检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第7期5卷 3393-3407页

作者： Gu, Jing Sun, Xinkai Feng, Jie Yang, Shuyuan Liu, Fang Jiao, Licheng Xidian University Key Lab of Intelligent Perception and Image Understanding of Ministry of Education Xi'an710071 China

Real-time image semantic segmentation (ISS) draws the attentions of more and more researchers as a basis of scene understanding, and it has been applied in many fields that need fast interaction and response, such as autonomous driving and robot control. Considering the loss of low-level spatial information with the deepening network layer, we propose a multiple resolutions detail enhancement network (MRDENet) in this article, which adequately extracts and utilizes accurate low-level detail information from original images with different resolutions. MRDENet consists of three light-weight branch subnetworks, and designs dense oblique connections between adjacent branches to preserve the different level effective features of previous branch. Furthermore, a new multilevel information aggregation (MIA) module is presented to effectively fuse the low-level detail features and the high-level semantic features of different branches by employing group convolution (group conv) and channel shuffle with low computation cost, thus ensuring that MRDENet could achieve a favorable tradeoff between segmentation precision with inference speed. The experimental results show that MRDENet achieves 73.1% mean intersection over union (mIoU) with 93 frames per second (FPS) on Cityscapes dataset, and 68.5% mIoU with 112 FPS on CamVid dataset, which indicates the performance of MRDENet is competitive with the state-of-art methods. © 2020 IEEE.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

Multiscale Representation Learning for image Classification: A Survey

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第1期4卷 23-43页

作者： Jiao, Licheng Gao, Jie Liu, Xu Liu, Fang Yang, Shuyuan Hou, Biao Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Xidian University Xi'an710071 China

Feature representation has been widely used and developed recently. Multiscale features have led to remarkable breakthroughs for representation learning process in many computer vision tasks. This paper aims to provide a comprehensive survey of the recent multiscale representation learning achievements in classification tasks. Multiscale representation learning methods can be divided into two broad categories (multiscale geometric analysis and multiscale networks). Eleven kinds of multiscale geometric tools and seven kinds of multiscale networks are introduced. Some corresponding fundamental subproblems of these two broad categories are also described, including some concepts in representation process, specific representation methods with multiscale geometric analysis, and multiscale representation design strategies for networks. Then, the correlation between these two broad categories is illustrated, including respective characteristics, combination strategies, and characteristics of optimal representation. Some datasets and evaluation results are included to verify the effectiveness of the multiscale representation learning. Eventually, conclusion and future work are given, covering four directions [a) Choice and fusion;b) Self-adaption;c) Structure;and d) Generalization and proof]. © 2022 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Peri-midFormer: Periodic Pyramid Transformer for Time Series Analysis 38

Peri-midFormer: Periodic Pyramid Transformer for Time Series...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Wu, Qiang Yao, Gechang Feng, Zhixi Yang, Shuyuan Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Xidian University China

Time series analysis finds wide applications in fields such as weather forecasting, anomaly detection, and behavior recognition. Previous methods attempted to model temporal variations directly using 1D time series. However, this has been quite challenging due to the discrete nature of data points in time series and the complexity of periodic variation. In terms of periodicity, taking weather and traffic data as an example, there are multi-periodic variations such as yearly, monthly, weekly, and daily, etc. In order to break through the limitations of the previous methods, we decouple the implied complex periodic variations into inclusion and overlap relationships among different level periodic components based on the observation of the multi-periodicity therein and its inclusion relationships. This explicitly represents the naturally occurring pyramid-like properties in time series, where the top level is the original time series and lower levels consist of periodic components with gradually shorter periods, which we call the periodic pyramid. To further extract complex temporal variations, we introduce self-attention mechanism into the periodic pyramid, capturing complex periodic relationships by computing attention between periodic components based on their inclusion, overlap, and adjacency relationships. Our proposed Peri-midFormer demonstrates outstanding performance in five mainstream time series analysis tasks, including short- and long-term forecasting, imputation, classification, and anomaly detection. The code is available at https://***/WuQiangXDU/Peri-midFormer. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Block Pruning and Collaborative Distillation for image Classification of Remote Sensing

Block Pruning and Collaborative Distillation for Image Class...

引用

2024 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2024

作者： Wang, Xiaokai Wang, Rongfang Jiao, Changzhe Niu, Yi Mu, Caihong Xidian Univerisity The Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Xi'an China

ISBN: (纸本)9798350360325

Convolutional Neural Networks (CNNs) have achieved remarkable performance in remote sensing image classification tasks. To address the issue of high model complexity, we propose a block-level pruning strategy based on the semantic similarity analysis that no fine-tuning is required during the pruning process. By employing this strategy, we effectively reduce the complexity of the model. Furthermore, to restore the overall performance of the pruned model, we propose a teacher-student collaborative distillation strategy that enables knowledge transfer through the collaboration of the original model and the dropped-blocks model to promote the performance of the compact pruned model. Experimental results demonstrate that our pruning and distillation strategies outperform other approaches, thereby achieving favorable performance while reducing model complexity. © 2024 IEEE.

