检索结果-内蒙古大学图书馆

Cross-dimensional knowledge-guided synthesizer trained with unpaired multimodality MRIs

Soft Computing 2024年第13-14期28卷 8393-8408页

作者： Zhou, Binjia Zhou, Qianwei Miao, Chenghang Liu, Yibo Guo, Yuan College of Computer Science and Technology Zhejiang University of Technology Hangzhou310023 China Key Laboratory of Visual Media Intelligent Processing Technology of Zhejiang Province Hangzhou310023 China Department of Radiology Guangzhou First People’s Hospital South China University of Technology Guangzhou510180 China

Magnetic resonance images (MRIs) of different modalities have different reference values for pathological diagnosis. The difficulty of obtaining multimodal MRIs makes it effective to synthesize medical images of missing modalities from existing one. To train a one-for-all synthesizer with limited number of unpaired MRIs, a novel cross-dimensional knowledge-guided generative adversarial network (CKG–GAN) is proposed. In CKG–GAN, a cross-dimensional knowledge transfer network is utilized to measure the perceptual similarity of 2D images (slices of MRIs) from source and synthesized modalities, the knowledge of which is transferred from a pre-trained 3D network without accessing its private training data set. We evaluate the proposed model for three tasks on BraTs2018 and BraTs2021 data sets, using one modality of T1, T2 or Flair to synthesize the other two modalities without changing the content. The results show that compared with the current state-of-the-art methods, our method improves the performance by 2–7%. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Auto-StyleMixer: A universal adaptive N-to-One framework for cross-domain data augmentation

引用

Knowledge-Based Systems 2025年 323卷

作者： Zhang, Huihuang Hu, Haigen Cao, Bin Zhang, Xiaoqin College of Computer Science and Technology Zhejiang University of Technology Hangzhou310023 China Key Laboratory of Visual Media Intelligent Processing Technology of Zhejiang Province Hangzhou310023 China

Existing domain generalization (DG) approaches that rely on traditional techniques like the Fourier transform and normalization can extract style information for cross-domain data augmentation by confusing styles to enhance model generalization. However, these one-to-one methods face two significant challenges: (1) They cannot effectively extract pure style information in deep layers, potentially disrupting the ability to learn content information. (2) Due to the unknown purity of the extracted style information, considerable resources are required to find the optimal style-mixing configuration based on manual experience. To address these challenges, we propose a universal N-to-one cross-domain data augmentation framework, named Auto-StyleMixer, which not only extracts purer style information but also adapts to learn style-mixing configurations without any manual intervention. The proposed framework can embed any traditional style extraction techniques and can be integrated as a plug-and-play module into any architecture, whether CNNs or Transformers. Extensive experiments demonstrate the effectiveness of the proposed method, showing that it achieves state-of-the-art performance on five DG benchmarks. The source code is available at https://***/Jin-huihuang/AutoStyleMixer. © 2025 Elsevier B.V.

关键词： Cross-domain augmentation Domain generalization Style mixing Transfer leaning

来源：评论

学校读者我要写书评

暂无评论

Joint Feature Learning for Cell Segmentation Based on Multi-scale Convolutional U-Net

Joint Feature Learning for Cell Segmentation Based on Multi-...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Jin, Zhichao Hu, Haigen Zhou, Qianwei Guan, Qiu Li, Xiaoxin Chen, Qi Zhejiang University of Technology College of Computer Science and Technology Hangzhou310023 China Key Laboratory of Visual Media Intelligent Processing Technology of Zhejiang Province 310023 China

ISBN: (纸本)9781665468190

A major challenge in the analysis of tissue imaging data is cell segmentation, the task of identifying precisely the boundary of each cell in a microscopic image. The cell segmentation task is still challenging due to the variable shapes, large size differences, uneven grayscale, and dense distribution of biological cells in microscopic images. In this paper, we propose a joint feature learning method that integrates the density and boundary branch into a multi-scale convolutional U-Net (MC-Unet). To enhance the supervision of cell density and boundary detection, the density and boundary loss is constructed to guide the joint learning of multiple features, where the density loss branch can address the challenges posed by high density, while the boundary loss branch can address the problems of unclear cell boundaries and partial cell occlusion. A series of experiments on different cell datasets show that two auxiliary branches improve the learning of features on cell density and cell boundaries and that the proposed method is effective on different segmentation models. The code is available at: https://***/HuHaigen/Joint-Feature-Learning-for-Cell-Segmentation. © 2022 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Fabrication of coconut shell-derived porous carbons for CO_(2) adsorption application

