检索结果-内蒙古大学图书馆

Proceedings of the 38th International Conference on neural information processing Systems

作者： Yixin Ren Yewei Xia Hao Zhang Jihong Guan Shuigeng Zhou Shanghai Key Lab of Intelligent Information Processing and School of Computer Science Fudan University Shanghai China Shanghai Key Lab of Intelligent Information Processing and School of Computer Science Fudan University Shanghai China and Machine Learning Department MBZUAI Abu Dhabi UAE SIAT Chinese Academy of Sciences Shenzhen China Department of Computer Science and Technology Tongji University Shanghai China

ISBN: (纸本)9798331314385

We propose a novel method to efficiently learn significant Fourier feature pairs for maximizing the power of Hilbert-Schmidt Independence Criterion (HSIC) based independence tests. We first reinterpret HSIC in the frequency domain, which reveals its limited discriminative power due to the inability to adapt to specific frequency-domain features under the current inflexible configuration. To remedy this shortcoming, we introduce a module of learnable Fourier features, thereby developing a new criterion. We then derive a finite sample estimate of the test power by modeling the behavior of the criterion, thus formulating an optimization objective for significant Fourier feature pairs learning. We show that this optimization objective can be computed in linear time (with respect to the sample size n), which ensures fast independence tests. We also prove the convergence property of the optimization objective and establish the consistency of the independence tests. Extensive empirical evaluation on both synthetic and real datasets validates our method's superiority in effectiveness and efficiency, particularly in handling high-dimensional data and dealing with large-scale scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fuzzy-based pseudo segmentation approach for handwritten word recognition using a sequence to sequence model with attention 25th

Fuzzy-based pseudo segmentation approach for handwritten wor...

引用

25th International Conference on Pattern Recognition Workshops, ICPR 2020

作者： Bhattacharya, Rajdeep Malakar, Samir Schwenker, Friedhelm Sarkar, Ram Department of Computer Science and Engineering Jadavpur University Kolkata India Department of Computer Science Ashutosh College Kolkata India Institute of Neural Information Processing University of Ulm Ulm Germany

ISBN: (纸本)9783030687892

Sequence to sequence models have shown significant progress in the field of handwriting recognition. The recent trend has been that the input to these models is fed from a convolutional neural network (CNN) that acts as a generic feature extractor for the handwritten text images. The input to the CNN is usually either a sequence of patches extracted from the text image or the output of a segmentation algorithm applied on the text image to break it up into individual characters. However, patching is unable to convey proper information about character boundaries in the image, and the segmentation-based approach often suffers from over and under segmentation. To this end, we propose a fuzzy-based pseudo segmentation approach for handwritten word recognition using a sequence to sequence model. We use a fuzzy triangular function that generates column wise weights based on the distance of the nearest data pixel from the top of the text image. Thus the probable segmentation regions are assigned higher weights than the other regions. These weights are superimposed on the original text image and this modified input is fed patch wise to the CNN. The features extracted are then encoded as a first part of a sequence to sequence model and then decoded to obtain the sequence of characters in the input. An attention mechanism is used to ensure that the decoder focuses on the appropriate section of the features outputted by the encoder while generating each character. Our method is tested upon the IAM word database after the words in it undergo skew and slant correction. The architecture of the model is optimized based on exhaustive numerical simulations on the IAM database and it shows promising results. © Springer Nature Switzerland AG 2021.

关键词： Vocabulary control

来源：评论

学校读者我要写书评

暂无评论

Hiren: Towards Higher Supervision Quality Forbetter Scene Text Image Super-Resolution

SSRN

引用

SSRN 2024年

作者： Zhao, Minyi Xu, Yi Li, Bingjia Wang, Jie Guan, Jihong Zhou, Shuigeng Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China ByteDance Inc China Department of Computer Science and Technology Tongji University China

