检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Chen, Shu Li, Junyao Zhang, Yang Zou, Beiji The School of Computer Science School of Cyberspace Security Xiangtan University Xiangtan China Key Laboratory of Intelligent Computing & Information Processing Ministry of Education Xiangtan China School of Computer Science and engineering Central South University Changsha China

With dense inputs, Neural Radiance Fields (NeRF) is able to render photo-realistic novel views under static conditions. Although the synthesis quality is excellent, existing NeRF-based methods fail to obtain moderate three-dimensional (3D) structures. The novel view synthesis quality drops dramatically given sparse input due to the implicitly reconstructed inaccurate 3D-scene structure. We propose SfMNeRF, a method to better synthesize novel views as well as reconstruct the 3D-scene geometry. SfMNeRF leverages the knowledge from the self-supervised depth estimation methods to constrain the 3D-scene geometry during view synthesis training. Specifically, SfMNeRF employs the epipolar, photometric consistency, depth smoothness, and position-of-matches constraints to explicitly reconstruct the 3D-scene structure. Through these explicit constraints and the implicit constraint from NeRF, our method improves the view synthesis as well as the 3D-scene geometry performance of NeRF at the same time. In addition, SfMNeRF synthesizes novel sub-pixels in which the ground truth is obtained by image interpolation. This strategy enables SfMNeRF to include more samples to improve generalization performance. Experiments on three public datasets demonstrate that SfMNeRF surpasses state-of-the-art approaches given the spare inputs. Code is available at https://***/XTU-PR-LAB/SfMNeRF. Copyright © 2023, The Authors. All rights reserved.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

High-accurate and efficient numerical algorithms for the self-consistent field theory of liquid-crystalline polymers

arXiv

引用

arXiv 2024年

作者： He, Zhijuan Jiang, Kai Tan, Liwei Wang, Xin Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan411105 China School of Mathematical Sciences Shanghai Jiao Tong University Shanghai200240 China

Self-consistent field theory (SCFT) is one of the most widely-used framework in studying the equilibrium phase behaviors of inhomogenous polymers. For liquid crystalline polymeric systems, the main numerical challenges of solving SCFT encompass efficiently solving plenty of six dimensional partial differential equations (PDEs), precisely determining the subtle energy difference among self-assembled structures, and developing effective iterative methods for nonlinear SCF iteration. To address these challenges, this work introduces a suite of high-order and efficient numerical methods tailored for SCFT of liquid-crystalline polymers. These methods include various advaced PDE solvers, an improved Anderson iteration algorithm to accelerate SCFT calculations, and an optimization technique of adjusting the computational domain during the SCF iterations. Extensive numerical tests demonstrate the efficiency of the proposed methods. Based on these algorithms, we further explore the self-assembly behavior of liquid crystalline polymers through simulations in four, five, and six dimensions, uncovering intricate three-dimensional spatial structures. Copyright © 2024, The Authors. All rights reserved.

关键词： Crystalline materials

来源：评论

学校读者我要写书评

暂无评论

Performer: A High-Performance Global-Local Model-Augmented with Dual Network Interaction Mechanism

引用

IEEE Transactions on Cognitive and Developmental Systems 2024年

作者： Tan, Dayu Hao, Rui Hua, Linfeng Xu, Qi Su, Yansen Zheng, Chunhou Zhong, Weimin Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Institutes of Physical Science and Information Technology Hefei230601 China East China University of Science and Technology Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of Education Shanghai200237 China Dalian University of Technology School of Computer Science and Technology Dalian116024 China