引用

Frontiers of Chemical Science and Engineering 2023年第8期17卷 1122-1130页

作者： Jiali Bai Jiamei Huang Qiyun Yu Muslum Demir Eda Akgul Bilge Nazli Altay Xin Hu Linlin Wang Key Laboratory of the Ministry of Education for Advanced Catalysis Materials Zhejiang Normal UniversityJinhua 321004China Department of Chemical Engineering Osmaniye Korkut Ata UniversityOsmaniye 80000Turkey College of Engineering Technology Print and Graphic Media ScienceRochester Institute of TechnologyNew York 14623USA Institute of Pure and Applied Sciences Marmara UniversityIstanbul 34722Turkey Key Laboratory of Urban Rail Transit Intelligent Operation and Maintenance Technology and Equipment of Zhejiang Province College of EngineeringZhejiang Normal UniversityJinhua 321004China

Biomass-derived porous carbons have been considered as the most potential candidate for effective CO_(2) adsorbent thanks to being widely-available precursor and having highly porous structure and stable chemical/physical ***,the biomass-derived porous carbons still suffer from the poor optimization process in terms of the synthesis ***,we have successfully fabricated coconut shell-derived porous carbon by a simple one-step synthesis *** as-prepared carbon exhibits advanced textual activity together with well-designed micropore morphology and possesses oxygen-containing functional groups(reached 18.81 wt%)within the carbon *** on the different activating temperatures(from 700 to 800℃)and KOH/biomass mass ratios(from 0.3 to 1),the 750℃ and 0.5 mass ratio were found to be enabling the highest CO_(2) capture *** optimal adsorbent was achieved a high CO_(2) uptake capacity of 5.92 and 4.15 mmol·g^(−1) at 0 and 25℃(1 bar),*** importantly,as-prepared carbon adsorbent exhibited moderate isosteric heat of adsorption and high CO_(2)/N_(2) *** results were revealed not only the textural feature but also the surface functional groups critically determine the CO_(2) capture performance,indicating coconut shell-derived porous carbon has a considerable potential as a solid-state adsorbent for the CO_(2) capture.

关键词： porous carbons CO_(2)adsorption KOH activation single step reaction biomass

来源：评论

学校读者我要写书评

暂无评论

Joint Feature Learning for Cell Segmentation Based on Multi-scale Convolutional U-Net

Joint Feature Learning for Cell Segmentation Based on Multi-...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Zhichao Jin Haigen Hu Qianwei Zhou Qiu Guan Xiaoxin Li Qi Chen College of Computer Science and Technology Zhejiang University of Technology Hangzhou China Key Laboratory of Visual Media Intelligent Processing Technology of Zhejiang Province China

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

关键词： Representation learning Convolutional codes Image segmentation Shape Microscopy Neural networks Gray-scale

来源：评论

学校读者我要写书评

暂无评论

HDConv: Heterogeneous Kernel-Based Dilated Convolutions

SSRN

引用

SSRN 2023年

作者： Hu, Haigen Yu, Chenghan Zhou, Qianwei Guan, Qiu Feng, Hailin College of Computer Science and Technology Zhejiang University of Technology Hangzhou310014 China Key Laboratory of Visual Media Intelligent Processing Technology of Zhejiang Province Hangzhou310023 China School of Mathematical and Computer Science Zhejiang A & F University Hangzhou310023 China

