检索结果-内蒙古大学图书馆

Multi-domain Transfer Learning for Text Classification 1

9th CCF International Conference on Natural Language processing and Chinese Computing, NLPCC 2020

作者： Su, Xuefeng Li, Ru Li, Xiaoli School of Computer and Information Technology Shanxi University Taiyuan China School of Electronic Business and Logistics Business College of Shanxi University Taiyuan China Key Laboratory of Ministry of Education for Computation Intelligence and Chinese Information Processing Shanxi University Taiyuan China Institute for Infocomm Research A-star Singapore Singapore

ISBN: (数字)9783030604509

ISBN: (纸本)9783030604493

Leveraging data from multiple related domains to enhance the model generalization performance is critical for transfer learning in text classification. However, most existing approaches try to separate the features into shared and private spaces regardless of correlations between domains, resulting in the inadequate features sharing among certain most related domains. In this paper, we propose a generic dual-channels multi-task learning framework for multi-domain text classification, which can capture global-shared, local-shared, and private features simultaneously. Our novel framework incorporates Adversarial network and Mixture of experts into a neural network for multi-domain text classification, which is very useful for sharing more features among domains. The extensive experiments on the real-world text classification data-sets across 16 domains demonstrate our proposed approach achieves better results than five state-of-the-art techniques. © 2020, Springer Nature Switzerland AG.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Co-training based prediction of multi-label protein–protein interactions

引用

Computers in Biology and Medicine 2024年 177卷 108623-108623页

作者： Tang, Tao Zhang, Xiaocai Li, Weizhuo Wang, Qing Liu, Yuansheng Cao, Xiaofeng School of Modern Posts Nanjing University of Posts and Telecommunications 9 Wenyuan Rd Jiangsu Nanjing210023 China 1 Fusionopolis Way Singapore138632 Singapore School of Management Nanjing University of Posts and Telecommunications 9 Wenyuan Rd Jiangsu Nanjing210023 China College of Computer Science and Electronic Engineering Hunan University 2 Lushan Rd Hunan Changsha410086 China Key Laboratory of Intelligent Computing & Signal Processing of Ministry of Education Anhui University 111 Jiulong Road Anhui Hefei230601 China School of Artificial Intelligence Jilin University 2699 Qianjin St Changchun Jilin130012 China

Prediction of protein–protein interaction (PPI) types enhances the comprehension of the underlying structural characteristics and functions of proteins, which gives rise to a multi-label classification problem. The nominal features describe the physicochemical characteristics of proteins directly, establishing a more robust correlation with the interaction types between proteins than ordered features. Motivated by this, we propose a multi-label PPI prediction model referred to as CoMPPI (Co-training based Multi-Label prediction of Protein–Protein Interaction). This approach aims to maximize the utility of both ordered and nominal features extracted from protein sequences. Specifically, CoMPPI incorporates graph convolutional network (GCN) and 1D convolution operation to process the complementary subsets of features individually, leveraging both local and contextualized information in a more efficient way. In addition, two multi-type PPI datasets were constructed to eliminate the duplication in previous datasets. We compare the performance of CoMPPI with three state-of-the-art methods on three datasets partitioned using distinct schemes (Breadth-first search, Depth-first search, and Random), CoMPPI consistently outperforms the other methods across all cases, demonstrating improvements ranging from 3.81% to 32.40% in Micro-F1. The subsequent ablation experiment confirms the efficacy of employing the co-training framework for multi-label PPI prediction, indicating promising avenues for future advancements in this domain. © 2024 Elsevier Ltd

关键词： Proteins

来源：评论

学校读者我要写书评

暂无评论

Flow Visualization for Complex Fluid Flows via A Structure-enhanced Motion Estimator

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Chen, Jun Wang, He Hao, Zhifeng Cai, Zemin Mei, Ling Foshan University School of Industrial Design and Ceramic Art Foshan528000 China Foshan University school of Mechatronic Engineering and Automation Foshan528231 China Shantou University College of Science Department of Mathematics Guangdong 515063 China Shantou University Department of Electronic Engineering Guangdong Shantou515063 China Guangdong Provincial Key Laboratory of Digital Signal and Image Processing Techniques Guangdong Shantou515063 China Wuhan University of Science and Technology School of Information Science and Engineering 430081 China Huazhong University of Science and Technology School of Artificial Intelligence and Automation 430074 China Western Michigan University Department of Mechanical and Aerospace Engineering KalamazooMI49008 United States