In deep learning, Convolutional Neural Networks (CNNs) focus on local information through convolutional kernels, while transformers attend to global information using self-attention mechanisms. The union of these distinct approaches enables a more comprehensive extraction of image features. However, the feature map dimensions of CNN and Transformer differ, leading to dimension mismatch issues when combining these architectures. Additionally, the parameter size of the hybrid model integrating both architectures remains large, making it difficult to train. To further augmenting the interpretation of complex image patterns, we present Performer, a dual-network architecture that seamlessly combines CNNs and transformers, resulting in a novel and efficient representation learning model. In the Performer model, we innovate by devising a unique interaction methodology for CNN and transformer architectures to enhance the image feature extraction capabilities mutually. To counteract issue of dimensionality mismatch, we also introduce a refined transformer block, a advancement over the transformer block of ViT. To validate the effectiveness of Performer, we conduct extensive experiments on both classification and segmentation tasks. Performer achieve an accuracy of 83.37% on the ImageNet-200 dataset. For semantic segmentation, Performer excels on the CamVid and Hippocampus datasets. On CamVid, our model achieves a mean Intersection over Union (mIoU) of 63.27% and Pixel Accuracy of 92.11%, demonstrating superior performance in capturing fine details and handling complex scenes effectively. The code is available at https://***/hlfthh/ Performer. © 2016 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Feature Selection Based on Fuzzy Related Family

SSRN

引用

SSRN 2023年

作者： Yang, Tian Guo, Zhijun Li, Yuan-Jiang Deng, Yanfang Qian, Yuhua Hunan Provincial Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Hunan Changsha410081 China Institute of Big Data Science and Industry Shanxi University Shanxi Taiyuan030006 China

Existing machine learning algorithms face the problems of label-missing and high dimensionality. Feature selection is an effective dimensionality reduction method that can improve the efficiency and accuracy of subsequent machine learning tasks by removing irrelevant and redundant features. Related family is an efficient and rough set-based feature selection method, but is difficult to be used in simisupervised learning tasks. However, due to the difficulty of obtaining all labeled data, partially labeled data has become an important object that machine learning models must deal with. Therefore, this paper proposes a semi-supervised fuzzy related family-based feature selection method for partially labeled data. This method first calculates the fuzzy label values of unlabeled samples through fuzzy similarity relationships to establish a new fuzzy covering system. Then, based on the fuzzy covering system, it constructs a fuzzy related family based on consistent fuzzy set. Finally, based on the constructed feature significance measurement, a semi-supervised feature selection algorithm based on fuzzy related family (SFRF) is established. Compared with existing semi-supervised feature selection algorithms, SFRF can significantly improve the efficiency of feature selection while maintaining classification accuracy, with the average reduction efficiency of nine datasets increased by up to 201 times. © 2023, The Authors. All rights reserved.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Balanced Contrastive Learning for Long-Tailed Visual Recognition

arXiv

引用

arXiv 2022年

作者： Zhu, Jianggang Wang, Zheng Chen, Jingjing Chen, Yi-Ping Phoebe Jiang, Yu-Gang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China Shanghai Collaborative Innovation Center on Intelligent Visual Computing China Department of Computer Science and Information Technology La Trobe University Australia

Real-world data typically follow a long-tailed distribution, where a few majority categories occupy most of the data while most minority categories contain a limited number of samples. Classification models minimizing cross-entropy struggle to represent and classify the tail classes. Although the problem of learning unbiased classifiers has been well studied, methods for representing imbalanced data are under-explored. In this paper, we focus on representation learning for imbalanced data. Recently, supervised contrastive learning has shown promising performance on balanced data recently. However, through our theoretical analysis, we find that for long-tailed data, it fails to form a regular simplex which is an ideal geometric configuration for representation learning. To correct the optimization behavior of SCL and further improve the performance of long-tailed visual recognition, we propose a novel loss for balanced contrastive learning (BCL). Compared with SCL, we have two improvements in BCL: class-averaging, which balances the gradient contribution of negative classes;class-complement, which allows all classes to appear in every mini-batch. The proposed balanced contrastive learning (BCL) method satisfies the condition of forming a regular simplex and assists the optimization of cross-entropy. Equipped with BCL, the proposed two-branch framework can obtain a stronger feature representation and achieve competitive performance on long-tailed benchmark datasets such as CIFAR-10-LT, CIFAR-100-LT, ImageNet-LT, and iNaturalist2018. Our code is available at this URL. Copyright © 2022, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Simple and Efficient Knowledge Graph Attention Network for Recommendation

Simple and Efficient Knowledge Graph Attention Network for R...