Dilated convolution is widely used in various computer vision tasks due to its ability to expand the receptive field while maintaining the resolution of feature maps. However, the critical challenge is the gridding problem caused by the isomorphic structure of the dilated convolution, where the holes filled in the dilated convolution destroy the integrity of the extracted information and cut off the relevance of neighboring pixels. In this work, a novel heterogeneous dilated convolution named HDConv is proposed to address this issue by setting independent dilation rates on grouped channels while keeping the general convolution operation. The heterogeneous structure can effectively avoid the gridding problem while introducing multi-scale kernels in the filters. Based on the heterogeneous structure of the proposed HDConv, we also explore the benefit of large receptive fields to feature extraction by comparing different combinations of dilated rates. Finally, a series of experiments are conducted to verify the effectiveness of some computer vision tasks, such as image segmentation and object detection. The results show the proposed HDConv can achieve a competitive performance on ADE20K, Cityscapes, COCO-Stuff10k, COCO, and a medical image dataset UESTC-COVID-19. The proposed module can readily replace conventional convolutions in existing convolutional neural networks (i.e., plug-and-play), and it is promising to further extend dilated convolution to wider scenarios. © 2023, 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

Tropical Cyclones Tracking Based on Satellite Cloud Images: Database and Comprehensive Study 1

引用

27th International Conference on Multimedia Modeling, MMM 2021

作者： Huang, Cheng Chan, Sixian Bai, Cong Ding, Weilong Zhang, Jinglin College of Computer Science Zhejiang University of Technology Hangzhou China Key Laboratory of Visual Media Intelligent Processing Technology of Zhejiang Province Hangzhou China College of Atmospheric Sciences Nanjing University of Information Science and Technology Nanjing China

ISBN: (数字)9783030678357

ISBN: (纸本)9783030678340

The tropical cyclone is one of disaster weather that cause serious damages for human community. It is necessary to forecast the tropical cyclone efficiently and accurately for reducing the loss caused by tropical cyclones. With the development of computer vision and satellite technology, high quality meteorological data can be got and advanced technologies have been proposed in visual tracking domain. This makes it possible to develop algorithms to do the automatic tropical cyclone tracking which plays a critical role in tropical cyclone forecast. In this paper, we present a novel database for Typical Cyclone Tracking based on Satellite Cloud Image, called TCTSCI. To the best of our knowledge, TCTSCI is the first satellite cloud image database of tropical cyclone tracking. It consists of 28 video sequences and totally 3,432 frames with 6001 × 6001 pixels. It includes tropical cyclones of five different intensities distributing in 2019. Each frame is scientifically inspected and labeled with the authoritative tropical cyclone data. Besides, to encourage and facilitate research of multimodal methods for tropical cyclone tracking, TCTSCI provides not only visual bounding box annotations but multimodal meteorological data of tropical cyclones. We evaluate 11 state-of-the-art and widely used trackers by using OPE and EAO metrics and analyze the challenges on TCTSCI for these trackers. © 2021, Springer Nature Switzerland AG.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Extending Chest X-Ray with Multi Label Disease Sequence 17th

Extending Chest X-Ray with Multi Label Disease Sequence

引用

17th International Forum on Digital TV and Wireless Multimedia Communication, IFTC 2020

作者： Zheng, Anqi Bai, Cong Liu, Ning College of Computer Science Zhejiang University of Technology Hangzhou310023 China Key Laboratory of Visual Media Intelligent Processing Technology of Zhejiang Province Hangzhou310023 China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai200000 China

ISBN: (纸本)9789811611933

Doctors need to spend a lot of time and energy on reading the patient’s medical images to write the corresponding diagnosis report. Therefore, it is interesting to use the artificial intelligence technology on the research of automatic generation of medical imaging reports. In order to improve the accuracy of the report generation, we extend the Chest X-Ray dataset with multi label of disease combining the medical characteristics of imaging reports. In this paper, we give the concrete steps of expanding the dataset. The original dataset contains 8121 chest X-ray images from different perspectives and 3996 diagnostic reports. Based on the original dataset, we pick out the complete data pair and use a multi label classification network named CheXNet to expand the dataset with the multi label disease sequence. The multi disease label sequence includes the judgment results of 14 common thoracic diseases. After manual correction, we get a dataset which contains 3119 multimodal data pairs. Each data pair is composed of two chest X-ray images and corresponding diagnostic reports, as well as a binary multi label sequence. The extended dataset is more useful for the task of medical diagnostic reports generation. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

