检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Pan, Zhiyu Wang, Kewei Wu, Yizheng Xiao, Liwen Cui, Jiahao Wang, Zhicheng Cao, Zhiguo Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

Automatic image cropping models predict reframing boxes to enhance image aesthetics. Yet, the scarcity of labeled data hinders the progress of this task. To overcome this limitation, we explore the possibility of utilizing both labeled and unlabeled data together to expand the scale of training data for image cropping models. This idea can be implemented in a pseudo-labeling way: producing pseudo labels for unlabeled data by a teacher model and training a student model with these pseudo labels. However, the student may learn from teacher's mistakes. To address this issue, we propose the multi-policy viewfinder network (MPV-Net) that offers diverse refining policies to rectify the mistakes in original pseudo labels from the teacher. The most reliable policy is selected to generate trusted pseudo labels. The reliability of policies is evaluated via the robustness against box jittering. The efficacy of our method can be evaluated by the improvement compared to the supervised baseline which only uses labeled data. Notably, our MPV-Net outperforms off-the-shelf pseudo-labeling methods, yielding the most substantial improvement over the supervised baseline. Furthermore, our approach achieves state-of-the-art results on both the FCDB and FLMS datasets, signifying the superiority of our approach. Copyright © 2024, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

A Point Cloud Segmentation Method Based on Ground Point Cloud Removal and Multi-Scale Twin Range image 42

A Point Cloud Segmentation Method Based on Ground Point Clou...

引用

42nd Chinese control Conference, CCC 2023

作者： Zhou, Yicheng Peng, Gang Duan, Hangqi Wu, Zhangang Zhu, Xukang School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of Image Processing and Intelligent Control Ministry of Education Wuhan430074 China Shantui Construction Machinery Co. Ltd. Jining272073 China

ISBN: (纸本)9789887581543

Aiming at the shortcomings of traditional point cloud segmentation algorithms, this paper proposes a 3D lidar point cloud segmentation method combining ground filtering and multi-scale twin range image construction. This method fully considers the geometric space distribution characteristics of the point cloud and the randomness of the positions between objects. Based on the assumption of multi plane model, the point cloud is divided into sectors. The ground points are removed through region ground plane fitting and growth, and then the multi-scale twin range image is constructed according to non-ground points. On the basis of the twin range image, the Breadth First Search algorithm is improved, the depth-breadth joint search strategy is proposed, all the points to be clustered are traversed, and the adaptive clustering threshold is used for point cloud clustering, which realizes a point cloud segmentation method with higher accuracy and robustness. Through the experimental analysis of KITTI dataset and collected campus outdoor scene dataset, compared with the traditional point cloud segmentation algorithm, the method proposed in this paper can effectively improve the point cloud segmentation accuracy and robustness of mobile robots in complex environments. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

FADE: A Task-Agnostic Upsampling Operator for Encoder-Decoder Architectures

arXiv

引用

arXiv 2024年

作者： Lu, Hao Liu, Wenze Fu, Hongtao Cao, Zhiguo The Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

The goal of this work is to develop a task-agnostic feature upsampling operator for dense prediction where the operator is required to facilitate not only region-sensitive tasks like semantic segmentation but also detail-sensitive tasks such as image matting. Prior upsampling operators often can work well in either type of the tasks, but not both. We argue that task-agnostic upsampling should dynamically trade off between semantic preservation and detail delineation, instead of having a bias between the two properties. In this paper, we present FADE, a novel, plug-and-play, lightweight, and task-agnostic upsampling operator by fusing the assets of decoder and encoder features at three levels: i) considering both the encoder and decoder feature in upsampling kernel generation;ii) controlling the per-point contribution of the encoder/decoder feature in upsampling kernels with an efficient semi-shift convolutional operator;and iii) enabling the selective pass of encoder features with a decoder-dependent gating mechanism for compensating details. To improve the practicality of FADE, we additionally study parameter- and memory-efficient implementations of semi-shift convolution. We analyze the upsampling behavior of FADE on toy data and show through large-scale experiments that FADE is task-agnostic with consistent performance improvement on a number of dense prediction tasks with little extra cost. For the first time, we demonstrate robust feature upsampling on both region- and detail-sensitive tasks successfully. Code is made available at: https://***/poppinace/fade Copyright © 2024, 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

A3E: Aligned and Augmented Adversarial Ensemble for Accurate, Robust and Privacy-Preserving EEG Decoding

arXiv

引用

arXiv 2024年

作者： Chen, Xiaoqing Jia, Tianwang Wu, Dongrui Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

