检索结果-内蒙古大学图书馆

Sensors, Electronics and computer Engineering (ICSECE), IEEE International Conference on

作者： Yantian Zheng Hangdi Xing Zhi Yu Xinhua Zhang Feiyu Gao Jiajun Bu Zhejiang Provincial Key Laboratory of Service Robot School of Software Technology Zhejiang University Ningbo China Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University Hangzhou China Zhejiang School for the Blind Hangzhou China Alibaba Group DAMO Academy Hangzhou China

In the field of education, Teachers of Students with Visual Impairments need to read and review student’s Braille homework. Reading Braille consumes a lot of teachers' time and energy. We propose an end-to-end solution to translate Braille into Chinese. Our approach uses a deep learning method to detect and recognize Braille in images and translate them into Chinese and mathematical formulas. Finally, we reconstruct the translation results into the style of the input Braille image. Our approach is able to adapt to more complex Braille images and make the translation results easier to read and understand, significantly improving the speed of reading Braille for non-disabled.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A multi-objective fog computing task scheduling strategy based on ant colony algorithm 4

A multi-objective fog computing task scheduling strategy bas...

引用

4th IEEE International Conference on Information Systems and computer Aided Education, ICISCAE 2021

作者： Gu, Jingjun Mo, Jiadi Li, Ben Zhang, Yueqing Wang, Wei College of Computer Science Zhejiang University Zhejiang Provincial Key Laboratory of Service Robot Hangzhou China Polytechnic Institute Zhejiang University Hangzhou China

ISBN: (纸本)9781665441247

Fog computing can effectively reduce latency and improve resource utilization by extending cloud services to the edge of the network. However, due to the wide variety of fog equipment and different computing capabilities, the theoretical knowledge and practical work related to fog computing task scheduling are insufficient. When scheduling tasks, factors such as cost of computing resources, power costs, and network cost were not considered comprehensively. Therefore, we propose a multi-objective fog computing task scheduling algorithm based on improved ant colony algorithm, which optimize the ant colony algorithm to make it more suitable for the characteristics of the fog node, use time and cost (TAC) to comprehensively consider the cost of the node, and introduce the critical factor in task allocation to improve the convergence speed of the algorithm. Different simulation experiments show that the efficiency of the improved ant colony algorithm is enhanced in processing time, cost, and load balance. © 2021 IEEE.

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

An Interpretable Deep Embedding Model for Few and Imbalanced Biomedical Data

引用

IEEE Journal of Biomedical and Health Informatics 2022年 PP卷 1-8页

作者： Wang, Haishuai Li, Li Ma, Jiali Chi, Lianhua Yang, Jianjun Tao, Guangyu Wu, Jun Zhao, Ziping Church, George M. Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University Hangzhou China Department of Genetics Blavatnik Institute and Wyss Institute for Biologically Inspired Engineering Harvard University Boston MA USA College of Computer Science Tianjin Normal University Tianjin China Department of Computer Science La Trobe University Melbourn VIC Australia Department of General Practice Shandong Provincial Third Hospital Cheeloo College of Medicine Shandong University Jinan China Department of Radiology Shanghai Chest Hospital Shanghai Jiao Tong University Shanghai China School of Computer Science Beijing Jiaotong University Beijing China

In healthcare, training examples are usually hard to obtain (e.g., cases of a rare disease), or the cost of labelling data is high. With a large number of features ($p$) be measured in a relatively small number of samples ($N$), the “big $p$, small $N$” problem is an important subject in healthcare studies, especially on the genomic data. Another major challenge of effectively analyzing medical data is the skewed class distribution caused by the imbalance between different class labels. In addition, feature importance and interpretability play a crucial role in the success of solving medical problems. Therefore, in this paper, we present an interpretable deep embedding model (IDEM) to classify new data having seen only a few training examples with highly skewed class distribution. IDEM model consists of a feature attention layer to learn the informative features, a feature embedding layer to directly deal with both numerical and categorical features, a siamese network with contrastive loss to compare the similarity between learned embeddings of two input samples. Experiments on both synthetic data and real-world medical data demonstrate that our IDEM model has better generalization power than conventional approaches with few and imbalanced training medical samples, and it is able to identify which features contribute to the classifier in distinguishing case and control. IEEE

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Hilbert distillation for cross-dimensionality networks 22

Hilbert distillation for cross-dimensionality networks

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

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

ISBN: (纸本)9781713871088

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.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Road Plant Image Classification Algorithm Based on Segmentation Prior

Road Plant Image Classification Algorithm Based on Segmentat...