DEEP CO-SUPERVISION and ATTENTION FUSION STRATEGY for AUTOMATIC COVID-19 LUNG INFECTION SEGMENTATION on CT IMAGES

arXiv

引用

arXiv 2021年

作者： Hu, Haigen Guan, Qiu Li, Xiaoxin Zhou, Qianwei Ruan, Su College of Computer Science and Technology Zhejiang University of Technology China Key Laboratory of Visual Media Intelligent Processing Technology of Zhejiang Province China University of Rouen Normandy France

Due to the irregular shapes,various sizes and indistinguishable boundaries between the normal and infected tissues, it is still a challenging task to accurately segment the infected lesions of COVID-19 on CT images. In this paper, a novel segmentation scheme is proposed for the infections of COVID-19 by enhancing supervised information and fusing multi-scale feature maps of different levels based on the encoder-decoder architecture. To this end, a deep collaborative supervision (Co-supervision) scheme is proposed to guide the network learning the features of edges and semantics. More specifically, an Edge Supervised Module (ESM) is firstly designed to highlight low-level boundary features by incorporating the edge supervised information into the initial stage of down-sampling. Meanwhile, an Auxiliary Semantic Supervised Module (ASSM) is proposed to strengthen high-level semantic information by integrating mask supervised information into the later stage. Then an Attention Fusion Module (AFM) is developed to fuse multiple scale feature maps of different levels by using an attention mechanism to reduce the semantic gaps between high-level and low-level feature maps. Finally, the effectiveness of the proposed scheme is demonstrated on four various COVID-19 CT datasets. The results show that the proposed three modules are all promising. Based on the baseline (ResUnet), using ESM, ASSM, or AFM alone can respectively increase Dice metric by 1.12%, 1.95%,1.63% in our dataset, while the integration by incorporating three models together can rise 3.97%. Compared with the existing approaches in various datasets, the proposed method can obtain better segmentation performance in some main metrics, and can achieve the best generalization and comprehensive *** code is publicly available at https://***/HuHaigen/COVID-19-Lung-Infection-Segentation or https://***/slz674763180/COVID19. The package includes the proposed three modules and joint loss function f

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

ADAPTIVELY CUSTOMIZING ACTIVATION FUNCTIONS for VARIOUS LAYERS

arXiv

引用

arXiv 2021年

作者： Hu, Haigen Liu, Aizhu Guan, Qiu Li, Xiaoxin Chen, Shengyong Zhou, Qianwei College of Computer Science and Technology Zhejiang University of Technology China Key Laboratory of Visual Media Intelligent Processing Technology of Zhejiang Province China School of Computer Science and Engineering Tianjin University of Technology China

To enhance the nonlinearity of neural networks and increase their mapping abilities between the inputs and response variables, activation functions play a crucial role to model more complex relationships and patterns in the data. In this work, a novel methodology is proposed to adaptively customize activation functions only by adding very few parameters to the traditional activation functions such as Sigmoid, Tanh, and ReLU. To verify the effectiveness of the proposed methodology, some theoretical and experimental analysis on accelerating the convergence and improving the performance is presented, and a series of experiments are conducted based on various network models (such as AlexNet, VGGNet, GoogLeNet, ResNet and DenseNet), and various datasets (such as CIFAR10, CIFAR100, miniImageNet, PASCAL VOC and COCO). To further verify the validity and suitability in various optimization strategies and usage scenarios, some comparison experiments are also implemented among different optimization strategies (such as SGD, Momentum, AdaGrad, AdaDelta and ADAM) and different recognition tasks like classification and detection. The results show that the proposed methodology is very simple but with significant performance in convergence speed, precision and generalization, and it can surpass other popular methods like ReLU and adaptive functions like Swish in almost all experiments in terms of overall *** code is publicly available at https://***/HuHaigen/Adaptively-Customizing-Activation-Functions. The package includes the proposed three adaptive activation functions for reproducibility purposes. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep learning

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：