检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Qian, Biao Wang, Yang Yin, Hongzhi Hong, Richang Wang, Meng Key Laboratory of Knowledge Engineering with Big Data Ministry of Education School of Computer Science and Information Engineering Hefei University of Technology China The University of Queensland

Online knowledge Distillation (OKD) improves the involved models by reciprocally exploiting the difference between teacher and student. Several crucial bottlenecks over the gap between them — e.g., Why and when does a large gap harm the performance, especially for student? How to quantify the gap between teacher and student? — have received limited formal study. In this paper, we propose Switchable Online knowledge Distillation (SwitOKD), to answer these questions. Instead of focusing on the accuracy gap at test phase by the existing arts, the core idea of SwitOKD is to adaptively calibrate the gap at training phase, namely distillation gap, via a switching strategy between two modes — expert mode (pause the teacher while keep the student learning) and learning mode (restart the teacher). To possess an appropriate distillation gap, we further devise an adaptive switching threshold, which provides a formal criterion as to when to switch to learning mode or expert mode, and thus improves the student’s performance. Meanwhile, the teacher benefits from our adaptive switching threshold and keeps basically on a par with other online arts. We further extend SwitOKD to multiple networks with two basis topologies. Finally, extensive experiments and analysis validate the merits of SwitOKD for classification over the state-of-the-arts. Our code is available at https://***/hfutqian/SwitOKD. Copyright © 2022, The Authors. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Multi-source Multi-label Feature Selection

Multi-source Multi-label Feature Selection

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Xiulan Yuan Xuegang Hu Peipei Li Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) Hefei University of Technology School of Computer Science and Information Engineering Hefei University of Technology Hefei City China Anhui Province Key Laboratory of Industry Safety and Emergency Technology Hefei City China

Feature selection for multi-source multi-label data has attracted much attention, because there are a lot of scenarios that produce multiple source data with multi-labels in the real-world applications, which aggravates the problems of dimensional disaster and the label skewness. However, most of existing multi-source feature selection methods miss the multi-label issue while existing multi-label feature selection methods can not select the optimal feature set in the multi-source environment. Motivated by this, we propose a novel feature selection method, called MSMLFS. To be specific, the Inf-FS algorithm is firstly introduced to handle multi-label feature selection for each data source, which considers the label weight in the feature selection. Secondly, the over-sampling mechanism and the inter-source feature fusion method are used to handle the label skewness of multi-label data and the feature selection in multiple sources respectively. Finally, extensive experiments conducted on synthetic and real-world multi-source multi-label data sets demonstrate that the proposed method outperforms several state-of-the-art multi-source or multi-label feature selection methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TREC: transient redundancy elimination-based convolution 22

TREC: transient redundancy elimination-based convolution

引用

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

作者： Jiawei Guan Feng Zhang Jiesong Liu Hsin-Hsuan Sung Ruofan Wu Xiaoyong Du Xipeng Shen Key Laboratory of Data Engineering and Knowledge Engineering (MOE) and School of Information Renmin University of China Computer Science Department North Carolina State University

ISBN: (纸本)9781713871088

The intensive computations in convolutional neural networks (CNNs) pose challenges for resource-constrained devices; eliminating redundant computations from convolution is essential. This paper gives a principled method to detect and avoid transient redundancy, a type of redundancy existing in input data or activation maps and hence changing across inferences. By introducing a new form of convolution (TREC), this new method makes transient redundancy detection and avoidance an inherent part of the CNN architecture, and the determination of the best configurations for redundancy elimination part of CNN backward propagation. We provide a rigorous proof of the robustness and convergence of TREC-equipped CNNs. TREC removes over 96% computations and achieves 3.51× average speedups on microcontrollers with minimal (about 0.7%) accuracy loss.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semantic SLAM Based on Compensated Segmentation and Geometric Constraints in Dynamic Environments

Semantic SLAM Based on Compensated Segmentation and Geometri...

引用

Artificial Intelligence Technology (ACAIT), Asian Conference on

作者： Baofu Fang Shuai Zhou Hao Wang School of Computer Science and Information Engineering Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data(Hefei University of Technology) Hefei China

Most of the existing slam algorithms are designed based on the assumption of a static environment, this strong assumption limits the practical application of most slam systems. The main reason is that moving objects will cause feature mismatch in the pose estimation process, which in turn affects the accuracy of localization and mapping. In this paper, we propose a SLAM algorithm in a dynamic environment. First, we use the BlendMask network to detect potential moving objects to generate masks for dynamic objects. The geometrically constrained joint optical flow method is used to detect dynamic feature points. Secondly, aiming at the failure of semantic segmentation network segmentation, a missed detection compensation algorithm based on the invariance of adjacent frame speed is proposed. Finally, a keyframe selection strategy is proposed to construct a semantic octree graph containing only static objects. We evaluate our algorithm on TUM RGB-D and real scene datasets. The experimental results show that the algorithm has high accuracy and real-time performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RGB-D SLAM Method Based on Feature Association in Dynamic Environment

RGB-D SLAM Method Based on Feature Association in Dynamic En...