引用

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

作者： Qiao Sun Yi Yang Jingjun Gu Zhi Yu Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University Hangzhou China School of Electronic Engineering Naval University of Engineering Wuhan China

As an important part of urban ecology, it is of great significance to grasp and analyze the detailed distribution of road plants for both scientific research and landscape planning. However, due to the advancement of urbanization, the types and numbers of road plants are increasing, and it is difficult to obtain accurate and timely plant distribution information by traditional field research and remote sensing techniques. In order to solve this problem, we proposes a deep learning-based road plant image classification algorithm, which identifies plants in streetscape data by multi- label image classification to obtain the distribution of road plants. In order to solve the problem of feature information loss in the network, we increases the channel capacity of the bottleneck structure in the network, and introduces the group convolution structure to optimize the network performance. Due to the complexity of the image background, we proposes a road plant image classification algorithm based on a priori segmentation by training the binary classification segmentation model of plants and background through transfer learning. This makes the classification model pay more attention to the area of road plants in the image and improves the classification accuracy by 5.16%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Confusan: A Unified Cross-Modal Retrieval Framework with Contextual Fusion and Sparse Alignment

SSRN

引用

SSRN 2024年

作者： Pan, Zhengxin Wang, Haishuai Bu, Jiajun Lin, Hui Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University Hangzhou310013 China Department of General Surgery Sir Run-Run Shaw Hospital School of Medicine Zhejiang University Hangzhou310013 China

Understanding both natural language and visual content is crucial for advancing artificial intelligence. Over the past decades, significant progress has been made in fields like computer Vision (CV) and Natural Language Processing (NLP). Recently, attention has shifted towards combining these domains to bridge the gap between vision and language. This paper focuses on the foundational task of cross-modal retrieval, which involves finding semantically consistent images or videos based on textual queries and vice versa. One of the primary challenges in this endeavor is reconciling the abstract nature of language with the vividness of visual content, known as the semantic gap. Traditional methods like Visual Semantic Embedding (VSE) encode images and captions into a common space for retrieval. Still, they often struggle with the ambiguity stemming from multiple descriptions for a single image or video. To address these issues, various techniques have been proposed, such as granular matching paradigms like SCAN and ProST. However, existing approaches frequently overlook intra-modality relationships and the differences between image-text and video-text retrieval tasks. To overcome these limitations, we introduce a unified framework called ConFuSAN (Contextual Fusion and Sparse Alignment Network), which handles both image-text and video-text retrieval tasks. The framework comprises three modules: the representation module, the fusion module for context-awareness, and the alignment module for similarity calculation. Specifically, to address the structural differences between images and videos, ConFuSAN leverages techniques like Graph Convolutional Networks (GCN) for images and transformer encoders for videos in the fusion module. To precisely measure semantic similarity, ConFuSAN utilizes the sparsemax operation for sparse alignment in the alignment module. Additionally, a new contrastive learning pipeline named Mix loss is introduced to train ConFuSAN effectively. Compreh

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Homophily-enhanced Structure Learning for Graph Clustering

arXiv

引用

arXiv 2023年

作者： Gu, Ming Yang, Gaoming Zhou, Sheng Ma, Ning Chen, Jiawei Tan, Qiaoyu Liu, Meihan Bu, Jiajun College of Computer Science and Technology Zhejiang University China School of Software Technology Zhejiang University China Zhejiang Provincial Key Laboratory of Service Robot Zhejiang University China Department of Computer Science New York University Shanghai China

Graph clustering is a fundamental task in graph analysis, and recent advances in utilizing graph neural networks (GNNs) have shown impressive results. Despite the success of existing GNN-based graph clustering methods, they often overlook the quality of graph structure, which is inherent in real-world graphs due to their sparse and multifarious nature, leading to subpar performance. Graph structure learning allows refining the input graph by adding missing links and removing spurious connections. However, previous endeavors in graph structure learning have predominantly centered around supervised settings, and cannot be directly applied to our specific clustering tasks due to the absence of ground-truth labels. To bridge the gap, we propose a novel method called homophily-enhanced structure learning for graph clustering (HoLe). Our motivation stems from the observation that subtly enhancing the degree of homophily within the graph structure can significantly improve GNNs and clustering outcomes. To realize this objective, we develop two clustering-oriented structure learning modules, i.e., hierarchical correlation estimation and cluster-aware sparsification. The former module enables a more accurate estimation of pairwise node relationships by leveraging guidance from latent and clustering spaces, while the latter one generates a sparsified structure based on the similarity matrix and clustering assignments. Additionally, we devise a joint optimization approach alternating between training the homophily-enhanced structure learning and GNN-based clustering, thereby enforcing their reciprocal effects. Extensive experiments on seven benchmark datasets of various types and scales, across a range of clustering metrics, demonstrate the superiority of HoLe against state-of-the-art baselines. Copyright © 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

AdaDFKD: Exploring Adaptive Inter-Sample Relationship in Data-Free Knowledge Distillation

