检索结果-内蒙古大学图书馆

Exploring Invariance Matters for Domain Generalization

IEEE Transactions on Image processing 2025年

作者： Wang, Shanshan He, Houmeng Yang, Xun Liu, Zhipu Zhong, Yuanhong Zhang, Xingyi Wang, Meng Anhui University National Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology Institutes of Physical Science and Information Technology Hefei230601 China University of Science and Technology of China School of Information Science and Technology Department of Electronic Engineering and Information Science Hefei230026 China Chongqing University of Technology School of Computer Science and Engineering Chongqing400054 China Chongqing University School of Microelectronics and Communication Engineering Chongqing400030 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education School of Computer Science and Technology Hefei230601 China Hefei University of Technology School of Computer Science and Information Engineering Hefei230009 China

Domain generalization (DG) aims to solve the problem of significant performance degradation when target domain data collected from the Out-Of-Distribution (O.O.D). Previous efforts try to exploit invariant features in the source domain through CNN networks. However, inspired by causal mechanisms, we find that the complex spurious-invariant information is still hidden in this view invariant features, and the impact of domain and class discrepancies on extracting invariance has not been effectively mitigated. To alleviate these issues, we propose a self-weighted multi-view mining invariance domain generalization framework (SMIDG). On the one hand, to make up for the insufficiency of traditional single-view convolutional feature extraction networks, we propose to mine features from another frequency view and use the self-adaptive adversarial masks to eliminate some spurious correlations, ensuring causal invariance in the coarse-grained generalization. However, due to inconsistencies in discriminative information between interdomain and intra-domain samples, as well as inter-class and intra-class samples, the coarse-grained elimination of spurious associations does not fully resolve this issue. On the other hand, we also consider the fine-grained generalization from two aspects. Firstly, to better tackle the domain discrepancies, we propose a novel progressive contrastive learning strategy that learns the underlying specific features of samples while gradually mitigating domain discrepancies, thereby ensuring domain invariance in fine-grained generalization. Secondly, due to the issue of feature inconsistency, we adopt a self-adaptive hard sample mining method with information gain to ensure that the model pays more attention on hard disentangled samples, thus maintaining feature invariance. Extensive experiments on five benchmark datasets demonstrate that our method outperforms state-of-the-art approaches. © 1992-2012 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MSFSAN: A Novel Multi-Scale Spatio-Temporal Feature Screening Attention Network for Urban Carbon Emission Prediction

MSFSAN: A Novel Multi-Scale Spatio-Temporal Feature Screenin...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Wang, Ben Qin, Xizhong Qin, Jiwei Zhang, Xiaoyu Ma, Haodong College of Computer Science and Technology Xinjiang University Xinjiang Key Laboratory of Signal Detection and Processing Ürümqi830046 China

ISBN: (纸本)9781665410205

In order to cope with the increasingly severe global energy conservation and emission reduction problems, research on urban carbon emission prediction is of great significance. The existing methods mainly use time series analysis to predict urban carbon emission, but there is a strong spatial correlation between the carbon emission data of several cities. Therefore, this paper designs a multi-scale spatial-temporal feature screening attention network to predict target cities' future carbon emission data. Firstly, this paper combines the daily carbon emission data of the near-neighbouring cities and the daily homologous emission data of the target city to analyze the urban carbon emission data from a spatio-temporal perspective. Then, this paper designs a multi-scale spatial interactive convolution module and a multi-scale temporal convolution module to extract multi-scale spatio-temporal features effectively. In addition, the feature screening module is designed to reduce the adverse effects of redundant features. Finally, the multi-scale features are used to predict the future carbon emissions of the target city through a predictor. The experimental results show that our prediction model is superior to the existing methods in six datasets. © 2024 IEEE.

关键词： Low emission

来源：评论

学校读者我要写书评

暂无评论

Distributed autocorrelation-based sequential detection of OFDM signals in cognitive radios

Distributed autocorrelation-based sequential detection of OF...

引用

3rd International Conference on Cognitive Radio Oriented Wireless Networks and Communications, CrownCom 2008

作者： Chaudhari, Sachin Koivunen, Visa Poor, Vincent H. SMARAD CoE Signal Processing Laboratory Helsinki Univ. of Technology Finland School of Engineering and Applied Science Princeton University

ISBN: (纸本)9781424423026

This paper addresses the problem of collaborative spectrum sensing using sequential detection (SD) in cognitive radios. The goal of sequential processing is to reduce the delay and amount of data needed in identifying underutilized spectrum. Each secondary user (SU) employs a simple and computationally efficient autocorrelation-based detector for Orthogonal Frequency Division Multiplexing (OFDM) signals of the primary user (PU). The decision statistics from individual detectors are combined in a fusion center that may be a separate node or one of the secondary users. The statistical properties of the decision statistics are established. The performance of the scheme is studied by theory and simulations. A comparison of the SD scheme with the Neyman-Pearson Fixed Sample Size (FSS) test for the same false alarm and missed detection probabilities is also carried out.