关键词： blocks pruning image classification knowledge distillation light CNN remote sensing

来源：评论

学校读者我要写书评

暂无评论

Graph Representation Learning Meets Computer Vision: A Survey

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第1期4卷 2-22页

作者： Jiao, Licheng Chen, Jie Liu, Fang Yang, Shuyuan You, Chao Liu, Xu Li, Lingling Hou, Biao Key Lab. of Intelligent Perception and Image Understanding of the Ministry of Education of China International Research Center of Intelligent Perception and Computation School of Artificial Intelligence Xidian University Xi'an710071 China

A graph structure is a powerful mathematical abstraction, which can not only represent information about individuals but also capture the interactions between individuals for reasoning. Geometric modeling and relational inference based on graph data is a long-standing topic of interest in the computer vision community. In this article, we provide a systematic review of graph representation learning and its applications in computer vision. First, we sort out the evolution of representation learning on graphs, categorizing them into the nonneural network and neural network methods based on the way the nodes are encoded. Specifically, nonneural network methods, such as graph embedding and probabilistic graphical models, are introduced, and neural network methods, such as graph recurrent neural networks, graph convolutional networks, and variants of graph neural networks, are also presented. Then, we organize the applications of graph representation algorithms in various vision tasks (such as image classification, semantic segmentation, object detection, and tracking) for review and reference, and the typical graph construction approaches in computer vision are also summarized. Finally, on the background of biology and brain inspiration, we discuss the existing challenges and future directions of graph representation learning and computer vision. © 2022 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Mathematical model and simulated annealing algorithm for Chinese high school timetabling problems under the new curriculum innovation

引用

Frontiers of Computer Science 2021年第1期15卷 167-177页

作者： Xingxing HAO Jing LIU Yutong ZHANG Gustaph SANGA Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education Xidian UniversityXi’an 710071China

As the first attempt,this paper proposes a model for the Chinese high school timetabling problems(CHSTPs)under the new curriculum innovation which was launched in 2011 by the Chine6e *** 10 the new our riculum innovation,students in high school can choose subjects that they are interested in instead of being forced to select one of the two study directions,namely,Science and Liberal ***,they also need to attend compulsory subjects as *** are student-oriented and involve more student constraints that make them more complex than the typi-cal"Class-Teacher model",in which the element"Teacher"is the primary *** this paper,we first describe in detail the mathematical model of CHSTPs and then design a new two-part representation for the candidate *** on the new representation,we adopt a two-phase simulated annealing(SA)algorithm to solve CHSTPs.A total number of 45 synthetic instances with different amounts of classes,teachers,and levels of student constraints are generated and used to ilustrate the characteristics of the CHSTP model and the effectiveness of the designed representation and ***,we apply the proposed model,the designed two-part representation and the two-phase SA on10 real high schools.

关键词： timetabling Chinese high school timetabling problem simulated annealing two-part representation

来源：评论

学校读者我要写书评

暂无评论

Radar antenna scanning type identification based on the fusion of multiple temporal features 8

Radar antenna scanning type identification based on the fusi...

引用

2023 8th International Seminar on Computer Technology, Mechanical and Electrical Engineering, ISCME 2023

作者： Xu, Caijin Tian, Shunli Zhang, Xiangrong Zhang, Yifang Wang, Guanchun The 29th Research Institute of CETC Chengdu China Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education International Research Center for Intelligent Perception and Computation Xidian University Xi'an China

Identifying the antenna scanning type (AST) of radar signal aims to deeply analyze the parameters of radar waveform and accurately judge the AST of the radar signal. Traditional methods rely heavily on domain priors and expert experience to set classification thresholds, which introduces human errors. Moreover, the generalization and anti-noise interference abilities are relatively weak, and it is difficult to deal with complex battlefield environments. The model based on the convolutional neural network (CNN) is limited by the receptive field of the convolution kernel, which makes the model unable to make full use of the global information of the signal. To fully exploit the global timing characteristics of radar signals, we propose a radar AST recognition method based on the fusion of multiple temporal features. Specifically, for the time series characteristics of the radar antenna scanning signal, a 1D CNN branch is first built to extract its short time series features. Given the limited receptive field of the convolutional network and the inability to fully consider the overall characteristics of the radar signal, we propose a transformer network branch to extract the global timing features fully. The recognition of radar AST based on multi-time series feature fusion can fully model the local and global sequence attributes, thereby improving the cognitive recognition ability of radar signals. Our method attains state-of-the-art results based on experimental findings. © 2024 Institute of Physics Publishing. All rights reserved.