引用

Artificial Intelligence Technology (ACAIT), Asian Conference on

作者： Baofu Fang Hao Wang School of Computer Science and Information Engineering Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data (Hefei University of Technology) Hefei China

Simultaneous localization and mapping (SLAM) is one of the current research hotspots. However, in visual SLAM for dynamic environments, inaccurate detection of object motion states and incomplete dynamic region culling will lead to large localization errors. To address these issues, this paper proposes an RGB-D SLAM method based on feature association. The method has strongly correlated features in time and space according to the input image sequence. Using the moving probability of the feature points in the previous frame, the movement of the feature points in the current frame is calculated in combination with the dynamic corner points screened in the current frame. Then, the motion state of the object is determined according to the proportion of different feature points. Then combined with semantic information and object depth information, the fast search method is used to obtain accurate dynamic regions. Finally, the selected effective feature points are used to estimate the camera pose and establish a static map of the environment. This paper evaluates the robustness and accuracy of our method on the TUM dataset and real environment, and the results show that our method can significantly improve the system tracking effect and reduce the system tracking error compared with other SLAM methods in dynamic environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning from Semi-Factuals: A Debiased and Semantic-Aware Framework for Generalized Relation Discovery

arXiv

引用

arXiv 2024年

作者： Wang, Jiaxin Zhang, Lingling Liu, Jun Guo, Tianlin Wu, Wenjun The School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an710049 China The Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University Shaanxi Xi’an710049 China National Engineering Lab for Big Data Analytics Xi’an Jiaotong University Shaanxi Xi’an710049 China

We introduce a novel task, called Generalized Relation Discovery (GRD), for open-world relation extraction. GRD aims to identify unlabeled instances in existing pre-defined relations or discover novel relations by assigning instances to clusters as well as providing specific meanings for these clusters. The key challenges of GRD are how to mitigate the serious model biases caused by labeled pre-defined relations to learn effective relational representations and how to determine the specific semantics of novel relations during classifying or clustering unlabeled instances. We then propose a novel framework, SFGRD, for this task to solve the above issues by learning from semi-factuals in two stages. The first stage is semi-factual generation implemented by a tri-view debiased relation representation module, in which we take each original sentence as the main view and design two debiased views to generate semi-factual examples for this sentence. The second stage is semi-factual thinking executed by a dual-space tri-view collaborative relation learning module, where we design a cluster-semantic space and a class-index space to learn relational semantics and relation label indices, respectively. In addition, we devise alignment and selection strategies to integrate two spaces and establish a self-supervised learning loop for unlabeled data by doing semi-factual thinking across three views. Extensive experimental results show that SFGRD surpasses state-of-the-art models in terms of accuracy by 2.36% ∼5.78% and cosine similarity by 32.19%∼ 84.45% for relation label index and relation semantic quality, respectively. To the best of our knowledge, we are the first to exploit the efficacy of semi-factuals in relation extraction. Copyright © 2024, The Authors. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Reconfigurable Digital Twin from the Perspective of Smart Manufacturing Systems in Industry 4.0/5.0

Reconfigurable Digital Twin from the Perspective of Smart Ma...

引用

2024 International Conference on Intelligent Systems and Robotics, CISR 2024

作者： Mo, Guangyu Sun, Yuan Huang, Sihan Gao, Feng Huang, Jintang Lai, Lijuan Wang, Guoxin Yan, Yan School of Mechanical Engineering Beijing Institute of Technology Beijing100081 China Beijing Aerospace Times Optical-Electronic Technology Co. Ltd. Beijing100094 China Key Laboratory of Industry Knowledge & Data Fusion Technology and Application Ministry of Industry and Information Technology Beijing Institute of Technology Beijing100081 China China Academy of Aerospace Electronic Technology Beijing100094 China School of Industrial Automation Beijing Institute of Technology Zhuhai519088 China

In industry 4.0/5.0, Smart manufacturing systems are typically complex systems that can be adjusted to deal with demand fluctuation through reconfigurable software/hardware. The emergence of digital twin as enabler technology can promote the operation efficiency of smart manufacturing systems. However, the modelling processes of digital twin of smart manufacturing systems is inefficient due to their complicated structures in general. Besides, the frequent reconfiguration of smart manufacturing systems and the differentiation among smart manufacturing systems will increase the burden of digital twin modelling. Therefore, a reconfigurable modelling method for digital twin of smart manufacturing systems is proposed in this paper. First, a reconfigurable modelling framework based on open architecture is proposed to provide basic model scenario for digital twin of smart manufacturing systems. Second, the reconfiguration of digital twin is elaborated from three dimensions, including reconfigurable virtual model, reconfigurable mapping, and reconfigurable scene. Finally, a case study is given to demonstrate the effectiveness of the proposed method. © Published under licence by IOP Publishing Ltd.