关键词： Autocorrelation

来源：评论

学校读者我要写书评

暂无评论

Identifying Disease Modules Based on Connectivity and Semantic Similarities 14th

Identifying Disease Modules Based on Connectivity and Semant...

引用

14th International Conference on Bio-inspired Computing: Theories and Applications, BIC-TA 2019

作者： Su, Yansen Zhu, Huole Zhang, Lei Zhang, Xingyi Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei China

ISBN: (纸本)9789811534140

The identification of disease modules has attracted increasing attention due to the importance in comprehending pathogenesis of complex diseases. Most of the existing methods were based on the protein-protein interaction (PPI) networks with the incompleteness and incorrectness of the interactome, which results in many disease-related proteins and pathways not within their disease modules. In this paper, we propose a method named IDMCSS to effectively identify disease modules by adding some potential interactions and removing some incorrect interactions in the existing human PPI network. Firstly, the connective similarity and semantic similarity are calculated between the known disease proteins and each of their neighbors. Then, the network is adjusted by adding the interactions with large connective and semantic similarity, and removing those with small connective and semantic similarity. Further, the proteins are sorted in the descending order according to the similarity to the known disease proteins, and the sorted proteins are added into a candidate node set one by one until a certain biological information is not enriched in the candidate node set. Finally, the connected subnetwork with the largest number of nodes in the candidate node set is selected as the disease module. The disease modules identified by IDMCSS involve crucial biological processes of related diseases and can predict 12 targets for drug intervention. The experimental results on asthma demonstrate the effectiveness of the proposed method in comparison to existing algorithms for disease module identification. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Proteins

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Music Source Separation Model with Graph Convolution Network 1

引用

18th National Conference on Man-Machine Speech Communication, NCMMSC 2023

作者： Zhu, Mengying Wang, Liusong Hu, Ying School of Computer Science and Technology Xinjiang University Urumqi China Key Laboratory of Signal Detection and Processing in Xinjiang Urumqi China

ISBN: (数字)9789819706013

ISBN: (纸本)9789819706006

With the rapid advancement of deep neural networks, there has been a significant improvement in the performance of music source separation methods. However, most of them primarily focus on improving their separation performance, while ignoring the issue of model size in the real-world environments. For the application in the real-world environments, in this paper, we propose a lightweight network combined with the Graph convolutional network Attention (GCN_A) module for Music Source Separation (G-MSS), which includes an Encoder and four Decoders, each of them outputs a target music source. The G-MSS network adopts both time-domain and frequency-domain L1 losses. The ablation study verifies the effectiveness of our designed GCN Attention (GCN_A) module and multiple Decoders, and also make a visualization analysis of the main components in the G-MSS network. Comparing with the other 13 methods on the MUSDB18 dataset, our proposed G-MSS achieves comparable separation performance while maintaining the lower amount of parameters. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Self-adaptive Two-Stage Local Expansion Algorithm for Community Detection on Complex Networks 7th

A Self-adaptive Two-Stage Local Expansion Algorithm for Com...

引用

7th International Conference on Data Mining and Big Data, DMBD 2022

作者： Shan, Hui Li, Bin Yang, Haipeng Zhang, Lei Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei China

ISBN: (纸本)9789811989902

Community detection is of great importance to find hidden information in complex networks. For this problem, local expansion algorithms are becoming popular due to the low time complexity. However, most of them depend heavily on seed selection or require setting some thresholds in advance, leading to inaccurate partition. To this end, this paper proposes a self-adaptive two-stage local expansion algorithm (SALEA) for community detection. Specifically, we propose a self-adaptive strategy that can be used in SALEA for finding communities spontaneously. In the first stage, we apply the self-adaptive strategy for nodes to conduct local expansion and get coarse community structures. In the second stage, we apply the self-adaptive strategy for weak communities obtained in the first stage to refine the coarse community structures and get more accurate partitions. Finally, the experimental results on real and synthetic networks demonstrate that SALEA is superior over several state-of-the-arts. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

In time passive localization using multi base-line phase comparison receivers

In time passive localization using multi base-line phase com...