引用

Cyber-Physical Social Intelligence (ICCSI), International Conference on

作者： Yangding Li Shaobin Fu Hao Feng Yangyang Zeng Jinghao Wang Zhihao Jiang Lvyun Zhang School of Information Science and Engineering Hunan Provincial Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha China Shenzhen Lazada Software Technology Company Limited Shenzhen China School of Big Data and Computer Science Hechi University Guangxi China

Existing methods for modeling recommendation systems based on knowledge graphs include embedding-based, pathbased, and propagation-based methods. The embedding-based approach is flexible but more suitable for intra-graph applications, the path-based approach can model complex relationships but has a high computational cost, and the propagation-based approach considers global information but may introduce noise. This study proposed a simple and efficient model, called SEKGAT, which comprehensive the ideology of path-based and propagation approach to personalized recommendation by aggregating the user preferences through graph attention mechanism and fusing multiple feature representations on the knowledge graph into item features through pooling aggregators. Experimental results for the CTR prediction and Top-K recommendation tasks on three datasets of real-world scenarios show that our model approach is competitive.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AR-CNN: an attention ranking network for learning urban perception

引用

science China(information sciences) 2022年第1期65卷 164-174页

作者： Zhetao LI Ziwen CHEN Wei-Shi ZHENG Sangyoon OH Kien NGUYEN Key Laboratory of Hunan Province for Internet of Things and Information Security Xiangtan University Key Laboratory of Intelligent Computing & Information Processing of Ministry of Education Xiangtan University School of Data and Computer Science Sun Yat-sen University Department of Computer and Information Engineering Ajou University Graduate School of Engineering Chiba University

An increasing number of deep learning methods is being applied to quantify the perception of urban environments, study the relationship between urban appearance and resident safety, and improve urban appearance. Most advanced methods extract image feature representations from street-level images through conventional visual computation algorithms or deep convolutional neural networks and then directly predict the results using features. Unfortunately, these methods take color and texture information together during processing. Color and texture are prime image features, and they affect human perception and judgment differently. We argue that color and texture should be operated differently; therefore, we formulate an end-to-end learning methodology to process input images according to color and texture information before inputting it into the neural network. The processed images and the original image constitute three input streams for the triad attention ranking convolutional neural network(AR-CNN) model proposed in this *** accordance with the aspects of color and texture, an improved attention mechanism in the convolution layer is proposed. Our objective is to obtain the scores of humans on urban appearance in accordance with the prediction results computed from pairwise comparisons generated by the AR-CNN model.

关键词： ranking network urban perception attribute learning attention network colour and texture

来源：评论

学校读者我要写书评

暂无评论

Label Distribution Learning with Correlation information

SSRN

引用

SSRN 2024年

作者： Wu, Yilin Lin, Yaojin Guo, Wenzhong Ding, Weiping College of Computer and Data Science Fuzhou University Fuzhou350116 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350116 China Key Laboratory of Data Science and Intelligence Application Minnan Normal University Zhangzhou363000 China School of Information Science and Technology Nantong University Nantong226019 China

Label distribution learning quantifies the label space for each instance and has widely applicability in different fields. However, most existing works primarily focus on label correlation, but they still have a limitation in capturing instance correlation. Meanwhile, traditional label distribution learning operates on individual labels sequentially, leading to limitation in applying common features. Therefore, in this paper, we propose a novel approach for label distribution learning with correlation information i.e. instance correlation and label correlation. Specifically, the instance correlation and label correlation are identified by an optimization function and Pearson correlation coefficient, respectively. Besides, we conduct $\ell_{2,1}-$norm regularization to exploit common features. Comprehensive experiments manifest the superiority of our proposed approach against other well-established label distribution learning algorithms. © 2024, The Authors. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

ABCD-HN: An Artificial Network Benchmark for Community Detection on Heterogeneous Networks 18th

ABCD-HN: An Artificial Network Benchmark for Community Dete...

