检索结果-内蒙古大学图书馆

11th International Conference on Bio-inspired Computing – Theories and Applications, BIC-TA 2016

作者： Wang, Zhao Gong, Maoguo Xie, Tian Key Laboratory of Intelligent Perception and Image Understanding Xidian University Xi’an China

ISBN: (纸本)9789811036101

For multiobjective optimization problems with large-scale decision variables, it is difficult to optimize all the decision variables at the same time. With the divide and conquer strategy, the decision variable analysis technique is applied to analyze the variables’ property and divide the variables into subcomponents. However it takes too much time to analyze a large-scale set of decision variables. In this paper, we propose a distributed decision variable analysis algorithm. The proposed algorithm divides all the variables into subcomponents assigns each of them to a computation node. We test the proposed algorithm on some popular multiobjcetive optimization problems with large-scale decision variables and the results show that the proposed algorithm can boost the analysis process effectively. © Springer Nature Singapore Pte Ltd. 2016.

关键词： Distributed computer systems

来源：评论

学校读者我要写书评

暂无评论

Generalization-aware Remote Sensing Change Detection via Domain-agnostic Learning

arXiv

引用

arXiv 2025年

作者： Zang, Qi Wang, Shuang Zhao, Dong Quan, Dou Hu, Yang Jiao, Licheng Yang, Zhi Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Xidian University Xi’an710071 China DFH Satellite Co. Ltd CAST Beijing100080 China

Change detection has essential significance for the region’s development, in which pseudo-changes between bitemporal images induced by imaging environmental factors are key challenges. Existing transformation-based methods regard pseudo-changes as a kind of style shift and alleviate it by transforming bitemporal images into the same style using generative adversarial networks (GANs). However, their efforts are limited by two drawbacks: 1) Transformed images suffer from distortion that reduces feature discrimination. 2) Alignment hampers the model from learning domain-agnostic representations that degrades performance on scenes with domain shifts from the training data. Therefore, oriented from pseudo-changes caused by style differences, we present a generalizable domain-agnostic difference learning network (DonaNet). For the drawback 1), we argue for local-level statistics as style proxies to assist against domain shifts. For the drawback 2), DonaNet learns domain-agnostic representations by removing domain-specific style of encoded features and highlighting the class characteristics of objects. In the removal, we propose a domain difference removal module to reduce feature variance while preserving discriminative properties and propose its enhanced version to provide possibilities for eliminating more style by decorrelating the correlation between features. In the highlighting, we propose a cross-temporal generalization learning strategy to imitate latent domain shifts, thus enabling the model to extract feature representations more robust to shifts actively. Extensive experiments conducted on three public datasets demonstrate that DonaNet outperforms existing state-of-the-art methods with a smaller model size and is more robust to domain shift. © 2025, CC BY.

关键词： Change detection

来源：评论

学校读者我要写书评

暂无评论

Multiple Resolutions Detail Enhancement Network for Real-Time image Semantic Segmentation

IEEE Transactions on Artificial Intelligence

引用

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

GAUSSIAN PRINCIPLE COMPONENTS FOR NONLOCAL MEANS image DENOISING

引用

Journal of Electronics(China) 2011年第4期28卷 539-547页

作者： Li Xiangping Wang Xiaotian Shi Guangming Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China Xidian University Xi＇ an 710071 China

NonLocal Means(NLM),taking fully advantage of image redundancy,has been proved to be very effective in noise ***,high computational load limits its wide *** on Principle Component Analysis(PCA),Principle Neighborhood Dictionary(PND) was proposed to reduce the computational load of ***,as the principle components in PND method are computed directly from noisy image neighborhoods,they are prone to be inaccurate due to the presence of *** this paper,an improved scheme for image denoising is *** scheme is based on PND and uses preprocessing via Gaussian filter to eliminate the influence of *** is then used to project those filtered image neighborhood vectors onto a lower-dimensional *** the preproc-essing process,the principle components computed are more accurate resulting in an improved de-noising performance.A comparison with some NLM based and state-of-art denoising methods shows that the proposed method performs well in terms of Peak Signal to Noise Ratio(PSNR) as well as image visual *** experimental results demonstrate that our method outperforms existing methods both subjectively and objectively.

关键词： image denoising NonLocal Means(NLM) Gaussian filter Principle Component Analysis(PCA)

来源：评论

学校读者我要写书评

暂无评论

Texture and wavelet based PCANet (TW-PCANet) for infants' facial expression recognition 2019

Texture and wavelet based PCANet (TW-PCANet) for infants' fa...

