检索结果-内蒙古大学图书馆

arxiv 2024年

作者： Yang, Li Luo, Zhipeng Zhang, Shiming Teng, Fei Li, Tianrui School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Southwest Jiaotong University Sichuan Chengdu611756 China

With the digitization of modern cities, large data volumes and powerful computational resources facilitate the rapid update of intelligent models deployed in smart cities. Continual learning (CL) is a novel machine learning paradigm that constantly updates models to adapt to changing environments, where the learning tasks, data, and distributions can vary over time. Our survey provides a comprehensive review of continual learning methods that are widely used in smart city development. The content consists of three parts: 1) Methodology-wise. We categorize a large number of basic CL methods and advanced CL frameworks in combination with other learning paradigms including graph learning, spatial-temporal learning, multi-modal learning, and federated learning. 2) Application-wise. We present numerous CL applications covering transportation, environment, public health, safety, networks, and associated datasets related to urban computing. 3) Challenges. We discuss current problems and challenges and envision several promising research directions. We believe this survey can help relevant researchers quickly familiarize themselves with the current state of continual learning research used in smart city development and direct them to future research trends. Copyright © 2024, The Authors. All rights reserved.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

Disentangled Representation Learning with Transmitted Information Bottleneck

arXiv

引用

arxiv 2023年

作者： Dang, Zhuohang Luo, Minnan Jia, Chengyou Dai, Guang Wang, Jihong Chang, xiaojun Wang, Jingdong The School of Computer Science and Technology The Ministry of Education Key Laboratory of Intelligent Networks and Network Security The Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Shaanxi Xi’an710049 China The SGIT AI Laboratory Xi’an710048 China The State Grid Shaanxi Electric Power Company Ltd. State Grid Corporation of China Xi’an710048 China The School of Information Science and Technology University of Science and Technology of China Hefei230026 China Abu Dhabi United Arab Emirates Baidu Inc Beijing100085 China

Encoding only the task-related information from the raw data, i.e., disentangled representation learning, can greatly contribute to the robustness and generalizability of models. Although significant advances have been made by regularizing the information in representations with information theory, two major challenges remain: 1) the representation compression inevitably leads to performance drop;2) the disentanglement constraints on representations are in complicated optimization. To these issues, we introduce Bayesian networks with transmitted information to formulate the interaction among input and representations during disentanglement. Building upon this framework, we propose DisTIB (Transmitted Information Bottleneck for Disentangled representation learning), a novel objective that navigates the balance between information compression and preservation. We employ variational inference to derive a tractable estimation for DisTIB. This estimation can be simply optimized via standard gradient descent with a reparameterization trick. Moreover, we theoretically prove that DisTIB can achieve optimal disentanglement, underscoring its superior efficacy. To solidify our claims, we conduct extensive experiments on various downstream tasks to demonstrate the appealing efficacy of DisTIB and validate our theoretical analyses. Copyright © 2023, The Authors. All rights reserved.

关键词： Information theory

来源：评论

学校读者我要写书评

暂无评论

A novel noise reduction and interaction enrichment recommendation model via contrastive learning

引用

Neurocomputing 2025年 645卷

作者： Zhang, Zhiqiang Wu, Qi Deng, Jiangzhou Ye, Jianmei Yang, Fang Wang, Yong Khushvakhtzoda, Kobiljon Kh. Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and Telecommunications Chongqing400065 China School of Economics and Management Chongqing University of Posts and Telecommunications Chongqing400065 China Research Center of Digital Intelligence Technology Innovation and Industry Development Chongqing University of Posts and Telecommunications Chongqing400065 China Mashang Consumer Finance Co. Ltd. Chongqing400065 China National Academy of Sciences of Tajikistan Dushanbe734025 Tajikistan

To address the challenge of noisy data in recommendation systems, we propose a novel model that combines adaptive denoising with structural similarity-based interaction filling to improve recommendation accuracy. Our method dynamically prunes noisy interactions using a threshold-based denoising strategy without requiring auxiliary information. To compensate for information loss and preserve data sparsity, we introduce a structural similarity-based approach that fills pruned interactions with high-reliability user–item pairs, computed via cosine similarity. We further enhance representation learning via a contrastive learning framework that separates reliable and unreliable interactions based on mutual information maximization. Experimental results on three public datasets demonstrate that our model outperforms state-of-the-art baselines, achieving up to 4.5% and 6.7% improvements in Recall@5 and NDCG@5, respectively, confirming its effectiveness and practical applicability. © 2025 Elsevier B.V.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Intra-Person Camera Adversarial for Intra-Camera Supervised Person Re-Identification

Intra-Person Camera Adversarial for Intra-Camera Supervised ...