关键词： Scanning antennas

来源：评论

学校读者我要写书评

暂无评论

The New Generation Brain-Inspired Sparse Learning: A Comprehensive Survey

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2022年第6期3卷 887-907页

作者： Jiao, Licheng Yang, Yuting Liu, Fang Yang, Shuyuan Hou, Biao Xidian University Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education of China School of Artificial Intelligence Xi'an710071 China

In recent years, the enormous demand for computing resources resulting from massive data and complex network models has become the limitation of deep learning. In the large-scale problems with massive samples and ultrahigh feature dimensions, sparsity has gradually drawn much attention from academia and the industrial field. In this article, the new generation of brain-inspired sparse learning is reviewed comprehensively. First, sparse cognition learning is introduced from the visual biology mechanism to modeling for the natural image. Second, the sparse representation algorithms are summarized to sort out the research progress of sparse learning. Third, the relevant research on sparse feature selection learning is reviewed. Then, the sparse deep networks and applications are summed up. Last but not least, ten public issues and challenges of sparse learning are discussed. By investigating the development process of sparse learning, this article summarizes the advantages, disadvantages, limitations, and future research directions of the algorithm, which can help readers conduct further study. © 2020 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

DELVING INTO SEMANTIC SCALE IMBALANCE

DELVING INTO SEMANTIC SCALE IMBALANCE

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Ma, Yanbiao Jiao, Licheng Liu, Fang Li, Yuxin Yang, Shuyuan Liu, Xu Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education School of Artificial Intelligence Xidian University Xi'an710071 China

Model bias triggered by long-tailed data has been widely studied. However, measure based on the number of samples cannot explicate three phenomena simultaneously: (1) Given enough data, the classification performance gain is marginal with additional samples. (2) Classification performance decays precipitously as the number of training samples decreases when there is insufficient data. (3) Model trained on sample-balanced datasets still has different biases for different classes. In this work, we define and quantify the semantic scale of classes, which is used to measure the feature diversity of classes. It is exciting to find experimentally that there is a marginal effect of semantic scale, which perfectly describes the first two phenomena. Further, the quantitative measurement of semantic scale imbalance is proposed, which can accurately reflect model bias on multiple datasets, even on sample-balanced data, revealing a novel perspective for the study of class imbalance. Due to the prevalence of semantic scale imbalance, we propose semantic-scale-balanced learning, including a general loss improvement scheme and a dynamic re-weighting training framework that overcomes the challenge of calculating semantic scales in real-time during iterations. Comprehensive experiments show that dynamic semantic-scale-balanced learning consistently enables the model to perform superiorly on large-scale long-tailed and non-long-tailed natural and medical datasets, which is a good starting point for mitigating the prevalent but unnoticed model bias. Furthermore, we look ahead to future challenges in the field. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

VAE-based Multi-domain Feature Alignment and Generative Network for Few-Shot Radar Models Identification 3

VAE-based Multi-domain Feature Alignment and Generative Netw...

引用

3rd International Conference on intelligent Power and Systems, ICIPS 2023

作者： Zhang, Yifang Fan, Xiyu Zhang, Xiangrong Xu, Caijin Wang, Guanchun The 29th Research Institute of CETC Chengdu China Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education International Research Center for Intelligent Perception and Computation Xidian University Xi’an China

ISBN: (纸本)9798350328691

In the field of electronic countermeasures reconnaissance, it is generally difficult to obtain sufficient target radar pulse information to realize radar model identification, whether it is traditional machine learning or deep learning methods are prone to fall into the problem that the model is easy to be overfitted with the amount of data is too small, so the radar model identification based on the few-shot learning is proposed. Existing few-shot learning methods focus on extracting features with generalizability, while ignoring the key problem of overfitting. To solve the problem of declining classification accuracy caused by overfitting, this paper combines the training samples with the radar model expert's knowledge, and generates new samples to achieve the transformation of the radar model identification problem under few-shot conditions into a conventional classification problem by means of the dual-driven approach of knowledge and data. Specifically, to address the problem that the semantic features of expert knowledge and the category features of radar models cannot be used at the same time, we design a multidomain feature alignment model for radar models based on the probabilistic generative model and construct a feature library of radar models composed of expert knowledge and category features. In addition, for the problem of insufficient samples, we build a multi-branch intra-class feature distribution learning network to learn the intra-class feature distribution of the samples, and expand the samples by combining semantic and category features. Experimental results show that our approach achieves state-of-the-art results. ©2023 IEEE.

关键词： Semantics

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：