检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wu, Yizheng Pan, Zhiyu Wang, Kewei Li, Xingyi Cui, Jiahao Xiao, Liwen Lin, Guosheng 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 S-Lab Nanyang Technological University Singapore639798 Singapore Nanyang Technological University Singapore639798 Singapore

Large-scale datasets with point-wise semantic and instance labels are crucial to 3D instance segmentation but also expensive. To leverage unlabeled data, previous semi-supervised 3D instance segmentation approaches have explored self-training frameworks, which rely on high-quality pseudo labels for consistency regularization. They intuitively utilize both instance and semantic pseudo labels in a joint learning manner. However, semantic pseudo labels contain numerous noise derived from the imbalanced category distribution and natural confusion of similar but distinct categories, which leads to severe collapses in self-training. Motivated by the observation that 3D instances are non-overlapping and spatially separable, we ask whether we can solely rely on instance consistency regularization for improved semi-supervised segmentation. To this end, we propose a novel self-training network InsTeacher3D to explore and exploit pure instance knowledge from unlabeled data. We first build a parallel base 3D instance segmentation model DKNet, which distinguishes each instance from the others via discriminative instance kernels without reliance on semantic segmentation. Based on DKNet, we further design a novel instance consistency regularization framework to generate and leverage high-quality instance pseudo labels. Experimental results on multiple large-scale datasets show that the InsTeacher3D significantly outperforms prior state-of-the-art semi-supervised approaches. Code is available: https://***/W1zheng/InsTeacher3D. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A hierarchical image matting model for blood vessel segmentation in fundus images

arXiv

引用

arXiv 2017年

作者： Fan, Zhun Lu, Jiewei Li, Wenji Wei, Caimin Huang, Han Cai, Xinye Chen, Xinjian Guangdong Provincial Key Laboratory of Digital Signal and Image Processing College of Engineering Shantou University Shan'tou515063 China Department of Mathematics Shantou University Shan'tou515063 China School of Software Engineering South China University of Technology Guang'zhou510006 China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Jiang'su210016 China Medical Image Processing and Analysis Lab School of Electronics and Information Engineering Soochow University Su'zhou215006 China

In this paper, a hierarchical image matting model is proposed to extract blood vessels from fundus images. More specifically, a hierarchical strategy utilizing the continuity and extendibility of retinal blood vessels is integrated into the image matting model for blood vessel segmentation. Normally the matting models require the user specified trimap, which separates the input image into three regions manually: the foreground, background and unknown regions. However, since creating a user specified trimap is a tedious and time-consuming task, region features of blood vessels are used to generate the trimap automatically in this paper. The proposed model has low computational complexity and outperforms many other state-of-art supervised and unsupervised methods in terms of accuracy, which achieves a vessel segmentation accuracy of 96.0%, 95.7% and 95.1% in an average time of 10.72s, 15.74s and 50.71s on images from three publicly available fundus image datasets DRIVE, STARE, and CHASE_DB1, respectively. Copyright © 2017, The Authors. All rights reserved.

关键词： Blood vessels

来源：评论

学校读者我要写书评

暂无评论

GazeGAN: A robust generative adversarial saliency model based on invariance analysis of human gaze during scene free viewing

arXiv

引用

arXiv 2019年

作者： Che, Zhaohui Borji, Ali Zhai, Guangtao Min, Xiongkuo Guo, Guodong Le Callet, Patrick Institute of Image Communication and Network Engineering Shanghai Key Laboratory of Digital Media Processing and Transmissions Shanghai Jiao Tong University Shanghai200240 China MarkableAI United States Institute of Deep Learning Baidu Research Department of Computer Science and Electrical Engineering West Virginia University MorgantownWV United States Equipe Image Perception et Interaction Laboratoire des Sciences du Numérique de Nantes Université de Nantes France

