检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Jin, Hailong Li, Huiying College of Computer Science and Technology Jilin Province Changchun China Key Laboratory of Symbol Computation and Knowledge Engineering Jilin University Changchun130012 China

Few-shot semantic segmentation aims to segment new categories with only a small number of annotated images. Previous methods mainly focused on exploiting the pixel-level correlation between the support image and the query image, combined with attention-based methods, resulting in significant advancements. In this paper, we introduce a new perspective to enhance few-shot segmentation. We identify that utilizing the bilinear interpolation method to downsample the mask leads to the loss of fine-grained information from the target features. To address this issue, we propose a Smooth Downsampling Mask (SDM) method. The SDM method is designed to retain more effective target semantic features by employing a cascaded downsampling approach with a smooth kernel for mask processing. Additionally, we propose a label smoothing loss to further enhance the performance, which provides direct guidance for low-resolution feature map optimization. Notably, our proposed method involves no additional learnable parameters and introduces only a small amount of extra computation. To validate the effectiveness of our approach, we conduct extensive experiments on three public benchmarks, PASCAL-$5^i$, COCO-$20^i$, and FSS-$1000$, and achieve considerable improvements. © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Multi-focus image fusion based on fully convolutional networks

引用

Frontiers of Information Technology & Electronic engineering 2020年第7期21卷 1019-1033页

作者： Rui GUO Xuan-jing SHEN Xiao-yu DONG Xiao-li ZHANG Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin UniversityChangchun 130012China College of Computer Science and Technology Jilin UniversityChangchun 130012China

We propose a multi-focus image fusion method, in which a fully convolutional network for focus detection(FD-FCN) is constructed. To obtain more precise focus detection maps, we propose to add skip layers in the network to make both detailed and abstract visual information available when using FD-FCN to generate maps. A new training dataset for the proposed network is constructed based on dataset CIFAR-10. The image fusion algorithm using FD-FCN contains three steps: focus maps are obtained using FD-FCN, decision map generation occurs by applying a morphological process on the focus maps, and image fusion occurs using a decision map. We carry out several sets of experiments, and both subjective and objective assessments demonstrate the superiority of the proposed fusion method to state-of-the-art algorithms.

关键词： Multi-focus image fusion Fully convolutional networks Skip layer Performance evaluation

来源：评论

学校读者我要写书评

暂无评论

Learning Stable Task-Level Manifold for Few-Shot Learning

Learning Stable Task-Level Manifold for Few-Shot Learning

引用

2023 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2023

作者： Yu, Siyi Luo, Wei Li, Gang Yang, Bo Jilin University College of Computer Science and Technology China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education China Deakin University School of Information Technology Geelong Australia

ISBN: (纸本)9798350382204

Few-shot learning (FSL) aims to learn to new concepts based on very limited data. One of the main challenges in FSL is the use of pretrained embeddings whose dimension is too high for the small sample size. While the large dimensionality helps capture diverse features in the training example, not all the features are relevant to the task at hand. Such task-irrelevant features from pre-trained embeddings can negatively impact the performance of the FSL model. To address this challenge, we propose a simple yet effective way to learn task-level manifolds that explicitly eliminate the negative effect of nuisance features. One key novelty of our approach is to address class imbalance in the training data by injecting supervised information through key virtual samples, which we named Manifold Support Points. Empirically, we demonstrate that the stability of the learnt task-level manifolds and their effectiveness in challenging tasks in FSL. Our approach shows competitive performance on several benchmark datasets, including tieredImageNet and CUB. © 2023 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

An algorithm of sensor optimization in controlled discrete event systems

引用

Journal of computational Information Systems 2014年第20期10卷 8677-8684页

作者： Hao, Shuang Ouyang, Dantong Li, Lin Zhang, Liming Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China

Sensor optimization is the problem of minimizing sensor activation in a controlled discrete event system. During the evolutionary process, the available resources are supposed to be limited. Therefore, sensors are activated by the agent when it is necessary. Sensor activation policies are the functions that determine which sensors are to be activated. One policy is considered to minimal, if any strictly less activation decided by the agent satisfies the feasibility. In this paper, a new algorithm is proposed to compute the minimal sensor activation policy. The algorithm, based on the operation of Reverse Change and the property of the Label-reached, calculates the minimal solution of sensor activation and achieves a lower complexity of computation relatively.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

Medical Image Fusion Based on Sparse Representation and Guided Filtering 4

Medical Image Fusion Based on Sparse Representation and Guid...