引用

18th CCF Conference on Computer Supported Cooperative Work and Social computing, ChineseCSCW 2023

作者： Liu, Junjie Guo, Kun Wu, Ling Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350108 China College of Computer and Data Science/College of Software Fuzhou University Fuzhou350108 China Key Laboratory of Spatial Data Mining and Information Sharing Ministry of Education Fuzhou350108 China

ISBN: (纸本)9789819996360

Community detection is essential for identifying cohesive groups in complex networks. Artificial benchmarks are critical for evaluating community detection algorithms, offering controlled environments with known community structures. However, existing benchmarks mainly focus on homogeneous networks and overlook the unique characteristics of heterogeneous networks. This paper proposes a novel artificial benchmark, called ABCD-HN (Artificial Network Benchmark for Community Detection on Heterogeneous Networks), for community detection in heterogeneous networks. This benchmark enables the generation of artificial heterogeneous networks with controllable community quantity, node quantity, and community complexity. Additionally, an evaluation framework for artificial heterogeneous networks is proposed to assess their effectiveness. Experimental results demonstrate the effectiveness and usability of ABCD-HN as a benchmark for artificial heterogeneous networks. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Heterogeneous networks

来源：评论

学校读者我要写书评

暂无评论

Gradually Vanishing Gap in Prototypical Network for Unsupervised Domain Adaptation

arXiv

引用

arXiv 2024年

作者： Wang, Shanshan Zhou, Hao Yang, Xun He, Zhenwei Wang, Mengzhu Zhang, Xingyi Wang, Meng The Information Materials and Intelligent Sensing Laboratory of Anhui Province Institutes of Physical Science and Information Technology Anhui University Hefei230601 China The Department of Electronic Engineering and Information Science School of Information Science and Technology University of Science and Technology of China Hefei230026 China The College of Computer Science and Engineering Chongqing University of Technology Chongqing400054 China The School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China The School of Artificial Intelligence Hebei University of Technology Tianjin China The Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education The School of Computer Science and Technology Anhui University Hefei230601 China

Unsupervised domain adaptation (UDA) is a critical problem for transfer learning, which aims to transfer the semantic information from labeled source domain to unlabeled target domain. Recent advancements in UDA models have demonstrated significant generalization capabilities on the target domain. However, the generalization boundary of UDA models remains unclear. When the domain discrepancy is too large, the model can not preserve the distribution structure, leading to distribution collapse during the alignment. To address this challenge, we propose an efficient UDA framework named Gradually Vanishing Gap in Prototypical Network (GVG-PN), which achieves transfer learning from both global and local perspectives. From the global alignment standpoint, our model generates a domain-biased intermediate domain that helps preserve the distribution structures. By entangling cross-domain features, our model progressively reduces the risk of distribution collapse. However, only relying on global alignment is insufficient to preserve the distribution structure. To further enhance the inner relationships of features, we introduce the local perspective. We utilize the graph convolutional network (GCN) as an intuitive method to explore the internal relationships between features, ensuring the preservation of manifold structures and generating domain-biased prototypes. Additionally, we consider the discriminability of the inner relationships between features. We propose a pro-contrastive loss to enhance the discriminability at the prototype level by separating hard negative pairs. By incorporating both GCN and the pro-contrastive loss, our model fully explores fine-grained semantic relationships. Experiments on several UDA benchmarks validated that the proposed GVG-PN can clearly outperform the SOTA models. Copyright © 2024, The Authors. All rights reserved.

关键词： Alignment

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：