—Data size is the bottleneck for developing deep saliency models, because collecting eye-movement data is very time-consuming and expensive. Most of current studies on human attention and saliency modeling have used high-quality stereotype stimuli. In real world, however, captured images undergo various types of transformations. Can we use these transformations to augment existing saliency datasets? Here, we first create a novel saliency dataset including fixations of 10 observers over 1900 images degraded by 19 types of transformations. Second, by analyzing eye movements, we find that observers look at different locations over transformed versus original images. Third, we utilize the new data over transformed images, called data augmentation transformation (DAT), to train deep saliency models. We find that label-preserving DATs with negligible impact on human gaze boost saliency prediction, whereas some other DATs that severely impact human gaze degrade the performance. These label-preserving valid augmentation transformations provide a solution to enlarge existing saliency datasets. Finally, we introduce a novel saliency model based on generative adversarial network (dubbed GazeGAN). A modified U-Net is proposed as the generator of the GazeGAN, which combines classic "skip connections" with a novel "center-surround connection (CSC)", in order to leverage multi-level features. We also propose a histogram loss based on Alternative Chi-Square Distance (ACS HistLoss) to refine the saliency map in terms of luminance distribution. Extensive experiments and comparisons over 3 datasets indicate that GazeGAN achieves the best performance in terms of popular saliency evaluation metrics, and is more robust to various perturbations. We also provide a comprehensive quantitative comparison of 22 state-of-the-art saliency models on distorted images, which contributes a robustness benchmark for saliency community. Our code and data are available at: https://***/CZHQuality/

关键词： Luminance

来源：评论

学校读者我要写书评

暂无评论

A reduced-reference quality assessment scheme for blurred images

A reduced-reference quality assessment scheme for blurred im...

引用

IEEE Visual communications and image processing (VCIP)

作者： Zongxi Han Guangtao Zhai Yutao Liu Ke Gu Xinfeng Zhang Institute of Image Communication and Information Processing Shanghai Jiao Tong University Shanghai China Department of Computer Science Harbin Institute of Technology Harbin China School of Computer Science and Engineering Nanyang Technological University Singapore Rapid-Rich Object Search (ROSE) Lab Nanyang Technological University Singapore

ISBN: (纸本)9781509053179

In this paper, we propose a reduced-reference scheme for evaluating the quality of blurred images under the theory of free-energy principle. Specifically, the free-energy principle indicates that the brain tries to account for the input image with an internal generative model and the discrepancy between the image and its model-explained version, which can be measured by free energy, is related to the image's perceptual quality. Accordingly, we define a visual distance between the blurred image and its original image in free energy to evaluate the quality of the blurred image. Therefore, the proposed quality scheme belongs to reduced-reference methods, which needs some information from the original image for quality assessment. Experimental results on public databases, LIVE, TID2013 and C-SIQ, demonstrate the proposed method works in high consistency with subjective assessment results and outperforms representative image quality assessment approaches.

关键词： Brain modeling image quality Mathematical model Quality assessment Dictionaries Energy measurement

来源：评论

学校读者我要写书评

暂无评论

A General End-to-end Diagnosis Framework for Manufacturing Systems

arXiv

引用

arXiv 2018年

作者： Yuan, Ye Ma, Guijun Cheng, Cheng Zhou, Beitong Zhao, Huan Zhang, Hai-Tao Ding, Han State Key Lab of Digital Manufacturing Equipment and Technology Huazhong University of Science and Technology Wuhan430074 China School of Artificial Intelligence and Automation MOE Key Lab of Intelligent Control and Image Processing Huazhong University of Science and Technology Wuhan430074 China School of Mechanical Science and Engineering Huazhong University of Science and Technology Wuhan430074 China

The manufacturing sector is envisioned to be heavily influenced by artificial intelligence-based technologies with the extraordinary increases in computational power and data volumes1,2. A central challenge in manufacturing sector lies in the requirement of a general framework to ensure satisfied diagnosis and monitoring performances in different manufacturing applications. Here we propose a general data-driven, end-to-end framework for the monitoring of manufacturing systems. This framework, derived from deep learning techniques, evaluates fused sensory measurements to detect and even predict faults and wearing conditions. This work exploits the predictive power of deep learning to automatically extract hidden degradation features from noisy, time-course data. We have experimented the proposed framework on ten representative datasets drawn from a wide variety of manufacturing applications. Results reveal that the framework performs well in examined benchmark applications and can be applied in diverse contexts, indicating its potential use as a critical corner stone in smart manufacturing. Copyright © 2018, The Authors. All rights reserved.

