检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Ramesh, Sanat Srivastav, Vinkle Alapatt, Deepak Yu, Tong Murali, Aditya Sestini, Luca Nwoye, Chinedu Innocent Hamoud, Idris Sharma, Saurav Fleurentin, Antoine Exarchakis, Georgios Karargyris, Alexandros Padoy, Nicolas ICube University of Strasbourg CNRS Strasbourg67000 France IHU Strasbourg Strasbourg67000 France Altair Robotics Lab Department of Computer Science University of Verona Verona37134 Italy Department of Electronics Information and Bioengineering Politecnico di Milano Milano20133 Italy

The field of surgical computer vision has undergone considerable breakthroughs in recent years with the rising popularity of deep neural network-based methods. However, standard fully-supervised approaches for training such models require vast amounts of annotated data, imposing a prohibitively high cost;especially in the clinical domain. Self-Supervised Learning (SSL) methods, which have begun to gain traction in the general computer vision community, represent a potential solution to these annotation costs, allowing to learn useful representations from only unlabeled data. Still, the effectiveness of SSL methods in more complex and impactful domains, such as medicine and surgery, remains limited and unexplored. In this work, we address this critical need by investigating four state-of-the-art SSL methods (MoCo v2, SimCLR, DINO, SwAV) in the context of surgical computer vision. We present an extensive analysis of the performance of these methods on the Cholec80 dataset for two fundamental and popular tasks in surgical context understanding, phase recognition and tool presence detection. We examine their parameterization, then their behavior with respect to training data quantities in semi-supervised settings. Correct transfer of these methods to surgery, as described and conducted in this work, leads to substantial performance gains over generic uses of SSL - up to 7.4% on phase recognition and 20% on tool presence detection - as well as state-of-the-art semi-supervised phase recognition approaches by up to 14%. Further results obtained on a highly diverse selection of surgical datasets exhibit strong generalization properties. The code is available at https://***/CAMMA-public/SelfSupSurg. © 2022, CC BY-SA.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Advancing Speaker Embedding Learning: Wespeaker Toolkit for Research and Production

SSRN

引用

SSRN 2024年

作者： Wang, Shuai Chen, Zhengyang Han, Bing Wang, Hongji Liang, Chengdong Zhang, Binbin Xiang, Xu Ding, Wen Rohdin, Johan Silnova, Anna Qian, Yanmin Li, Haizhou Shenzhen Institute of Big Data Guangdong Shenzhen China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Tencent Ethereal Audio Lab Tencent Corporation Shenzhen China Horizon Robotics Beijing China NVIDIA Shanghai China Brno University of Technology Faculty of Information Technology IT4I Centre of Excellence Czech Republic School of Data Science The Chinese University of Hong Kong Guangdong Shenzhen China

Speaker modeling plays a crucial role in various tasks, and fixed-dimensional vector representations, known as speaker embeddings, are the predominant modeling approach. These embeddings are typically evaluated within the framework of speaker verification, yet their utility extends to a broad scope of related tasks including speaker diarization, speech synthesis, voice conversion, and target speaker extraction. This paper presents Wespeaker, a user-friendly toolkit designed for both research and production purposes, dedicated to the learning of speaker embeddings. Wespeaker offers scalable data management, state-of-the-art speaker embedding models, and self-supervised learning training schemes with the potential to leverage large-scale unlabeled real-world data. The toolkit incorporates structured recipes that have been successfully adopted in winning systems across various speaker verification challenges, ensuring highly competitive results. For production-oriented development, Wespeaker integrates CPU- and GPUcompatible deployment and runtime codes, supporting mainstream platforms such as Windows, Linux, Mac and on-device chips such as horizon X3’PI. Wespeaker also provides off-the-shelf high-quality speaker embeddings by providing various pretrained models, which can be effortlessly applied to different tasks that require speaker modeling. The toolkit is publicly available at https://***/wenet-e2e/wespeaker. © 2024, The Authors. All rights reserved.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

redPATH:Reconstructing the Pseudo Development Time of Cell Lineages in Single-cell RNA-seq Data and Applications in Cancer

引用

Genomics, Proteomics & Bioinformatics 2021年第2期19卷 292-305页

作者： Kaikun Xie Zehua Liu Ning Chen Ting Chen Institute for Artificial Intelligence State Key Lab of Intelligent Technology and SystemsDepartment of Computer Science and TechnologyTsinghua UniversityBeijing 100084China Tsinghua-Fuzhou Institute of Digital Technology Beijing National Research Center for Information Science and TechnologyTsinghua UniversityBeijing 100084China Center for Computational and Integrative Biology Massachusetts General HospitalHarvard Medical SchoolBostonMA 02114USA Department of Molecular Biology Massachusetts General HospitalHarvard Medical SchoolBostonMA 02114USA Broad Institute of Massachusetts Institute of Technology and Harvard CambridgeMA 02142USA