Flow visualization through motion estimation using time-sequenced images plays a significant role in analyzing and understanding complex flow phenomena, and it is widely used in meteorology, oceanography, medicine, astronomy, experimental fluid mechanics, etc. However, it is difficult for current motion estimators to adapt to illumination changes, remove instable perturbation, and capture diverse motion patterns. In this paper, a novel flow visualization tool is developed to address these issues by employing a structure-enhanced motion estimator composed of a data term and a regularization term. Specifically, a statistical correlation descriptor is designed for the data term to improve the accuracy of motion estimation by enhancing both illumination robustness and matching discrimination. Inspired by the strong distinguishability of a structure-texture distribution in a local window, a structure-enhanced regularizer that considers the physical mechanism of fluid diffusion is introduced to capture different motion patterns, enhance prominent flow structures, and remove unnecessary ripples or textures caused by instable perturbation or noise. The experimental results demonstrate that our approach significantly outperforms current motion estimators in handling illumination changes and predicting complex fluid flows, and it also achieves state-of-the-art evaluation results on the public fluid flow datasets. Furthermore, the designed flow visualization tool successfully captures diverse motion patterns in Jupiter’s White Ovals, which is crucial for understanding the physical mechanisms behind their formation and sustenance. © 1991-2012 IEEE.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

Improving Chinese Character Representation with Formation Tree

SSRN

引用

SSRN 2024年

作者： Hong, Yang Li, Yinfei Qiao, Xiaojun Li, Rui Zhang, Junsong National Engineering Research Center for E-learning Central China Normal University No.152 Luoyu Road Hubei Wuhan430079 China Mind Art and Computation Group Department of Artificial Intelligence Xiamen University No. 4221 South Xiang’an Road Xiang’an District Fujian Xiamen361104 China National Engineering Research Center of Educational Big Data Central China Normal University No.152 Luoyu Road Hubei Wuhan430079 China Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan Xiamen University Ministry of Culture and Tourism Fujian Xiamen China

Learning effective representations for Chinese characters presents unique challenges, primarily due to the vast number of characters and their continuous growth, which requires models to handle an expanding category space. Additionally, the inherent sparsity of character usage complicates the generalization of learned representations. Prior research has explored radical-based sequences to overcome these issues, achieving progress in recognizing unseen characters. However, these approaches fail to fully exploit the inherent tree structure of such sequences. To address these limitations and leverage established data properties, we propose Formation Tree-CLIP (FT-CLIP). This model utilizes formation trees to represent characters and incorporates a dedicated tree encoder, significantly improving performance in both seen and unseen character recognition tasks. We further introduce masking for to both character images and tree nodes, enabling efficient and effective training. This approach accelerates training significantly (by a factor of 2 or more) while enhancing accuracy. Extensive experiments show that processing characters through formation trees aligns better with their inherent properties than direct sequential methods, significantly enhancing the generality and usability of the representations. © 2024, The Authors. All rights reserved.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

Multi-interactive dual-decoder for RGB-thermal salient object detection

arXiv

引用

arXiv 2020年

作者： Tu, Zhengzheng Li, Zhun Li, Chenglong Lang, Yang Tang, Jin Key Lab of Intelligent Computing and Signal Processing of Ministry of Education Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China

RGB-thermal salient object detection (SOD) aims to segment the common prominent regions of visible image and corresponding thermal infrared image that we call it RGBT SOD. Existing methods don’t fully explore and exploit the potentials of complementarity of different modalities and multi-type cues of image contents, which play a vital role in achieving accurate results. In this paper, we propose a multi-interactive dual-decoder to mine and model the multi-type interactions for accurate RGBT SOD. In specific, we first encode two modalities into multi-level multi-modal feature representations. Then, we design a novel dual-decoder to conduct the interactions of multi-level features, two modalities and global contexts. With these interactions, our method works well in diversely challenging scenarios even in the presence of invalid modality. Finally, we carry out extensive experiments on public RGBT and RGBD SOD datasets, and the results show that the proposed method achieves the outstanding performance against state-of-the-art algorithms. The source code has been released at: https://***/lz118/Multi-interactiveDual-decoder. Copyright © 2020, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Challenge-aware rgbt tracking

arXiv

引用

arXiv 2020年

作者： Li, Chenglong Liu, Lei Lu, Andong Ji, Qing Tang, Jin Key Lab of Intelligent Computing and Signal Processing Ministry of Education Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China