关键词： Manufacture

来源：评论

学校读者我要写书评

暂无评论

Fast multiple reference frame selection algorithm based on H.264/AVC

引用

Sichuan Daxue Xuebao (Gongcheng Kexue Ban)/Journal of Sichuan University (Engineering Science Edition) 2005年第4期37卷 100-103页

作者： Teng, Guo-Wei Zhang, Zhao-Yang Zhang, Yi-Jun Zhang, Wen-Jun Key Lab. of Advanced Display and System Appl. Shanghai Univ. Shanghai 200072 China Inst. of Image Communication and Info. Processing Shanghai Jiaotong Univ. Shanghai 200030 China

A reference frame selection algorithm was proposed to fast determine the reference frames required by the current macroblock, which can avoid redundant reference frames. This algorithm can utilize the texture characteristic of sequence to estimate the possible number of reference frames, and further determine the best reference frame of 16 × 16, 8 × 8 and 4 × 4 modes according to the motion information and the monotony of RDO among different reference frames. So the likely reference frames of other modes may be adaptively chosen according to the correlation of reference frame selection with the above modes. The results showed that it can save about 30% of encoding time while maintaining nearly unchanged PSNR and bit-rate.

关键词： Video signal processing

来源：评论

学校读者我要写书评

暂无评论

Adversarial attacks and defenses in physiological computing:a systematic review

引用

National Science Open 2023年第1期2卷 62-90页

作者： Dongrui Wu Jiaxin Xu Weili Fang Yi Zhang Liuqing Yang Xiaodong Xu Hanbin Luo Xiang Yu Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and AutomationHuazhong University of Science and TechnologyWuhan 430074China Zhejiang Lab Hangzhou 311121China School of Civil and Hydraulic Engineering Huazhong University of Science and TechnologyWuhan 430074China College of Public Administration Huazhong University of Science and TechnologyWuhan 430074China Electrical Engineering and Computer Science Department University of MichiganAnn Arbor MI 48109USA School of Management and Sino-European Institute for Intellectual Property Huazhong University of Science and TechnologyWuhan 430074China

Physiological computing uses human physiological data as system inputs in real *** includes,or significantly overlaps with,brain-computer interfaces,affective computing,adaptive automation,health informatics,and physiological signal based *** computing increases the communication bandwidth from the user to the computer,but is also subject to various types of adversarial attacks,in which the attacker deliberately manipulates the training and/or test examples to hijack the machine learning algorithm output,leading to possible user confusion,frustration,injury,or even ***,the vulnerability of physiological computing systems has not been paid enough attention to,and there does not exist a comprehensive review on adversarial attacks to *** study fills this gap,by providing a systematic review on the main research areas of physiological computing,different types of adversarial attacks and their applications to physiological computing,and the corresponding defense *** hope this review will attract more research interests on the vulnerability of physiological computing systems,and more importantly,defense strategies to make them more secure.

关键词： physiological computing brain-computer interfaces health informatics biometrics machine learning adversarial attack

来源：评论

学校读者我要写书评

暂无评论

Graph Convolutional Network-based Functional-structural Sub-region Framework for Head and Neck Cancer Prognosis with PET/CT Imaging

Graph Convolutional Network-based Functional-structural Sub-...