The recent advancement of single-cell RNA sequencing(scRNA-seq)technologies facilitates the study of cell lineages in developmental processes and *** this study,we developed a computational method,called redPATH,to reconstruct the pseudo developmental time of cell lineages using a consensus asymmetric Hamiltonian path ***,we developed a novel approach to visualize the trajectory development and implemented visualization methods to provide biological *** validated the performance of redPATH by segmenting different stages of cell development on multiple neural stem cell and cancer datasets,as well as other single-cell transcriptome *** particular,we identified a stem cell-like subpopulation in malignant glioma *** cells express known proliferative markers,such as GFAP,ATP1A2,IGFBPL1,and ALDOC,and remain silenced for quiescent markers such as ***,we identified MCL1 as a significant gene that regulates cell apoptosis and CSF1R for reprogramming macrophages to control tumor *** conclusion,redPATH is a comprehensive tool for analyzing scRNA-seq datasets along the pseudo developmental *** is available at https://***/tinglabs/redPATH.

关键词： Single-cell pseudotime reconstruction Consensus Hamiltonian path Cell differentiation Cell proliferation Cell development and diseases

来源：评论

学校读者我要写书评

暂无评论

What can real information content tell us about compressing climate model data?

What can real information content tell us about compressing ...

引用

IEEE/ACM International Workshop on Data Analysis and Reduction for Big Scientific Data (DRBSD-5)

作者： Hayden Sather Alexander Pinard Allison H. Baker Dorit M. Hammerling Department of Computer Science Colorado School of Mines Golden CO USA Applied Mathematics and Statistics Colorado School of Mines Golden CO USA Computational and Information Systems Lab National Center for Atmospheric Research Boulder CO USA

ISBN: (纸本)9781665463386

The massive data volumes produced by climate simulation models create an urgent need for data reduction. Lossy compression in particular is a solution that can significantly reduce storage requirements, however, a tradeoff must be made between the amount of compression applied and the scientific integrity of the data. Determining how much compression can be applied is therefore vital for applying lossy compression. One particular metric for gauging the quality of compression is the percentage of real information present in the original data that is preserved in the compressed data. We compute bitwise real information content for several climate variables from the popular Community Earth System Model, and we investigate the amount of compression that can be applied to each of these climate variables using two popular compression algorithms designed for floating-point data while preserving 99% of the real information content. The analysis of the real information content of data after lossy compression has been applied shows a helpful visualization of how compression artifacts have been introduced to the data. Finally, we demonstrate how this real information content can be used in a straightforward manner to determine compressor settings for our data.

关键词： Measurement Earth Analytical models Data analysis Conferences computational modeling Data visualization

来源：评论

学校读者我要写书评

暂无评论

Exploring the Needle Tip Interaction Force with Retinal Tissue Deformation in Vitreoretinal Surgery

Exploring the Needle Tip Interaction Force with Retinal Tiss...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Simon Pannek Shervin Dehghani Michael Sommersperger Peiyao Zhang Peter Gehlbach M. Ali Nasseri Iulian Iordachita Nassir Navab Department of Computer Science Technische Universität München München Germany Laboratory for Computational Sensing and Robotics Johns Hopkins University Baltimore MD USA Wilmer Eye Institute Johns Hopkins Hospital Baltimore MD USA Augenklinik und Poliklinik Klinikum Rechts der Isar der Technische Universität München München Germany Professor and the Chair for Computer Aided Medical Procedures & Augmented Reality Technical University of Munich Munich Germany Adjunct Professor at the Whiting School of Engineering Johns Hopkins University Baltimore MD USA

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Recent advancements in age-related macular degeneration treatments necessitate precision delivery into the subretinal space, emphasizing minimally invasive procedures targeting the retinal pigment epithelium (RPE)-Bruch’s membrane complex without causing trauma. Even for skilled surgeons, the inherent hand tremors during manual surgery can jeopardize the safety of these critical *** has fostered the evolution of robotic systems designed to prevent such tremors. These robots are enhanced by FBG sensors, which sense the small force interactions between the surgical instruments and retinal tissue. To enable the community to design algorithms taking advantage of such force feedback data, this paper focuses on the need to provide a specialized dataset, integrating optical coherence tomography (OCT) imaging together with the aforementioned force *** introduce a unique dataset, integrating force sensing data synchronized with OCT B-scan images, derived from a sophisticated setup involving robotic assistance and OCT integrated microscopes. Furthermore, we present a neural network model for image-based force estimation to demonstrate the dataset’s applicability.

