检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Liu, Ke Liu, Feng Wang, Haishuai Ma, Ning Bu, Jiajun Han, Bo Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University Hangzhou China School of Computing and Information Systems The University of Melbourne Australia Department of Computer Science Hong Kong Baptist University Hong Kong

Implicit neural representations (INRs) aim to learn a continuous function (i.e., a neural network) to represent an image, where the input and output of the function are pixel coordinates and RGB/Gray values, respectively. However, images tend to consist of many objects whose colors are not perfectly consistent, resulting in the challenge that image is actually a discontinuous piecewise function and cannot be well estimated by a continuous function. In this paper, we empirically investigate that if a neural network is enforced to fit a discontinuous piecewise function to reach a fixed small error, the time costs will increase exponentially with respect to the boundaries in the spatial domain of the target signal. We name this phenomenon the exponential-increase hypothesis. Under the exponential-increase hypothesis, learning INRs for images with many objects will converge very slowly. To address this issue, we first prove that partitioning a complex signal into several sub-regions and utilizing piecewise INRs to fit that signal can significantly speed up the convergence. Based on this fact, we introduce a simple partition mechanism to boost the performance of two INR methods for image reconstruction: one for learning INRs, and the other for learning-to-learn INRs. In both cases, we partition an image into different sub-regions and dedicate smaller networks for each part. In addition, we further propose two partition rules based on regular grids and semantic segmentation maps, respectively. Extensive experiments validate the effectiveness of the proposed partitioning methods in terms of learning INR for a single image (ordinary learning framework) and the learning-to-learn framework. Code is released here. © 2023, CC BY-NC-SA.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Braille Layout Detection Model Based on Semantic Assistance

Hierarchical Braille Layout Detection Model Based on Semanti...

引用

Image Processing and computer Applications (ICIPCA), IEEE International Conference on

作者： Guangwu Wang Yu Gu Wei Wang Zhi Yu Shuyi Song China Braille Library Beijing China School of Software Technology Zhejiang University Hangzhou China Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University Hangzhou China DBAPPSecurity Ltd. College of Computer Science Zhejiang University Hangzhou China

This paper proposes a hierarchical Braille layout detection model based on semantic assistance, BLayoutNet. As research on Braille layout analysis is relatively scarce and there is a lack of relevant datasets, this paper proposes a Braille layout detection dataset to support research in this field. Finally, experimental results demonstrate that the proposed model achieves stable and accurate detection of Braille layout. It is hoped that this model can serve as a strong baseline for Braille layout analysis tasks and promote the development of this field.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Braille Detection Model Based on Foreground Attention and Semantic Learning

Braille Detection Model Based on Foreground Attention and Se...

引用

IEEE International Conference on Power, Intelligent Computing and Systems (ICPICS)

作者： Guangwu Wang Yu Gu Wei Wang Zhi Yu Shuyi Song China Braille Library Beijing China School of Software Technology Zhejiang University Hangzhou China Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University Hangzhou China DBAPP Security Ltd College of Computer Science Zhejiang University Hangzhou China

This paper presents BrailleNet, an enhanced one-stage anchor-based object detection model for Braille character recognition, incorporating foreground attention and semantic learning. BrailleNet is validated using two new datasets: mobile phone live shot Braille and chart Braille. Experimental results show BrailleNet's superior performance on both public and introduced datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Partition Speeds Up Learning Implicit Neural Representations Based on Exponential-Increase Hypothesis

Partition Speeds Up Learning Implicit Neural Representations...

引用

International Conference on computer Vision (ICCV)

作者： Ke Liu Feng Liu Haishuai Wang Ning Ma Jiajun Bu Bo Han Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University Hangzhou China School of Computing and Information Systems The University of Melbourne Australia Department of Computer Science Hong Kong Baptist University Hong Kong SAR China

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Traffic Light Recognition Method Based on Image Super Resolution in Intelligent Blind Glasses System

A Traffic Light Recognition Method Based on Image Super Reso...

引用

Advances in Informatics, Electronics and Education (ISAIEE), International Symposium on

作者： Yueqing Zhang Zhi Yu Wei Wang Jiajun Bu Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University Hangzhou China School of Software Technology Zhejiang University Hangzhou Zhejiang China

One kind of traffic light recognition method based on super resolution technology applied in intelligent eyeglasses system is proposed in this paper. Take advantage of the high recognition accuracy of the latest hot target detectors and the ability of super-resolution technology which can increase image resolution dramatically, so as to achieve the accurate identification of pedestrian traffic lights. The lightweight adjustment operation can ensure the real-time performance of the model on the mobile terminal and correctly assist the safe passage of visually impaired people at traffic intersections.

关键词： Image recognition Target recognition Image color analysis Superresolution Education Glass Detectors

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Blind Glasses System Based on Stair & Step Recognition Function

An Intelligent Blind Glasses System Based on Stair & Step Re...

引用

Signal Processing, Communications and Engineering Management Conference (ISPCEM), International

In this paper, an intelligent blind glasses system based on stair & step recognition is proposed, which combines the innovative appearance of the product and the high performance advantages of functional modules to effectively assist visually impaired users to safely avoid obstacles when they encounter stairs or steps in indoor environments.