引用

International Conference on Automatic Face and Gesture Recognition

作者： Ruochen Tang Xun Gong School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education Chengdu China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Southwest Jiaotong University Chengdu China

ISBN: (数字)9798350394948

ISBN: (纸本)9798350394955

Re-identification (ReID) of individuals across different cameras is a challenging task due to the high-quality large-scale datasets required for the model. Intra-camera supervised (ICS) person re-identification has been proposed to address the high cost of annotating large-scale datasets, but reducing the gap between camera domains remains a major challenge. Current approaches use intra- and inter-camera learning with contrastive learning performed separately in both phases. However, the effect of features from the same person under different cameras on the model during inter-camera learning, and the fine-grained characteristic where the same person can be classified into multiple classes based on the camera labels, still require further research. To address this issue, we propose a Camera-Based Contrastive Learning (CBCL) method that moves features away from their respective cameras and closer to other cameras to reduce domain gaps. We also introduce an Intra-Person Camera Adversarial (IPCA) loss that effectively utilizes fine-grained characteristics of person re-identification and improve IPCA by introducing camera labels to obtain IPCA_2 which achieves better model recognition performance than IPCA alone. Extensive experiments on multiple datasets demonstrate that our method outperforms existing methods and is comparable to fully-supervised methods.

关键词： Costs Scalability Face recognition Contrastive learning Gesture recognition Cameras Robustness

来源：评论

学校读者我要写书评

暂无评论

A Node-collaboration-informed Graph Convolutional Network for Precise Representation to Undirected Weighted Graphs

arXiv

引用

arxiv 2022年

作者： Wang, Ying Yuan, Ye Luo, xin The School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China The Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Engineering Research Center of Big Data Application for Smart Cities Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing400714 China The College of Computer and Information Science Southwest University Chongqing400715 China

An undirected weighted graph (UWG) is frequently adopted to describe the interactions among a solo set of nodes from real applications, such as the user contact frequency from a social network services system. A graph convolutional network (GCN) is widely adopted to perform representation learning to a UWG for subsequent pattern analysis tasks such as clustering or missing data estimation. However, existing GCNs mostly neglects the latent collaborative information hidden in its connected node pairs. To address this issue, this study proposes to model the node collaborations via a symmetric latent factor analysis model, and then regards it as a node-collaboration module for supplementing the collaboration loss in a GCN. Based on this idea, a Node-collaboration-informed Graph Convolutional Network (NGCN) is proposed with three-fold ideas: a) Learning latent collaborative information from the interaction of node pairs via a node-collaboration module;b) Building the residual connection and weighted representation propagation to obtain high representation capacity;and c) Implementing the model optimization in an end-to-end fashion to achieve precise representation to the target UWG. Empirical studies on UWGs emerging from real applications demonstrate that owing to its efficient incorporation of node-collaborations, the proposed NGCN significantly outperforms state-of-the-art GCNs in addressing the task of missing weight estimation. Meanwhile, its good scalability ensures its compatibility with more advanced GCN extensions, which will be further investigated in our future studies. Copyright © 2022, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Predicting Transcription Factor Binding Signals Based on a Novel Encoder-Decoder Framework 2nd

Predicting Transcription Factor Binding Signals Based on a N...

引用

2nd International Conference on Applied Intelligence, ICAI 2024

作者： Wang, Siguo Li, Zhipeng Zhang, Qinhu Ningbo Institute of Digital Twin Eastern Institute of Technology No. 568 Tongxin Road Zhuangshi Street Zhejiang Ningbo315201 China Big Data and Intelligent Computing Research Center Guangxi Academy of Science Nanning530007 China Institute for Regenerative Medicine Medical Innovation Center and State Key Laboratory of Cardiology School of Medicine Shanghai East Hospital Tongji University Shanghai200123 China

ISBN: (纸本)9789819619061

The transcription process is the initial step in gene expression and the core of the regulatory mechanism, in which transcription factors control gene expression through interactions with particular DNA sequences. Therefore, identification of transcription factor binding sites (TFBSs) provides theoretical basis for further dissection of transcriptional regulatory mechanisms and disease diagnosis. To address the limitations of current research on TFBSs, a novel symmetric Encoder-Decoder framework is proposed for predicting transcription factor binding signals values at base sites. Our approach utilizes word vectors to encode DNA sequences, followed by encoders that progressively extract feature representations from these sequences. We then employ Gated Recurrent Unit (GRU) to capture the contextual dependencies within the sequences, ultimately using decoders to reconstruct the binding signal values for the DNA sequence sites. In order to access the effectiveness of the proposed symmetric Encoder-Decoder framework, some experiments were conducted on 20 ChIP-seq datasets, and the results show that the proposed novel method outperformers several existing advanced methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： DNA sequences

来源：评论

学校读者我要写书评

暂无评论

Small Object Detection via Precise Region-Based Fully Convolutional Networks

引用

Computers, Materials & Continua 2021年第11期69卷 1503-1517页

作者： Dengyong Zhang Jiawei Hu Feng Li xiangling Ding Arun Kumar Sangaiah Victor SSheng Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science and TechnologyChangsha410114China School of Computer and Communication Engineering Changsha University of Science and TechnologyChangsha410114China School of Computer Science and Engineering Hunan University of Science and TechnologyXiangtan411004China School of Computing Science and Engineering Vellore Institute of Technology(VIT)Vellore632014India Department of Computer Science Texas Tech UniversityLubbock79409TXUSA