关键词： Force Estimation Pigments Robot sensing systems Retina Needles Robot learning

来源：评论

学校读者我要写书评

暂无评论

BroadCAM: Outcome-agnostic Class Activation Mapping for Small-scale Weakly Supervised Applications

arXiv

引用

arXiv 2023年

作者： Lin, Jiatai Han, Guoqiang Xu, Xuemiao Liang, Changhong Wong, Tien-Tsin Chen, C.L. Philip Liu, Zaiyi Han, Chu The School of Computer Science and Engineering South China University of Technology Guangdong Guangzhou510006 China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangzhou510080 China Southern Medical University Guangzhou510080 China School of Computer Science and Engineering South China University of Technology State Key Laboratory of Subtropical Building Science Ministry of Education Key Laboratory of Big Data and Intelligent Robot Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong

Class activation mapping (CAM), a visualization technique for interpreting deep learning models, is now commonly used for weakly supervised semantic segmentation (WSSS) and object localization (WSOL). It is the weighted aggregation of the feature maps by activating the high class-relevance ones. Current CAM methods achieve it relying on the training outcomes, such as predicted scores (forward information), gradients (backward information), etc. However, when with small-scale data, unstable training may lead to less effective model outcomes and generate unreliable weights, finally resulting in incorrect activation and noisy CAM seeds. In this paper, we propose an outcome-agnostic CAM approach, called BroadCAM, for small-scale weakly supervised applications. Since broad learning system (BLS) is independent to the model learning, BroadCAM can avoid the weights being affected by the unreliable model outcomes when with small-scale data. By evaluating BroadCAM on VOC2012 (natural images) and BCSS-WSSS (medical images) for WSSS and OpenImages30k for WSOL, BroadCAM demonstrates superior performance than existing CAM methods with small-scale data (less than 5%) in different CNN architectures. It also achieves SOTA performance with large-scale training data. Extensive qualitative comparisons are conducted to demonstrate how BroadCAM activates the high class-relevance feature maps and generates reliable CAMs when with small-scale training data. © 2023, CC BY.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Automatic detection of lung nodule in CT scan slices using CNN segmentation schemes: A study

Automatic detection of lung nodule in CT scan slices using C...

引用

2022 International Conference on Machine Learning and Data Engineering, ICMLDE 2022

作者： Kadry, Seifedine Herrera-Viedma, Enrique Crespo, Rubén González Krishnamoorthy, Sujatha Rajinikanth, Venkatesan Faculty of Applied Computing and Technology Noroff University College Kristiansand94612 Norway Research Institute in Data Science and Computational Intelligence University of Granada Andalusian Granada Spain Computer Science Department School of Engineering and Technology Universidad Internacional de la Rioja 26006 Spain Zhejiang Bioinformatics International Science and Technology Cooperation Center Wenzhou-Kean University Zhejiang Province China Wenzhou Municipal Key Lab of Applied Biomedical and Biopharmaceutical Informatics Wenzhou-Kean University Zhejiang Province China Department of Electronics and Instrumentation Engineering St. Joseph's College of Engineering OMR Tamil Nadu Chennai600119 India

The lung is one of the prime respiratory organs in human physiology, and its abnormality will severely disrupt the respiratory system. Lung Nodule (LN) is one of the abnormalities, and early screening and treatment are necessary to reduce its harshness. The proposed work aims to implement the Convolutional-Neural-Network (CNN) segmentation methodology to extract the LN in various lung CT slices, such as axial, coronal, and sagittal planes. This work consists of the following phases;(i) Image collection and pre-processing, (ii) Ground-truth generation, (iii) CNN-supported segmentation, and (iv) Performance evaluation and validation. In this work, the merit of pre-trained CNN segmentation schemes is verified using (i) One-fold training and (ii) Two-fold training methods. The test images for this study are collected from The Cancer Imaging Archive (TCIA) database. The experimental investigation is executed using Python®, and the outcome of this study confirms that the VGG-SegNet helps to get better values of Jaccard (>88%), Dice (>93%), and Accuracy (>96%) compared to other CNN methods. © 2023 The Authors. Published by Elsevier B.V.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Deep and handcrafted feature supported diabetic retinopathy detection: A study

Deep and handcrafted feature supported diabetic retinopathy ...

引用

2022 International Conference on Machine Learning and Data Engineering, ICMLDE 2022

作者： Kadry, Seifedine Crespo, Rubén González Herrera-Viedma, Enrique Krishnamoorthy, Sujatha Rajinikanth, Venkatesan Faculty of Applied Computing and Technology Noroff University College Kristiansand94612 Norway Computer Science Department School of Engineering and Technology Universidad Internacional de la Rioja Andalusia26006 Spain Research Institute in Data Science and Computational Intelligence University of Granada Granada Spain Zhejiang Bioinformatics International Science and Technology Cooperation Center Wenzhou-Kean University Zhejiang Province China Wenzhou Municipal Key Lab of Applied Biomedical and Biopharmaceutical Informatics Wenzhou-Kean University Zhejiang Province China Department of Electronics and Instrumentation Engineering St. Joseph's College of Engineering OMR Tamil Nadu Chennai600119 India