关键词： Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

Temporal Based Instance-Level Fusion for Video Object Detection 17th

Temporal Based Instance-Level Fusion for Video Object Detect...

引用

17th Chinese Intelligent Systems Conference, CISC 2021

作者： Cai, Qiang Kang, Nan Li, Haisheng Cao, Jian Liu, Wenqing Wan, Ruyi School of Computer Science and Engineering Beijing Technology and Business University Beijing100048 China Beijing Key Laboratory of Big Data Technology for Food Safety Beijing China National Engineering Laboratory For Agri-product Quality Traceability Beijing China Beijing zhiyunda Technology Co. Ltd. Beijing100085 China

ISBN: (纸本)9789811663277

Static image object detection is naively applied to videos in a frame-by-frame approach, and the prediction is often temporally inconsistent. Enhancement of every selected frame becomes a typical solution by aggregating temporal nearby frames features. But the solutions above just use features in pixel-level. In this work, we emphasize the importance of the temporal sequential relationship, which considers calibrating instance-level features on time line, and combining the pixel-level features with the calibrated instance-level features finally. In order to prevent mismatch in video boundary, pixel-level re-fusion is remained to amend above issue. Although the instance-level fusion gains more global motion cues for the pixel-level calibration’s sake of robustness to occlusion, using temporal information can further improve the robustness. Experiments on the large-scale ImageNet VID dataset state the improvement of the our work for object detection in videos. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Charge Prediction with Multi-grained Features and Mutual Information 20

Few-Shot Charge Prediction with Multi-grained Features and M...

引用

20th China National Conference on Computational Linguistics, CCL 2021

作者： Zhang, Han Dou, Zhicheng Zhu, Yutao Wen, Jirong School of Information Renmin University of China Beijing China Gaoling School of Artificial Intelligence Renmin University of China Beijing China Université de Montréal Montreal Canada Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China Key Laboratory of Data Engineering and Knowledge Engineering MOE Beijing China

ISBN: (纸本)9783030841850

Charge prediction aims to predict the final charge for a case according to its fact description and plays an important role in legal assistance systems. With deep learning based methods, prediction on high-frequency charges has achieved promising results but that on few-shot charges is still challenging. In this work, we propose a framework with multi-grained features and mutual information for few-shot charge prediction. Specifically, we extract coarse- and fine-grained features to enhance the model’s capability on representation, based on which the few-shot charges can be better distinguished. Furthermore, we propose a loss function based on mutual information. This loss function leverages the prior distribution of the charges to tune their weights, so the few-shot charges can contribute more on model optimization. Experimental results on several datasets demonstrate the effectiveness and robustness of our method. Besides, our method can work well on tiny datasets and has better efficiency in the training, which provides better applicability in real scenarios. © 2021, Springer Nature Switzerland AG.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Personalized Recommendation Based on Entity Attributes and Graph Features 12

Personalized Recommendation Based on Entity Attributes and G...

引用

12th IEEE International Conference on Big knowledge, ICBK 2021

作者： Zhu, Yi Dong, Bingbing Sha, Zhiqing Yangzhou University School of Information Engineering Yangzhou China Key Laboratory of Knowledge Engineering With Big Data Hefei University of Technology Ministry of Education China School of Computer Science and Information Engineering Hefei University of Technology Hefei China Institute of Big Knowledge Science Hefei University of Technology Hefei China

ISBN: (纸本)9781665438582

With the rapid increase in the amount of website data, it has been a more difficult task for users to get the infor-mation they are interested in. Personalized recommendation is an important bridge to find the information which users really need on the website. Many recent studies have introduced additional attribute information about users and/or items to the rating matrix for alleviating the problem of data sparsity. In order to make full use of the attribute information and scoring matrix, deep learning based recommendation methods are proposed, especially the autoencoder model has attracted much attention because of its strong ability to learn hidden features. However, most of the existing autoencoder- based models require that the dimension of the input layer is equal to the dimension of the output layer, which may increase model complexity and certain information loss when using attribute information. In addition, as users' awareness of privacy protection increases, user attribute information is difficult to obtain. To address the above problems, in this paper, we propose a hybrid personalized recommendation model, which uses a semi-autoencoder to jointly embed the item's score vector and internal graph features (short for Co-Agpre). Specifically, we regard the user-item historical interaction matrix as a bipartite graph, and the Laplacian of the user-item co-occurrence graph is utilized to obtain the graph features of the item for solving the problem of sparse attributes. Then a semi-autoencoder is introduced to learn the hidden features of the item and perform rating prediction. The proposed model can flexibly use information from different sources to reduce the complexity of the model. Experiments on two real-world datasets demonstrate the effectiveness of the proposed Co-Agpre compared with state-of-the-art methods. © 2021 IEEE.

关键词： Websites

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：