An electroencephalogram (EEG) based brain-computer interface (BCI) enables direct communication between the brain and external devices. However, EEG-based BCIs face at least three major challenges in real-world applications: data scarcity and individual differences, adversarial vulnerability, and data privacy. While previous studies have addressed one or two of these issues, simultaneous accommodation of all three challenges remains challenging and unexplored. This paper fills this gap, by proposing an Aligned and Augmented Adversarial Ensemble (A3E) algorithm and integrating it into three privacy protection scenarios (centralized source-free transfer, federated source-free transfer, and source data perturbation), achieving simultaneously accurate decoding, adversarial robustness, and privacy protection of EEG-based BCIs. Experiments on three public EEG datasets demonstrated that our proposed approach outperformed over 10 classic and state-of-the-art approaches in both accuracy and robustness in all three privacy-preserving scenarios, even outperforming state-of-the-art transfer learning approaches that do not consider privacy protection at all. This is the first time that three major challenges in EEG-based BCIs can be addressed simultaneously, significantly improving the practicalness of EEG decoding in real-world BCIs. © 2024, CC BY.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Data Fusion Based Source-Free Semi-Supervised Domain Adaptation for Seizure Subtype Classification

arXiv

引用

arXiv 2024年

作者： Peng, Ruimin An, Jiayu Wu, Dongrui Key Laboratory of the Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

Electroencephalogram (EEG)-based seizure subtype classification enhances clinical diagnosis efficiency. Source-free semi-supervised domain adaptation (SF-SSDA), which transfers a pre-trained model to a new dataset with no source data and limited labeled target data, can be used for privacy-preserving seizure subtype classification. This paper considers two challenges in SF-SSDA for EEG-based seizure subtype classification: 1) How to effectively fuse both raw EEG data and expert knowledge in classifier design? 2) How to align the source and target domain distributions for SF-SSDA? We propose a Knowledge-Data Fusion based SF-SSDA approach, KDF-MutualSHOT, for EEG-based seizure subtype classification. In source model training, KDF uses Jensen-Shannon Divergence to facilitate mutual learning between a feature-driven Decision Tree-based model and a data-driven Transformer-based model. To adapt KDF to a new target dataset, an SF-SSDA algorithm, MutualSHOT, is developed, which features a consistency-based pseudo-label selection strategy. Experiments on the public TUSZ and CHSZ datasets demonstrated that KDF-MutualSHOT outperformed other supervised and source-free domain adaptation approaches in cross-subject seizure subtype classification. © 2024, CC BY.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

An Integrated Scheduling Algorithm of Satellite Observation and Data Download Based on Multi-Agent Deep Reinforcement Learning

An Integrated Scheduling Algorithm of Satellite Observation ...

引用

2023 China Automation Congress, CAC 2023

作者： Chen, Kang Du, Shaochong Huo, Hong Fang, Tao Shanghai Jiao Tong University Department of Automation Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai China Shanghai Engineering Research Centre of Intelligent Control and Management Shanghai China

ISBN: (纸本)9798350303759

The earth observation satellite scheduling has always been critical for the maximum use of limited satellite resources, which basically includes scheduling ground target observation and observation data downloading. Due to the complexity of the mathematical model and its NP-hardness, current research usually splits it into two problems to simplify the model. In this paper, we propose a model of the integrated scheduling problem of satellite observation and data downloading (ISP-SODD) based on the decentralized partially observable Markov decision process (Dec-POMDP), treating each satellite as an agent with autonomous decision-making capability. A multi-agent deep reinforcement learning-based (MADRL-based) algorithm is proposed to solve it. A series of simulation experiments of different scales validate the effectiveness of the method and its advantages compared with the traditional heuristic algorithms. To the best of our knowledge, this study is the first attempt to apply multi-agent reinforcement learning to a multi-satellite scheduling scenario with downloading considerations. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Learning Knowledge Evolution with Time Duration from Finer-Time-Granularity Temporal Knowledge Graph

Learning Knowledge Evolution with Time Duration from Finer-T...

引用

2023 China Automation Congress, CAC 2023

作者： Du, Shaochong Chen, Kang Yang, Shijie Huo, Hong Fang, Tao Shanghai Jiao Tong University Department of Automation Shanghai China Ministry of Education Key Laboratory of System Control and Information Processing Shanghai China Shanghai Engineering Research Centre of Intelligent Control and Management Shanghai China

ISBN: (纸本)9798350303759

How to represent the temporal information corresponding to each fact in temporal knowledge graphs (TKGs) effectively is always challenging. Most existing representation learning methods usually map the timelines of knowledges into multiple points and ignore the underlying continuous time property and periodic characteristics behind those dense timestamps in finer-time granularity temporal knowledge graphs. A novel Knowledge Evolution with Time Duration (KETD) model is proposed for knowledge representation of temporal knowledge graphs with finer-time granularities. It represents the entity embedding as a time-varying nonlinear function to find the specific continuous time property from dense timestamps. To the best of our knowledge, it is the first attempt to learn embeddings of time durations and combines them into embeddings of entities and relations to predict potential periodic facts. It also uses the temporal point process to capture the impact of historical facts on the current fact. The experiments on self-built finer-time granularity TKG of Satellite-to-Earth Communication (STEC) and two public datasets have demonstrated the superiority of KETD compared to some baseline approaches. © 2023 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Domain-Invariant Similarity Activation Map Contrastive Learning for Retrieval-Based Long-Term Visual Localization