In the past several years,remarkable achievements have been made in the field of object *** performance is generally improving,the accuracy of small object detection remains low compared with that of large object *** addition,localization misalignment issues are common for small objects,as seen in GoogLeNets and residual networks(ResNets).To address this problem,we propose an improved region-based fully convolutional network(R-FCN).The presented technique improves detection accuracy and eliminates localization misalignment by replacing positionsensitive region of interest(PS-RoI)pooling with position-sensitive precise region of interest(PS-Pr-RoI)pooling,which avoids coordinate quantization and directly calculates two-order integrals for position-sensitive score maps,thus preventing a loss of spatial precision.A validation experiment was conducted in which the Microsoft common objects in context(MS COCO)training dataset was *** showed an accuracy improvement of 3.7%for object detection tasks and an increase of 6.0%for small objects.

关键词： Small object detection precise R-FCN PS-Pr-RoI pooling two-stage detector

来源：评论

学校读者我要写书评

暂无评论

A Self-Supervised Transfer Learning Framework for Gland Segmentation in Colorectal Cancer Histopathology with Limited Labeled data 2nd

A Self-Supervised Transfer Learning Framework for Gland Segm...

引用

2nd International Conference on Applied Intelligence, ICAI 2024

作者： Wen, Huer Wu, Yan Huang, De-Shuang Institute for Regenerative Medicine Medical Innovation Center and State Key Laboratory of Cardiology Shanghai East Hospital School of Medicine Tongji University Shanghai200123 China Big Data and Intelligent Computing Research Center Guangxi Academy of Science Nanning530007 China Ningbo Institute of Digital TwinEastern Institute of Technology No. 568 Tongxin Road Zhuangshi Street Zhejiang Ningbo315201 China

ISBN: (纸本)9789819619061

Accurate gland segmentation in colorectal cancer histopathology images is crucial for diagnosis and grading but is hampered by the limited availability of annotated data. To develop a robust and accurate gland segmentation method that effectively leverages unlabeled data to overcome the limitations of small annotated datasets. We propose a novel framework that combines self-supervised learning and transfer learning. A vision transformer is pre-trained using DINOv2 on a large unlabeled dataset (IMP-CRS-2024) and then fine-tuned on the GlaS dataset using a lightweight decoder and a boundary-aware loss function that combines Dice loss and a distance transform-weighted boundary loss. Our method achieves state-of-the-art performance on the GlaS dataset, surpassing existing methods in terms of F1-score, Object Dice, and Object Hausdorff distance. An ablation study confirms the benefits of both the self-supervised pre-training and the boundary-aware loss. Our approach effectively addresses the challenge of limited annotated data in gland segmentation, offering a promising solution for improving the accuracy and efficiency of colorectal cancer diagnosis. The framework can be generalized to other histopathology image analysis tasks and cancer types. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features

arXiv

引用

arxiv 2024年

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Cao, xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China

Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative tasks such as semantic segmentation. Given numerous activations, selecting a small yet effective subset poses a fundamental problem. To this end, the early study of this field performs a large-scale quantitative comparison of the discriminative ability of the activations. However, we find that many potential activations have not been evaluated, such as the queries and keys used to compute attention scores. Moreover, recent advancements in diffusion architectures bring many new activations, such as those within embedded ViT modules. Both combined, activation selection remains unresolved but overlooked. To tackle this issue, this paper takes a further step with a much broader range of activations evaluated. Considering the significant increase in activations, a full-scale quantitative comparison is no longer operational. Instead, we seek to understand the properties of these activations, such that the activations that are clearly inferior can be filtered out in advance via simple qualitative evaluation. After careful analysis, we discover three properties universal among diffusion models, enabling this study to go beyond specific models. On top of this, we present effective feature selection solutions for several popular diffusion models. Finally, the experiments across multiple discriminative tasks validate the superiority of our method over the SOTA competitors. Our code is available at this url. © 2024, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Transformer-Based Hierarchical Dynamic Decoders for Salient Object Detection

SSRN

引用

SSRN 2023年

作者： Zheng, Qingping Zheng, Ling Deng, Jiankang Li, Ying Shang, Changjing Shen, Qiang School of Computer Science National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Provincial Key Laboratory of Speech & Image Information Processing Northewestern Polytechnical University Shaanxi Xi’an710129 China Fuzhou Institute of Data Technology Fujian350200 China Department of Computing Imperial College London LondonSW7 2AZ United Kingdom

HighlightsTransformer-Based Hierarchical Dynamic Decoders for Salient Object DetectionQingping Zheng, Ling Zheng, Jiankang Deng, Ying Li, Changjing Shang, Qiang Shen• T-HDDNet employs dynamic upsampling and fusion for data-driven salient object detection.• T-HDDNet uses a spatially sensitive loss to learn salient object structures, yielding a high-resolution map.• Our method exceeds benchmarks at 22.19G MACs and 27M Params, reducing costs compared to the top model. © 2023, The Authors. All rights reserved.

关键词： Object detection

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：