, Xiangbo Chen, Junliang Shen, Linlin Wu, Huisi Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence of Robotics of Society Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China University of California Irvine United States

Due to the difficulty of cancer samples collection and annotation, cervical cancer datasets usually exhibit a long-tailed data distribution. When training a detector to detect the cancer cells in a WSI (Whole Slice Image) image captured from the TCT (Thinprep Cytology Test) specimen, head categories (e.g. normal cells and inflammatory cells) typically have a much larger number of samples than tail categories (e.g. cancer cells). Most existing state-of-the-art long-tailed learning methods in object detection focus on category distribution statistics to solve the problem in the long-tailed scenario, without considering the "hardness" of each sample. To address this problem, in this work we propose a Grad-Libra Loss that leverages the gradients to dynamically calibrate the degree of hardness of each sample for different categories, and re-balance the gradients of positive and negative samples. Our loss can thus help the detector to put more emphasis on those hard samples in both head and tail categories. Extensive experiments on a long-tailed TCT WSI image dataset show that the mainstream detectors, e.g. RepPoints, FCOS, ATSS, YOLOF, etc. trained using our proposed Gradient-Libra Loss, achieved much higher (7.8%) mAP than that trained using cross-entropy classification loss. Copyright © 2022, The Authors. All rights reserved.

关键词： Cytology

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：