引用

IEEE/CAA Journal of Automatica Sinica 2022年第2期9卷 313-328页

作者： Hanjiang Hu Hesheng Wang Zhe Liu Weidong Chen Department of Automation Shanghai Jiao Tong UniversityShanghai 200240China IEEE Department of Automation Institute of Medical RoboticsKey Laboratory of System Control and Information Processing of Ministry of EducationKey Laboratory of Marine Intelligent Equipment and System of Ministry of EducationShanghai Jiao Tong UniversityShanghai 200240China Department of Computer Science and Technology University of CambridgeCambridge CB30FDUnited Kingdom

Visual localization is a crucial component in the application of mobile robot and autonomous *** retrieval is an efficient and effective technique in image-based localization *** to the drastic variability of environmental conditions,e.g.,illumination changes,retrievalbased visual localization is severely affected and becomes a challenging *** this work,a general architecture is first formulated probabilistically to extract domain-invariant features through multi-domain image ***,a novel gradientweighted similarity activation mapping loss(Grad-SAM)is incorporated for finer localization with high *** also propose a new adaptive triplet loss to boost the contrastive learning of the embedding in a self-supervised *** final coarse-to-fine image retrieval pipeline is implemented as the sequential combination of models with and without Grad-SAM *** experiments have been conducted to validate the effectiveness of the proposed approach on the CMU-Seasons *** strong generalization ability of our approach is verified with the RobotCar dataset using models pre-trained on urban parts of the CMU-Seasons *** performance is on par with or even outperforms the state-of-the-art image-based localization baselines in medium or high precision,especially under challenging environments with illumination variance,vegetation,and night-time ***,real-site experiments have been conducted to validate the efficiency and effectiveness of the coarse-to-fine strategy for localization.

关键词： Deep representation learning place recognition visual localization

来源：评论

学校读者我要写书评

暂无评论

A Class of Distributed Variable Structure Multiple Model Algorithm Based on Posterior Information of Information Matrix

引用

Journal of Shanghai Jiaotong university(Science) 2022年第5期27卷 671-679页

作者： HUANG Yinghao WU Yi YAO Lixiu CAI Yunze Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Jiao Tong UniversityShanghai200240China Department of Automation Key Laboratory of System Control and Information Processing of Ministry of EducationShanghai Jiao Tong UniversityShanghai200240China Alibaba(China)Co. Ltd.Hangzhou311121China

The tracking of maneuvering targets in radar networking scenarios is studied in this *** the interacting multiple model algorithm and the expected-mode augmentation algorithm,the fixed base model set leads to a mismatch between the model set and the target motion mode,which causes the reduction on tracking *** adaptive grid-expected-mode augmentation variable structure multiple model algorithm is *** adaptive grid algorithm based on the turning model is extended to the two-dimensional pattern space to realize the self-adaptation of the model ***,combining with the unscented information filtering,and by interacting the measurement information of neighboring radars and iterating information matrix with consistency strategy,a distributed target tracking algorithm based on the posterior information of the information matrix is *** the problem of filtering divergence while target is leaving radar surveillance area,a k-coverage algorithm based on particle swarm optimization is applied to plan the radar motion trajectory for achieving filtering convergence.

关键词： radar network system variable structure multiple model consistency filtering information matrix particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

GAN-DIRNet:A Novel Deformable image Registration Approach for Multimodal Histological images

引用

Computers, Materials & Continua 2024年第7期80卷 487-506页

作者： Haiyue Li Jing Xie Jing Ke Ye Yuan Xiaoyong Pan Hongyi Xin Hongbin Shen Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong Universityand Key Laboratory of System Control and Information ProcessingMinistry of Education of ChinaShanghai200240China Department of Pathology Ruijin HospitalShanghai Jiao Tong UniversitySchool of MedicineShanghai200025China Department of Computer Science and Engineering Shanghai Jiao Tong UniversityShanghai200240China Global Institute of Future Technology Shanghai Jiao Tong UniversityShanghai200240China

Multi-modal histological image registration tasks pose significant challenges due to tissue staining operations causing partial loss and folding of *** neural network(CNN)and generative adversarial network(GAN)are pivotal inmedical image ***,existing methods often struggle with severe interference and deformation,as seen in histological images of conditions like Cushing’s *** argue that the failure of current approaches lies in underutilizing the feature extraction capability of the discriminator *** this study,we propose a novel multi-modal registration approach GAN-DIRNet based on GAN for deformable histological image *** begin with,the discriminators of two GANs are embedded as a new dual parallel feature extraction module into the unsupervised registration networks,characterized by implicitly extracting feature descriptors of specific ***,modal feature description layers and registration layers collaborate in unsupervised optimization,facilitating faster convergence and more precise ***,experiments and evaluations were conducted on the registration of the Mixed National Institute of Standards and Technology database(MNIST),eight publicly available datasets of histological sections and the Clustering-Registration-Classification-Segmentation(CRCS)dataset on the Cushing’s *** results demonstrate that our proposed GAN-DIRNet method surpasses existing approaches like DIRNet in terms of both registration accuracy and time efficiency,while also exhibiting robustness across different image types.

关键词： Histological images registration deformable registration generative adversarial network cushing’s disease machine learning computer vision

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：