Scene text image super-resolution (STISR) is an important pre-processing technique for text recognition from low-resolution scene images. Nowadays, various methods have been proposed to extract text-specific information from high-resolution (HR) images to supervise STISR model training. However, due to uncontrollable factors (e.g. shooting equipment, focus, and environment) in manually photographing HR images, the quality of HR images cannot be guaranteed, which unavoidably impacts STISR performance. Observing the quality issue of HR images, in this paper we propose a novel idea to boost STISR by first enhancing the quality of HR images and then using the enhanced HR images as supervision to do STISR. Concretely, we develop a new STISR framework, called High-Resolution ENhancement (HiREN) that consists of two branches and a quality estimation module. The first branch is developed to recover the low-resolution (LR) images, and the other is an HR quality enhancement branch aiming at generating high-quality (HQ) text images based on the HR images to provide more accurate supervision to the LR images. As the degradation from HQ to HR may be diverse, and there is no pixel-level supervision for HQ image generation, we design a kernel-guided enhancement network to handle various degradation, and exploit the feedback from a recognizer and text-level annotations as weak supervision signal to train the HR enhancement branch. Then, a quality estimation module is employed to evaluate the qualities of HQ images, which are used to suppress the erroneous supervision information by weighting the loss of each image. Extensive experiments on TextZoom show that HiREN can work well with most existing STISR methods and significantly boost their performances. © 2024, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Supervised Relation Extraction Based on labels Contrastive Learning

Supervised Relation Extraction Based on Labels Contrastive L...

引用

International Congress on Image and Signal processing, BioMedical Engineering and Informatics (CISP-BMEI)

作者： Yuanru Wang Yanhui Zhao Rong-Yi Cui Guo-Zhe Jin Department of Computer Science & Technology Intelligent Information Processing Lab. Yanbian University Yanji China

Relation extraction is an important task in natural language processing. Existing relation extraction tasks usually use data augmentation to construct positive and negative samples for contrastive learning training. And previous works lack the accurate selection of positive and negative samples and the full use of relation labels. To overcome these defects, for supervised relational extraction, we propose a labels Contrastive Learning framework (labelsCL) that considers both global and local perspectives, which makes full use of labels for design. Specifically, from a global perspective, we use label and cosine similarity to select the most easily misclassified samples as positive and negative examples for training. From a local perspective, positive and negative samples are selected according to batch and label, and this way of sample selection increases the randomness of sample selection. The contrastive learning framework labelsCL proposed by us makes full use of labels and synthesizes two perspectives to construct contrastive learning labelsCL, which increases the tolerance of the framework. Finally, the experimental results demonstrate the effectiveness of our proposed framework, which is significantly improved on the Semeval-2010 Task 8 dataset compared with the baselines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Impact of COVID-19 on Residential and Non-residential Power Consumption: A Data-Driven Study

Impact of COVID-19 on Residential and Non-residential Power ...

引用

Power and Electrical Engineering (ACPEE), 5th Asia Conference on

作者： Qifan Zhang Xiu Cao Yang Chen Yixin Cao Min Gao Department of Computer Science Shanghai Key Lab of Intelligent Information Processing Fudan University Shanghai China

In the past few years, the COVID-19 pandemic has affected all aspects of people’s daily life. In particular, people in large cities have also been greatly affected. How to accurately and timely evaluate and analyze the impact of COVID-19 on large cities in China is increasingly significant. Based on the four-year power consumption data of a large city in China, this paper examines COVID-19’s impact from the perspective of residential and non-residential power *** address the discrepancies in climate and date information, we created COVID-19-Power, a framework that predicts the predicted power consumption of the city in 2020 without the outbreak of COVID-19, and then analyzes the difference in power consumption between the real situation and predicted results. For residential power consumption, we analyze the respective users’ behavior citywide, in different districts, and with different historical power consumption habits clustered by the K-means algorithm. On the other hand, for non-residential consumption, we analyze the users citywide, in different regions and industries. The results showed that while the impact of the pandemic on resident power consumption has been small, it is significant for non-residential power consumption, which is independent of geographical location. The regional differences were mainly reflected in the main types of industries. Through these research results, we can understand in detail the impact of the pandemic on residents’ lives and industries in China’s large cities; Power enterprises can more precisely understand the impact of the pandemic on electrical load, so that power enterprises can adjust power supply strategies more effectively and pertinently.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detecting compromised accounts caused by phone number recycling on e-commerce platforms: taking Meituan as an example