SSRN

引用

SSRN 2023年

作者： Li, Jingru Zhou, Sheng Li, Liangcheng Wang, Haishuai Bu, Jiajun Yu, Zhi College of Computer Science and Technology Zhejiang University Zheda Rd. Zhejiang Hangzhou310027 China Zhejiang Provincial Key Laboratory of Service Robot Zhejiang University Zheda Rd. Zhejiang Hangzhou310027 China

In scenarios like privacy protection or large-scale data transmission, Data-free knowledge distillation (DFKD) methods are proposed to learn Knowledge Distillation (KD) when the data is not accessible. They generate pseudo samples that distill the knowledge from a pretrained teacher model and then use them to train a small student model. Current approaches have limitations in effectively addressing the learning capacity of the student model and the inter-sample relationship among the generated pseudo samples during DFKD, leading to the bottleneck of efficiency and performance. In this research, we propose AdaDFKD to construct adaptive targets for the inter-sample relationship. We achieve this by generating targets from "easy-to-discriminate" samples to "hard-to-discriminate" samples as human does. AdaDFKD designs a relationship refinement module (R$^2$M) to optimize the generation process, wherein we learn a progressive conditional distribution of negative samples and maximize the log-likelihood of inter-sample similarity of pseduosamples. Theoretically, we discover that such design of AdaDFKD both minimize the divergence and maximize the mutual information between the distribution of teacher and student models. Experimental results demonstrate the superiority of our approach over state-of-the-art (SOTA) DFKD methods across various benchmarks, teacher-student pairs, and evaluation metrics, as well as well robustness and fast convergence. © 2023, 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

CPDG: A Contrastive Pre-Training Method for Dynamic Graph Neural Networks

arXiv

引用

arXiv 2023年

作者： Bei, Yuanchen Xu, Hao Zhou, Sheng Chi, Huixuan Wang, Haishuai Zhang, Mengdi Li, Zhao Bu, Jiajun Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science and Technology Zhejiang University China Meituan China School of Software Technology Zhejiang University China Institute of Computing Technology Chinese Academy of Science China

Dynamic graph data mining has gained popularity in recent years due to the rich information contained in dynamic graphs and their widespread use in the real world. Despite the advances in dynamic graph neural networks (DGNNs), the rich information and diverse downstream tasks have posed significant difficulties for the practical application of DGNNs in industrial scenarios. To this end, in this paper, we propose to address them by pre-training and present the Contrastive Pre-Training Method for Dynamic Graph Neural Networks (CPDG). CPDG tackles the challenges of pre-training for DGNNs, including generalization capability and long-short term modeling capability, through a flexible structural-temporal subgraph sampler along with structural-temporal contrastive pre-training schemes. Extensive experiments conducted on both large-scale research and industrial dynamic graph datasets show that CPDG outperforms existing methods in dynamic graph pre-training for various downstream tasks under three transfer settings. Copyright © 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

Image Search with Text Feedback by Deep Hierarchical Attention Mutual Information Maximization 21

Image Search with Text Feedback by Deep Hierarchical Attenti...

引用

29th ACM International Conference on Multimedia, MM 2021

作者： Gu, Chunbin Bu, Jiajun Zhang, Zhen Yu, Zhi Ma, Dongfang Wang, Wei Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University China Alibaba- Zhejiang University Joint Institute of Frontier Technologies China Zhejiang Provincial Key Laboratory of Service Robot School of Software Technology Ningbo Research Institute Zhejiang University China Institute of Marine Sensing and Networking Key Laboratory of Ocean Observation-Imaging Testbed of Zhejiang Province Zhejiang University China

ISBN: (纸本)9781450386517

Image retrieval with text feedback is an emerging research topic with the objective of integrating inputs from multiple modalities as queries. In this paper, queries contain a reference image plus text feedback that describes modifications between this image and the desired image. The existing work for this task mainly focuses on designing a new fusion network to compose the image and text. Still, little research pays attention to the modality gap caused by the inconsistent distribution of features from different modalities, which dramatically influences the feature fusion and similarity learning between queries and the desired image. We propose a Distribution-Aligned Text-based Image Retrieval (DATIR) model, which consists of attention mutual information maximization and hierarchical mutual information maximization, to bridge this gap by increasing non-linear statistic dependencies between representations of different modalities. More specifically, attention mutual information maximization narrows the modality gap between different input modalities by maximizing mutual information between the text representation and its semantically consistent representation captured from the reference image and the desired image by the difference transformer. For hierarchical mutual information maximization, it aligns distributions of features from the image modality and the fusion modality by estimating mutual information between a single-layer representation in the fusion network and the multi-level representations in the desired image encoder. Extensive experiments on three large-scale benchmark datasets demonstrate that we can bridge the modality gap between different modalities and achieve state-of-the-art retrieval performance. © 2021 ACM.

关键词： Image fusion

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：