引用

2006 CIE International Conference on Radar, ICR 2006

作者： Wei, Xing Wan, Jian-Wei Huangfu, Kan Laboratory of Digital Signal Processing School of Electronic Science and Engineering National Univ. of Defense Technology Changsha 410073 China

ISBN: (纸本)0780395824

A new in time passive localization system based on multi base-line phase comparison receivers is proposed. The new system uses short base-line to avoid the long base-line phase illegibility then uses the phase differences without illegibility to get the signal arriving angle and to detect the emitter's range. The GDOP and Simulation performance have also been discussed in this paper. © 2006 IEEE.

关键词： Radar receivers

来源：评论

学校读者我要写书评

暂无评论

Multi-Level Context Ultra-Aggregation for Stereo Matching

Multi-Level Context Ultra-Aggregation for Stereo Matching

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition

作者： Guang-Yu Nie Ming-Ming Cheng Yun Liu Zhengfa Liang Deng-Ping Fan Yue Liu Yongtian Wang Beijing Institute of Technology TKLNDST CS Nankai University National Key Laboratory of Science and Technology on Blind Signal Processing

ISBN: (纸本)9781728132945

Exploiting multi-level context information to cost volume can improve the performance of learning-based stereo matching methods. In recent years, 3-D Convolution Neural Networks (3-D CNNs) show the advantages in regularizing cost volume but are limited by unary features learning in matching cost computation. However, existing methods only use features from plain convolution layers or a simple aggregation of multi-level features to calculate cost volume, which is insufficient because stereo matching requires discriminative features to identify corresponding pixels in rectified stereo image pairs. In this paper, we propose a unary features descriptor using multi-level context ultra-aggregation (MCUA), which encapsulates all convolutional features into a more discriminative representation by intra-and inter-level features combination. Specifically, a child module that takes low-resolution images as input captures larger context information;the larger context information from each layer is densely connected to the main branch of the network. MCUA makes good usage of multi-level features with richer context and performs the image-to-image prediction holistically. We introduce our MCUA scheme for cost volume calculation and test it on PSM-Net. We also evaluate our method on Scene Flow and KITTI 2012/2015 stereo datasets. Experimental results show that our method outperforms state-of-the-art methods by a notable margin and effectively improves the accuracy of stereo matching.

关键词： branch main Volume Costs Unary multilayers stereo imaging Convolution

来源：评论

学校读者我要写书评

暂无评论

On the Role of Priors in Bayesian Causal Learning

arXiv

引用

arXiv 2025年

作者： Geiger, Bernhard C. Kern, Roman Signal Processing and Speech Communication Laboratory Graz University of Technology Inf-feldgasse 16c Graz8010 Austria Know Center Research GmbH Sandgasse 34 Graz8010 Austria Institute for Interactive Systems and Data Science Graz University of Technology Sandgasse 36 Graz8010 Austria

In this work, we investigate causal learning of independent causal mechanisms from a Bayesian perspective. Confirming previous claims from the literature, we show in a didactically accessible manner that unlabeled data (i.e., cause realizations) do not improve the estimation of the parameters defining the mechanism. Furthermore, we observe the importance of choosing an appropriate prior for the cause and mechanism parameters, respectively. Specifically, we show that a factorized prior results in a factorized posterior, which resonates with Janzing and Schölkopf’s definition of independent causal mechanisms via the Kolmogorov complexity of the involved distributions and with the concept of parameter independence of Heckerman et al. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Sampling Observer based Control Design with Application to Networked Visual Servoing Control Systems

Event-Triggered Sampling Observer based Control Design with ...

引用

第三十二届中国控制会议

作者： Wang Haoping Tian Yang Nicolai Christov Sino-French Joint Laboratory of Automation and Signal Processing School of Automation Nanjing University of Science and Technology LAGIS-CNRS UMR 8219 Lille University of Science and Technology

ISBN: (纸本)9789881563835

The present paper deals with a new continuous undelayed state observer based trajectory tracking approach by using only the sampled and delayed measurements where the sampling period and delayed value are variable and unknown. This proposed event-triggered sampling observer based control, which is derived by using the theory of a particular hybrid systems called Piecewise Continuous Systems, has a very simple structure and can be easily implemented to the networked visual servoing control systems. To show the proposed method performance, a numerical application example is introduced.

关键词： Networked visual servoing control systems, Piecewise continuous systems, Piecewise continuous controller

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：