引用

Frontiers of information Technology & Electronic Engineering 2024年第8期25卷 1077-1095页

作者： Min GAO Shutong CHEN Yangbo GAO Zhenhua ZHANG Yu CHEN Yupeng LI Qiongzan YE Xin WANG Yang CHEN School of Computer Science Fudan UniversityShanghai 200438China Shanghai Key Lab of Intelligent Information Processing Fudan UniversityShanghai 200438China Meituan Beijing 100005China Department of Interactive Media Hong Kong Baptist UniversityHong Kong 999077China

Phone number recycling(PNR)refers to the event wherein a mobile operator collects a disconnected number and reassigns it to a new *** has posed a threat to the reliability of the existing authentication solution for e-commerce ***,a new owner of a reassigned number can access the application account with which the number is associated,and may perform fraudulent *** solutions that employ a reassigned number database from mobile operators are costly for e-commerce platforms with large-scale ***,alternative solutions that depend on only the information of the applications are *** this work,we study the problem of detecting accounts that have been compromised owing to the reassignment of phone *** analysis on Meituan's real-world dataset shows that compromised accounts have unique statistical features and temporal *** on the observations,we propose a novel model called temporal pattern and statistical feature fusion model(TSF)to tackle the problem,which integrates a temporal pattern encoder and a statistical feature encoder to capture behavioral evolutionary interaction and significant operation *** experiments on the Meituan and IEEE-CIS datasets show that TSF significantly outperforms the baselines,demonstrating its effectiveness in detecting compromised accounts due to reassigned numbers.

关键词： Phone number recycling neural networks E-commerce Compromised account detection

来源：评论

学校读者我要写书评

暂无评论

scRNA-seq Data Clustering by Cluster-aware Iterative Contrastive Learning

arXiv

引用

arXiv 2023年

作者： Jiang, Weikang Wang, Jinxian Guan, Jihong Zhou, Shuigeng Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China Department of Computer Science and Technology Tongji University China

Single-cell RNA sequencing (scRNA-seq) enables researchers to analyze gene expression at single-cell level. One important task in scRNA-seq data analysis is unsupervised clustering, which helps identify distinct cell types, laying down the foundation for other downstream analysis tasks. In this paper, we propose a novel method called Cluster-aware Iterative Contrastive Learning (CICL in short) for scRNA-seq data clustering, which utilizes an iterative representation learning and clustering framework to progressively learn the clustering structure of scRNA-seq data with a cluster-aware contrastive loss. CICL consists of a Transformer encoder, a clustering head, a projection head and a contrastive loss module. First, CICL extracts the feature vectors of the original and augmented data by the Transformer-encoder. Then, it computes the clustering centroids by K-means and employs the student’s t-distribution to assign pseudo-labels to all cells in the clustering head. The projection-head uses a Multi-Layer Perceptron (MLP) to obtain projections of the augmented data. At last, both pseudo-labels and projections are used in the contrastive loss to guide the model training. Such a process goes iteratively so that the clustering result becomes better and better. Extensive experiments on 25 real-world scRNA-seq datasets show that CICL outperforms the state-of-the-art (SOTA) methods. Concretely, CICL surpasses the existing methods by from 14% to 280%, and from 5% to 133% on average in terms of performance metrics ARI and NMI respectively. Source code is available at https://***/Alunethy/CICL. Copyright © 2023, The Authors. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Effect of Pectoral Muscles on CNN based Mammographic Cancer Detection

Effect of Pectoral Muscles on CNN based Mammographic Cancer ...