RGB and thermal source data suffer from both shared and specific challenges, and how to explore and exploit them plays a critical role to represent the target appearance in RGBT tracking. In this paper, we propose a novel challenge-aware neural network to handle the modality-shared challenges (e.g., fast motion, scale variation and occlusion) and the modality-specific ones (e.g., illumination variation and thermal crossover) for RGBT tracking. In particular, we design several parameter-shared branches in each layer to model the target appearance under the modality-shared challenges, and several parameter-independent branches under the modality-specific ones. Based on the observation that the modality-specific cues of different modalities usually contains the complementary advantages, we propose a guidance module to transfer discriminative features from one modality to another one, which could enhance the discriminative ability of some weak modality. Moreover, all branches are aggregated together in an adaptive manner and parallel embedded in the backbone network to efficiently form more discriminative target representations. These challenge-aware branches are able to model the target appearance under certain challenges so that the target representations can be learnt by a few parameters even in the situation of insufficient training data. From the experimental results we will show that our method operates at a real-time speed while performing well against the state-of-the-art methods on three benchmark datasets. Copyright © 2020, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Principled design of translation, scale, and rotation invariant variation operators for metaheuristics

arXiv

引用

arXiv 2021年

作者： Tian, Ye Zhang, Xingyi He, Cheng Tan, Kay Chen Jin, Yaochu Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Institutes of Physical Science and Information Technology Anhui University Hefei230601 China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei230601 China Guangdong Provincial Key Laboratory of Braininspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Department of Computing The Hong Kong Polytechnic University Hong Kong Department of Computer Science University of Surrey Guildford SurreyGU2 7XH United Kingdom

In the past three decades, a large number of metaheuristics have been proposed and shown high performance in solving complex optimization problems. While most variation operators in existing metaheuristics are empirically designed, this paper aims to design new operators automatically, which are expected to be search space independent and thus exhibit robust performance on different problems. For this purpose, this work first investigates the influence of translation invariance, scale invariance, and rotation invariance on the search behavior and performance of some representative operators. Then, we deduce the generic form of translation, scale, and rotation invariant operators. Afterwards, a principled approach is proposed for the automated design of operators, which searches for highperformance operators based on the deduced generic form. The experimental results demonstrate that the operators generated by the proposed approach outperform state-of-theart ones on a variety of problems with complex landscapes and up to 1000 decision variables. © 2021, CC BY.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Distribution Preserving Deep Semi-Nonnegative Matrix Factorization

Distribution Preserving Deep Semi-Nonnegative Matrix Factori...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Zhuolin Tan Anyong Qin Yongqing Sun Yuan Yan Tang School of Communications and Information Engineering Chongqing University of Posts and Telecommunications Chongqing China Chongqing Key Laboratory of Signal and Information Processing Chongqing China NTT Media Intelligence Laboratories Yokosuka Japan Zhuhai UM Science & Technology Research Institute University of Macau Macau China

ISBN: (纸本)9781665442084

Deep semi-nonnegative matrix factorization can obtain the hidden hierarchical representations according to the unknown attributes of the given data. On the other hand, the inherent structure of the each data cluster can be described by the distribution of the intra-class data. Then one hopes to learn a new low dimensional representation which can preserve the intrinsic structure embedded in the original high dimensional data space perfectly. Here we propose a novel distribution preserving deep semi-nonnegative matrix factorization method (DPNMF) to achieve this goal. As a result, the manifold structures in the raw data are well preserved in the feature space being from the top layer. The experimental results on the real-world datasets show that the proposed algorithm has good performance in terms of cluster accuracy and normalized mutual information (NMI).