引用

2019 4th Annual International Conference on Information System and Artificial Intelligence, ISAI 2019

作者： Huang, Sa Chu, Guangyu Fei, Yifan Zhang, Xiaoli Wang, Hailiang Department of Radiology Second Hospital Jilin University Changchun Jilin130041 China Key Laboratory of Symbol Computation and Knowledge Engineer of Ministry of Education Jilin University Changchun130012 China Department of Neurosurgery Second Hospital Jilin University Changchun Jilin130041 China

In this paper, we proposed a medical image fusion algorithm based on sparse representation and guided filtering. One of attractive features in the algorithm is that it can preserve the structural information of structural image and color information of functional image. We use a sparse representation in low frequency, initialize the dictionary by using DCT transform, and train the dictionary with each input source image as a training example. It not only ensures time complexity, but also ensures that the low-frequency fusion rules are adaptive. At high frequencies, we use the method of guided filtering to extract structural information from high-frequency images, and use the injection method to fuse high-frequency sub-bands to ensure the validity and richness of structural information. Experimental results show that the proposed fusion algorithm is superior to comparative algorithms in terms of subjective and objective evaluation methods. © 2019 Published under licence by IOP Publishing Ltd.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

A Sarsa() algorithm based on double-layer fuzzy reasoning

引用

Mathematical Problems in engineering 2013年 2013卷

作者： Liu, Quan Mu, Xiang Huang, Wei Fu, Qiming Zhang, Yonggang School of Computer Science and Technology Soochow University Suzhou Jiangsu 215006 China Key Laboratory of Symbol Computation and Knowledge Engineering Jilin University Ministry of Education Changchun 130012 China

Solving reinforcement learning problems in continuous space with function approximation is currently a research hotspot of machine learning. When dealing with the continuous space problems, the classic Q-iteration algorithms based on lookup table or function approximation converge slowly and are difficult to derive a continuous policy. To overcome the above weaknesses, we propose an algorithm named DFR-Sarsa() based on double-layer fuzzy reasoning and prove its convergence. In this algorithm, the first reasoning layer uses fuzzy sets of state to compute continuous actions;the second reasoning layer uses fuzzy sets of action to compute the components of Q-value. Then, these two fuzzy layers are combined to compute the Q-value function of continuous action space. Besides, this algorithm utilizes the membership degrees of activation rules in the two fuzzy reasoning layers to update the eligibility traces. Applying DFR-Sarsa() to the Mountain Car and Cart-pole Balancing problems, experimental results show that the algorithm not only can be used to get a continuous action policy, but also has a better convergence performance. © 2013 Quan Liu et al.

关键词： Fuzzy sets

来源：评论

学校读者我要写书评

暂无评论

Improving the Recommendation of Collaborative Filtering by Fusing Trust Network

Improving the Recommendation of Collaborative Filtering by F...

引用

International Conference on computational Intelligence and Security

作者： Bo Yang Pengfei Zhao Shuqiu Ping Jing Huang School of Computer Science and Technology Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education Jilin University Changchun P.R.China

To accurately and actively provide users with their potentially interested information or services is the main task of a recommender system. Collaborative filtering is one of the most widely adopted recommender methods, whereas it is suffering the issue of sparse rating data that will severely degenerate the quality of recommendations. To address this issue, the article proposes a novel method, named the FTRA (Fusing Trust and Ratings), trying to improve the performance of collaborative filtering recommendation by means of elaborately integrating twofold sparse information, i.e., the conventional rating data given by users and the social trust network among the same users. The performance of FTRA is rigorously validated by comparing it with six representative methods on a real-world dataset. The experimental results show that the FTRA outperforms all other competitors in terms of both precision and recall. More importantly, our work suggests that the strategy of augmenting sparse rating data by fusing trust networks does significantly improve the quality of conventional collaborative filtering recommendation, and its quality could be further improved by means of designing more effective integrating schemes.