关键词： Headphones Engineering management Lighting Glass Stairs Signal processing Bones

来源：评论

学校读者我要写书评

暂无评论

Hilbert Distillation for Cross-Dimensionality Networks

arXiv

引用

arXiv 2022年

作者： Qin, Dian Wang, Haishuai Liu, Zhe Xu, Hongjia Zhou, Sheng Bu, Jiajun Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University Hangzhou China School of Software Technology Zhejiang University Ningbo China

3D convolutional neural networks have revealed superior performance in processing volumetric data such as video and medical imaging. However, the competitive performance by leveraging 3D networks results in huge computational costs, which are far beyond that of 2D networks. In this paper, we propose a novel Hilbert curve-based cross-dimensionality distillation approach that facilitates the knowledge of 3D networks to improve the performance of 2D networks. The proposed Hilbert Distillation (HD) method preserves the structural information via the Hilbert curve, which maps high-dimensional (>=2) representations to one-dimensional continuous space-filling curves. Since the distilled 2D networks are supervised by the curves converted from dimensionally heterogeneous 3D features, the 2D networks are given an informative view in terms of learning structural information embedded in well-trained high-dimensional representations. We further propose a Variable-length Hilbert Distillation (VHD) method to dynamically shorten the walking stride of the Hilbert curve in activation feature areas and lengthen the stride in context feature areas, forcing the 2D networks to pay more attention to learning from activation features. The proposed algorithm outperforms the current state-of-the-art distillation techniques adapted to cross-dimensionality distillation on two classification tasks. Moreover, the distilled 2D networks by the proposed method achieve competitive performance with the original 3D networks, indicating the lightweight distilled 2D networks could potentially be the substitution of cumbersome 3D networks in the real-world scenario. Copyright © 2022, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Heterophilous Distribution Propagation for Graph Neural Networks

SSRN

引用

SSRN 2024年

作者： Zheng, Zhuonan Zhou, Sheng Xu, Hongjia Gu, Ming Xu, Yilun Li, Ao Li, Yuhong Gu, Jingjun Bu, Jiajun College of Computer Science Zhejiang University Hangzhou310027 China Zhejiang Provincial Key Laboratory of Service Robot Zhejiang University Hangzhou310027 China School of Software Technology Zhejiang University Ningbo315048 China Bytedance Inc. Hangzhou311113 China Alibaba Group Hangzhou310052 China

Graph Neural Networks (GNNs) have achieved remarkable success in various graph mining tasks by aggregating information from neighborhoods for representation learning. The success relies on the homophily assumption that nearby nodes exhibit similar behaviors, while it may be violated in many real-world graphs. Recently, heterophilous graph neural networks (HeterGNNs) have attracted increasing attention by modifying the neural message passing schema for heterophilous neighborhoods. However, they suffer from insufficient neighborhood partition and heterophily modeling, both of which are critical but challenging to break through. To tackle these challenges, in this paper, we propose heterophilous distribution propagation (HDP) for graph neural networks. Instead of aggregating information from all neighborhoods, HDP adaptively separates the neighbors into homophilous and heterphilous parts based on the pseudo assignments during training. The heterophilous neighborhood distribution is learned with orthogonality-oriented constraint via a trusted prototype contrastive learning paradigm. Both the homophilous and heterophilous patterns are propagated with a novel semantic-aware message passing mechanism. We conduct extensive experiments on 9 benchmark datasets with different levels of homophily. Experimental results show that our method outperforms representative baselines on heterophilous datasets. © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Heterophilous Distribution Propagation for Graph Neural Networks

arXiv

引用

arXiv 2024年

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Structure Enhanced Prototypical Alignment for Unsupervised Cross-Domain Node Classification

SSRN

引用

SSRN 2023年

作者： Liu, Meihan Zhang, Zhen Ma, Ning Gu, Ming Wang, Haishuai Zhou, Sheng Bu, Jiajun College of Computer Science Zhejiang University Hangzhou310027 China Zhejiang Provincial Key Laboratory of Service Robot Zhejiang University Hangzhou310027 China School of Software Technology Zhejiang University Ningbo315048 China School of Computing National University of Singapore 117417 Singapore

Graph Neural Networks (GNNs) have demonstrated remarkable success in graph node classification task. However, their performance heavily relies on the availability of high-quality labeled data, which can be time-consuming and labor-intensive to acquire for graph-structured data. Therefore, the task of transferring knowledge from a label-rich graph (source domain) to a completely unlabeled graph (target domain) becomes crucial. In this paper, we propose a novel unsupervised graph domain adaptation framework called Structure Enhanced Prototypical Alignment (SEPA), which aims to learn domain-invariant representations on non-IID (non-independent and identically distributed) data. Specifically, SEPA captures class-wise semantics by constructing a prototype-based graph and introduces an explicit domain discrepancy metric to align the source and target domains. The proposed SPEA framework is optimized in an end-to-end manner, which could be incorporated into various GNN architectures. Experimental results on several real-world datasets demonstrate that our proposed framework outperforms recent state-of-the-art baselines with different gains. © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

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：