引用

International Conference on Computing for Sustainable Global Development (INDIACom)

作者： Santoresh Kumari Dhimann Tinny Sawhney Rakesh Kumar Yadav Department of Computer Science & Engineering Maharishi University of Information Technology Lucknow India Department of Electronics Digital Signal Processing Lab University of Jammu Jammu India

Cancer is attributed to abnormal growth of tissue cells in any part of the living body. The number of cancer patients is increasing worldwide. The reason of the development of abnormal cells within the body is still unknown to the researchers. The most common is breast cancer and it is affective affecting one out of every ten women. The reason of breast lesions formation may be calcification or mass deposit and digital mammography is generally used for verifying it. It is a cheap, non-toxic, and user-friendly test, but needs expert opinion for ascertaining the presence of cancer. The accuracy of mammographic detection varies between 80% and 90%. Recently, Convolutional neural networks (CNNs) have shown their application in automatic detection of the cancer, but inclusion of pectoral muscle in the mammogram reduces the efficiency of the CNN system as the texture of the muscle resembles with cancerous tissues. Further, CNN based detection requires high resolution images which in turn requires state of art technology-based machines, generally, not available in rural area-based clinics. The focus of the proposed research is to investigate effect of low-quality blurred input mammograms on the detection of pectoral muscle boundary, so that the pectoral muscle removed mammograms can be applied to CNN system for automatic prediction of cancerous images. The investigations carried out have shown that low quality blurred images can also be employed for detecting cancerous tissues provided the pectoral muscle is removed from the mammograms before using CNN based classifier.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Causal Discovery by Continuous Optimization with Conditional Independence Constraint: Methodology and Performance

Causal Discovery by Continuous Optimization with Conditional...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Yewei Xia Hao Zhang Yixin Ren Jihong Guan Shuigeng Zhou Shanghai Key Lab of Intelligent Information Processing and School of Computer Science Fudan University China Department of Computer Science & Technology Tongji University China

Discovering causal relationships from observational data is a challenging topic in artificial intelligence. Recent works formulate causal discovery as a continuous optimization problem with a differentiable acyclic constraint. Although these methods have achieved considerable performance improvement, they have two drawbacks: 1) they require a relatively large number of training samples; and 2) their performance will substantially deteriorate when facing heterogeneous noise. To address these problems, we first propose a low-order conditional independence (CI) constraint for the continuous optimization problem, and then design a soft version of the constraint by transforming it to a regularization term in the loss function of the continuous optimization problem. We show the convergence of continuous optimization with our constraint under some mild conditions, and the consistency of causal structure learning with the CI regularization. Extensive experiments on both synthetic and real-world datasets show that with our CI constraint or regularization, existing continuous optimization methods can achieve considerable performance improvement of causal discovery, especially when sample size is small.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adversarial Quantum Machine Learning: An information-Theoretic Generalization Analysis

Adversarial Quantum Machine Learning: An Information-Theoret...

引用

IEEE International Symposium on information Theory

作者： Petros Georgiou Sharu Theresa Jose Osvaldo Simeone Department of Computer Science University of Birmingham UK Department of Engineering KCLIP Lab Centre for Intelligent Information Processing Systems (CIIPS) King's College London

ISBN: (数字)9798350382846

ISBN: (纸本)9798350382853

In a manner analogous to their classical counterparts, quantum classifiers are vulnerable to adversarial attacks that perturb their inputs. A promising countermeasure is to train the quantum classifier by adopting an attack-aware, or adversarial, loss function. This paper studies the generalization properties of quantum classifiers that are adversarially trained against bounded-norm white-box attacks. Specifically, a quantum adversary maximizes the classifier's loss by transforming an input state $\rho(x)$ into a state $\tau$ that is $\epsilon$ -close to the original state $\rho(x)$ in p-Schatten distance. Under suitable assumptions on the quantum embedding $\rho(x)$ , we derive novel information-theoretic upper bounds on the generalization error of adversarially trained quantum classifiers for $p=1$ and $p=\infty$ . The derived upper bounds consist of two terms: the first is an exponential function of the 2-Renyi mutual information between classical data and quantum embedding, while the second term scales linearly with the adversarial perturbation size $\epsilon$ . Both terms are shown to decrease as $1/\sqrt{T}$ over the training set size $T$ . An extension is also considered in which the adversary assumed during training has different parameters $p$ and $\epsilon$ as compared to the adversary affecting the test inputs. Finally, we validate our theoretical findings with numerical experiments for a synthetic setting.

关键词： Training Upper bound Perturbation methods Quantum mechanics Machine learning Mutual information Glass box

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：