关键词： Collaboration Recommender systems Measurement Social network services Web sites Educational institutions

来源：评论

学校读者我要写书评

暂无评论

Robust and efficient annotation based on ontology evolution for deep web data

引用

Journal of Computers 2011年第10期6卷 2029-2036页

作者： Chen, Kerui Zuo, Wanli Zhang, Fan He, Fengling Chen, Yongheng Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education College of Computer Science and Technology Jilin University Changchun 130012 China College of Information Engineering Zhongzhou University Zhengzhou 450044 China

Among those researches in Deep Web, compared to research of data extraction which is more mature, the research of data annotation is still at its preliminary stage. Currently, although the approach of applying ontology in data annotating has been approved by most researchers, there are many weaknesses existed, such as the complexity of the ontology, as well as the limitation on static ontology's ability to annotate new pages. Respond to those problems, this paper proposes a robust, highly efficient data annotation method based on ontology evolution. It needs to be noticed that this paper defines a simpler ontology which can improve annotating efficiency significantly. Experiments indicate that this method could improve the accuracy and efficiency of data annotation. © 2011 ACADEMY PUBLISHER.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Geometric constraint solving using PACAO

引用

Journal of computational Information Systems 2007年第2期3卷 423-428页

作者： Yuan, Hua Li, Wenhui Yi, Rongqin Key Laboratory of Symbol Computation and Knowledge Engineering College of Computer Science and Technology Jilin University Changchun 130012 China School of Computer Science and Engineering Changchun University of Technology Changchun 130012 China

Previous methods of volume rendering are very slow and thus impractical. We present volume rendering based on marching cubes iso-surfacing and transfer function. For an iso-surface, we divide the voxels into logical cubes according to a predefined threshold value, the tangent planes and normal vectors at each voxel are calculated and the normal vectors are orientated to the outside of surface based on wide first searching (WFS), and the 3D surface model is then obtained using marching cubes. Transfer function is used to specify the optical properties for volume rendering technology. We employ a 2D function. The end-user interacts with a set of direct manipulation widgets (triangles and rectangles). Each widget precisely corresponds to a different material and widgets are blended automatically to compute an overall transfer function. Compared to traditional techniques, the overall specification process takes a fraction of the time.

关键词： Volume rendering

来源：评论

学校读者我要写书评

暂无评论

Acupuncture and Tuina knowledge Graph for Ancient Literature of Traditional Chinese Medicine

Acupuncture and Tuina Knowledge Graph for Ancient Literature...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Xiaosong Han Xiaoran Li Yanchun Liang Xinghao Wang Dong Xu Renchu Guan Key Laboratory for Symbol Computation and Knowledge Engineering of National Education Ministry College of Computer Science and Technology Jilin University Changchun China Key Laboratory for Symbol Computation and Knowledge Engineering of National Education Ministry College of Software Jilin University Changchun China Christopher S. Bond Life Sciences Center University of Missouri Columbia USA

ISBN: (纸本)9781665429825

The Traditional Chinese Medicine’s ancient literature recorded the massive medical theories and abundant medical experiences. To better understand and utilize, the knowledge from the literature, the Acupuncture and Tuina knowledge Graph is proposed in this paper. Meanwhile, a deep learning network is established for acupuncture and tuina-related entity recognition and entity-relationship extraction. Finally, the trained network is able to reach an 82%+ F1-score for NER and 70%+ F1-score for relationship extraction.

关键词： Deep learning Conferences Labeling Bioinformatics

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：