关键词： Manifolds Conferences Clustering algorithms Approximation algorithms Mutual information Cybernetics

来源：评论

学校读者我要写书评

暂无评论

Uncertainty estimation by boosting with Gaussian process for expensive optimization problems

引用

Applied Soft Computing 2025年 180卷

作者： Zou, Hanhua Zeng, Sanyou Li, Changhe Jiao, Ruwang Zhao, Fei School of Mechanical Engineering and Electronic Information China University of Geosciences Wuhan China School of Artificial Intelligence Anhui University of Science & Technology Hefei China School of Future Science and Engineering Soochow University Suzhou China National Key Laboratory of Blind Signal Processing Chengdu China

In surrogate-assisted evolutionary algorithms (SAEAs), uncertainty measures the confidence level of the predicted fitness and plays an important role in selecting candidate points for expensive evaluation, as evaluating those with a large degree of uncertainty can enhance the exploration ability of algorithms and significantly improve model reliability. Gaussian process (GP) gains great popularity with a predictive variance to estimate uncertainty. However, the performance of GP-assisted SAEAs is still limited with weakened predictions and underutilized uncertainty. In this paper, we propose a novel SAEA that leverages a boosting ensemble with GP as the base learner to enhance optimization performance. First, GP is leveraged to boost a weak learner that captures global trends, refining its prediction in guiding the search. Then, the uncertainty provided by GP is integrated into boosting ensemble model to estimate its overall ensemble uncertainty, enhancing the model reliability and promoting the exploration capabilities. Moreover, a mechanism study is performed through standardized residual and a distance-based metric to have deep insights into search behaviors, demonstrating that the migrated uncertainty basically covers the statistical boundary of Gaussian distribution and contributes to exploitation and exploration trade-off. Experimental results across multiple benchmark problems and an antenna design problem demonstrate that the proposed method significantly enhanced GP-assisted SAEAs in statistical results of the best fitness value and convergence profile without increasing too much running time, particularly in high-dimensional problems. © 2025 Elsevier B.V.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Cross-Modality Coherent Registration of Whole Mouse Brains

Research Square

引用

Research Square 2021年

作者： Peng, Hanchuan Qu, Lei Li, Yuanyuan Xie, Peng Liu, Lijuan Wang, Yimin Wu, Jun Liu, Yu Wang, Tao Li, Longfei Guo, Kaixuan Wan, Wan Ouyang, Lei Xiong, Feng Zheng, Yefeng Xu, Fang Gong, Hui Dong, Hongwei Luo, Qingming Bi, Guo-Qiang Hawrylycz, Michael Zeng, Hongkui Allen Institute for Brain Science United States Key Laboratory of Intelligent Computation & Signal Processing Ministry of Education Anhui University China SEU-ALLEN Joint Center Institute for Brain Intelligence Southeast University Bangladesh Institute for Brain and Intelligence Southeast University Bangladesh Tencent Jarvis Lab China CAS Key Laboratory of Brain Connectome and Manipulation China Britton Chance Center for Biomedical Photonics Wuhan National Laboratory for Optoelectronics MoE Key Laboratory for Biomedical Photonics Huazhong University of Science and Technology China Center for Integrative Connectomics Department of Neurobiology David Geffen School of Medicine UCLA United States Hainan University China Hefei National Laboratory for Physical Sciences at the Microscale School of Life Sciences University of Science and Technology of China China

Recent whole brain mapping projects are collecting large-scale 3D images using powerful and informative modalities, such as STPT, fMOST, VISoR, or MRI. Registration of these multi-dimensional whole-brain images onto a standard atlas is essential for characterizing neuron types and constructing brain wiring diagrams. However, cross-modality image registration is challenging due to intrinsic variations of brain anatomy and artifacts resulted from different sample preparation methods and imaging modalities. We introduced a cross-modality registration method, called mBrainAligner, which uses coherent landmark mapping as well as deep neural networks to align whole mouse brain images to the standard Allen Common Coordinate Framework atlas. We also built a single cell resolution atlas using the fMOST modality, and used our method to generate whole brain map of 3D full single neuron morphology and neuron cell types. © 2021, CC BY.

关键词： Brain mapping

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：