引用

2019 International Conference on Artificial Intelligence and Computer Science, AICS 2019

作者： Shen, Fang Liu, Jing Wu, Peng Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education Xidian University Xi'an China

ISBN: (纸本)9781450371506

The babyhood is a very important stage in the human growth process. Thus learning the facial expression characteristics of infants is of great significance to nursing care for infants. Infants' faces are significantly different from adults' faces, like eyebrows, eyes, nose, cheeks, skin texture, etc. Therefore, the facial expression recognition models trained on adults' facial expression database cannot be directly applied to infants' facial expression recognition. There are dozens of facial expression databases for adults' facial expression analysis, but there is no database composed by various infants' facial expressions. Hence we first collect candid images of infants' facial expression, which includes six obvious expressions of infants, namely crying, curious, happy, sleeping, wronged, neutral. Then the texture and wavelet based PCANet (TW-PCANet) is proposed to fully extract the features of infants' facial expressions. The proposed method first handles original input color images by local binary patterns (LBP) and Gabor wavelet, then the processed images are put into the PCANet to get the final class. The experimental results show that the proposed method can achieve higher recognition rate obtained by PCANet, LBP and Gabor wavelet. © 2019 Association for Computing Machinery.

关键词： Local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Pre-extracting boundary vectors for support vector machine using pseudo-density estimation method

Pre-extracting boundary vectors for support vector machine u...

引用

MIPPR 2009 - Pattern Recognition and Computer Vision: 6th International Symposium on Multispectral image Processing and Pattern Recognition

作者： Zhang, Li Zhou, Weida Chen, Guirong Zhou, Hongjie Ye, Ning Jiao, Licheng Institute of Intelligent Information Processing Key Laboratory of Intelligent Perception and Image Understanding Xidian University 710071 China

ISBN: (纸本)9780819478078

Support vector machines (SVMs) have become useful and universal learning machines. SVMs construct a decision function by support vectors (SVs) and their corresponding weights. The training phase of SVMs definitely uses all training samples, which leads to a large computational complexity for a large scale sample set. Moreover support vectors could not be found until a quadratic programming (QP) problem is solved. Actually we know only SVs play a role in the decision function. Hence, pseudo density estimation (PDE) is presented to extract a set of boundary vectors (BVs) which may contain SVs. The PDE method is a variant of Parzen window method. Hyperspheres are considered as the window functions. In our method, for each sample we construct a hypersphere with an unfixed radius. The ratio of the number of samples contained in the hypersphere of a sample to the total training samples can be taken as the pseudo density of the corresponding sample. The set of BVs is taken as the training input to SVMs. In doing so, it speeds the training procedure of SVMs. It is convenient for PDE to determine its parameter. The experiments show that SVMs using PDE have the similar generalization performance to SVMs. © 2009 Copyright SPIE - The International Society for Optical Engineering.

关键词： Support vector machines

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

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

K-means selective cluster ensembles based on multiple feature subsets

K-means selective cluster ensembles based on multiple featur...

引用

MIPPR 2009 - Pattern Recognition and Computer Vision: 6th International Symposium on Multispectral image Processing and Pattern Recognition

作者： Zhang, Li Zhou, Weida Zou, Haishuang Huo, Jieting Wu, Caili Jiao, Licheng Institute of Intelligent Information Processing Key Laboratory of Intelligent Perception and Image Understanding Xidian University 710071 China

ISBN: (纸本)9780819478078

Combining multiple clusterers is emerged as a powerful method for improving both the robustness and the stability of unsupervised classification solutions. In this paper, k-means selective cluster ensembles based on multiple feature subsets are proposed. In the ensemble, a random subset of features is used to train an individual k-means clusterer. In the final step, the selective weighted voting scheme is used for finding the best partition. The consensus function is constructed by relabeling all partitions of clusterers and finding the best partition. Experimental results on 4 UCI data sets show that our ensemble method can improve the clustering performance. © 2009 Copyright SPIE - The International Society for Optical Engineering.

关键词： Set theory

来源：评论

学校读者我要写书评

暂无评论

Adaptation and learning of spatio-temporal thresholds in spiking neural networks

引用

Neurocomputing 2025年 644卷

作者： Jiahui Fu Shuiping Gou Peizhao Wang Licheng Jiao Zhang Guo Jisheng Li Rong Liu Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Xidian University Xi’an 710071 Shannxi China School of Physics and Information Technology Shaanxi Normal University Xi’an 710119 Shannxi China

Spiking neural networks (SNNs) have attracted substantial attention in recent years due to their brain-inspired and event-driven characteristics. To mimic the behavior of biological neurons, the neuron in SNNs generates spikes to transmit information across the network once its membrane potential surpasses a certain firing threshold. Due to model complexity and computational challenges, the threshold is often set as a fixed value, which limits the rich dynamical features of neurons and is inconsistent with the dynamic nature of thresholds observed in biological systems. Additionally, treating the threshold as an optimized parameter presents challenges in achieving convergence and maintaining stability. Therefore, we introduce a spatio-temporal adjustment strategy for the firing threshold. We propose a Learnable Temporal Factor (LTF) to dynamically adapt the threshold over time and an Adaptive Learnable Spatial Factor (ALSF) to spatially extend the threshold. By coupling these factors with the neuronal dynamics, we achieve a stronger spike coding capacity by utilizing more information in the generation of spikes. Our experiments show that the proposed method yields remarkable performance on both static and neuromorphic datasets. Our code is available at ***/gzxdu/ST-Thresholds-SNN .

关键词：

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：