引用

IEEE Symposium on Nuclear Science (NSS/MIC)

作者： Zidong Zhou Junyi Peng Guoyu Lin Huiqin Wu Wenbing Lv Lijun Lu School of Biomedical Engineering Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology Southern Medical University Guangdong Provincial Key Laboratory of Medical Image Processing Guangzhou China School of Information Science and Engineering Yunnan University Kunming China Pazhou Lab Guangzhou China

In order to improve the behavior of the prognostic model for patients with head and neck cancer (HNC), we constructed a graph convolutional network (GCN), characterizing the interaction of functional and structural information among different sub-regions of tumors in both PET and CT images. Sub-regions were obtained by using the Watershed-based method and were regarded as vertexes in the graph. The element of 1 in the adjacency matrix indicates corresponding two vertices are spatially contiguous, while the element of 0 indicates they are separated. The selected radiomics features were used to characterize each vertex. 642 HNC patients from 8 different centers were used. The best C-index of 0.767 was achieved by the combination of GCN and clinical parameters compared to the radiomics model (0.747) or GCN model (0.702). the proposed approach has great potential in aiding treatment decision-making.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A MULTI-SCALE SPATIAL TRANSFORMER U-NET FOR SIMULTANEOUSLY AUTOMATIC REORIENTATION AND SEGMENTATION OF 3D NUCLEAR CARDIAC imageS

arXiv

引用

arXiv 2023年

作者： Ni, Yangfan Zhang, Duo Ma, Gege Lu, Lijun Huang, Zhongke Zhu, Wentao Research Center for Human-Machine Augmented Intelligence Zhejiang Lab Hangzhou China School of Biomedical Engineering and Guangdong Provincial Key Laboratory of Medical Image Processing Southern Medical University Guangzhou China Department of Nuclear Medicine Sir Run Run Shaw Hospital Hangzhou China

Accurate reorientation and segmentation of the left ventricular (LV) is essential for the quantitative analysis of myocardial perfusion imaging (MPI), in which one critical step is to reorient the reconstructed transaxial nuclear cardiac images into standard short-axis slices for subsequent image processing. Small-scale LV myocardium (LV-MY) region detection and the diverse cardiac structures of individual patients pose challenges to LV segmentation operation. To mitigate these issues, we propose an end-to-end model, named as multi-scale spatial transformer UNet (MS-ST-UNet), that involves the multi-scale spatial transformer network (MSSTN) and multi-scale UNet (MSUNet) modules to perform simultaneous reorientation and segmentation of LV region from nuclear cardiac images. The proposed method is trained and tested using two different nuclear cardiac image modalities: 13N-ammonia PET and 99mTc-sestamibi SPECT. We use a multi-scale strategy to generate and extract image features with different scales. Our experimental results demonstrate that the proposed method significantly improves the reorientation and segmentation performance. This joint learning framework promotes mutual enhancement between reorientation and segmentation tasks, leading to cutting edge performance and an efficient image processing workflow. The proposed end-to-end deep network has the potential to reduce the burden of manual delineation for cardiac images, thereby providing multimodal quantitative analysis assistance for physicists. Copyright © 2023, The Authors. All rights reserved.

关键词： Ammonia

来源：评论

学校读者我要写书评

暂无评论

Cooperative label-Free Moving Target Fencing for Second-Order Multi-Agent Systems with Rigid Formation

arXiv

引用

arXiv 2023年

作者： Hu, Bin-Bin Zhang, Hai-Tao Shi, Yang School of Artificial Intelligence Automation Key Laboratory of Image Processing Intelligent Control State Key Lab of Digital Manufacturing Equipment and Technology Huazhong University of Science and Technology Wuhan430074 China Department of Mechanical Engineering University of Victoria VictoriaBCV8W 2Y2 Canada

This paper proposes a label-free controller for a second-order multi-agent system to cooperatively fence a moving target of variational velocity into a convex hull formed by the agents whereas maintaining a rigid formation. Therein, no label is predetermined for a specified agent. To attain a rigid formation with guaranteed collision avoidance, each controller consists of two terms: a dynamic regulator with an internal model to drive agents towards the moving target merely by position information feedback, and a repulsive force between each pair of adjacent agents. Significantly, sufficient conditions are derived to guarantee the asymptotic stability of the closed-loop systems governed by the proposed fencing controller. Rigorous analysis is provided to eliminate the strong nonlinear couplings induced by the label-free property. Finally, the effectiveness of the controller is substantiated by numerical simulations. Copyright © 2023, The Authors. All rights reserved.

关键词： Multi agent systems

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：