The eye is the prime sensory organ in physiology, and the abnormality in the eye severely influences the vision system. Therefore, eye irregularity is commonly assessed using imaging schemes, and Fundus Retinal Image (FRI) supported eye screening is one of the ophthalmological practices. This work proposed a Deep-Learning Procedure (DLP) to recognize Diabetic Retinopathy (DR) in FI. The proposed work presents the experimental work with different DLP methods found in the literature. This work is executed with two modes;(i) DR detection using conventional deep-features and (ii) DR discovery using deep ensemble features. To demonstrate this work, 1800 fundus images (900 regular and 900 DR class) are considered for the assessment, and the advantage of proposed plan is confirmed using various performance metrics. The experimental outcome of this study confirms that the AlexNet-based detection provides a better detection (>96%), and the deep ensemble features of AlexNet, VGG16, and ResNet18 provide a detection accuracy of >98% on the chosen FRI database. © 2022 Elsevier B.V.. 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

Unprecedented Smart Algorithm for Uninterrupted SDN Services During DDoS Attack

引用

computers, Materials & Continua 2022年第1期70卷 875-894页

作者： Muhammad Reazul Haque Saw Chin Tan Zulfadzli Yusoff Kashif Nisar Rizaludin Kaspin Iram Haider Sana Nisar J.P.C.Rodrigues Bhawani Shankar Chowdhry Muhammad AslamUqaili Satya Prasad Majumder Danda B.Rawat Richard Etengu Rajkumar Buyya Faculty of Computing&Informatics Multimedia UniversityPersiaranMultimediaCyberjaya63100SelangorMalaysia Faculty of Engineering Multimedia UniversityPersiaran MultimediaCyberjaya63100SelangorMalaysia Faculty of Computing and Informatics University Malaysia SabahJalan UMSKota Kinabalu Sabah88400Malaysia Telekom Malaysia Research&Development TM Innovation Centre63000CyberjayaSelangorMalaysia Federal University of Piauí(UFPI) TeresinaPIBrazil Instituto de Telecomunica珲es 6201-001Covilh?Portugal National Center of Robotics and Automation-Condition Monitoring Systems Lab MUETJamshoroPakistan Department of Electrical and Electronic Engineering BUETDhaka1205Bangladesh Department of Electrical Engineering and Computer Science Data Science and Cybersecurity CenterHoward UniversityWashingtonDCUSA Cloud Computing and Distributed Systems(CLOUDS)Laboratory School of Computing and Information SystemsThe University of MelbourneMelbourneVIC 3053Australia

In the design and planning of next-generation Internet of Things(IoT),telecommunication,and satellite communication systems,controller placement is crucial in software-defined networking(SDN).The programmability of the SDN controller is sophisticated for the centralized control system of the entire ***,it creates a significant loophole for the manifestation of a distributed denial of service(DDoS)attack ***,recently a Distributed Reflected Denial of Service(DRDoS)attack,an unusual DDoS attack,has been ***,minimal deliberation has given to this forthcoming single point of SDN infrastructure failure ***,recently the high frequencies of DDoS attacks have increased *** this paper,a smart algorithm for planning SDN smart backup controllers under DDoS attack scenarios has *** proposed smart algorithm can recommend single or multiple smart backup controllers in the event of DDoS *** obtained simulated results demonstrate that the validation of the proposed algorithm and the performance analysis achieved 99.99%accuracy in placing the smart backup controller under DDoS attacks within 0.125 to 46508.7 s in SDN.

关键词： SDN smart algorithm RTZLK-DAASCP DDoS attack DRDoS

来源：评论

学校读者我要写书评

暂无评论

Stochastic Sensitivity Regularized Autoencoder for Robust Feature Learning

Stochastic Sensitivity Regularized Autoencoder for Robust Fe...

引用

IEEE International Conference on Cognitive Informatics

作者： Jianjun Zhang Ting Wang Wing W. Y. Ng Witold Pedrycz Sam Kwong School of Computer Science and Engineering South China University of Technology Guangzhou Guangdong China Department of Radiology Guangzhou First People's Hospital School of Medicine South China University of Technology Guangzhou Guangdong China Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information School of Computer Science and Engineering South China University of Technology Guangzhou Guangdong China Department of Electrical and Computer Engineering University of Alberta Edmonton Alberta Canada Department of Computer Science Hong Kong City University Hong Kong China

We present a new regularized autoencoder for robust feature learning. The regularization, implying stochastic sensitivity, is defined as the sum of entries of the absolute covariance matrix of the output perturbation at each layer of the autoencoder. The advantages of the stochastic sensitivity regularization are two-fold. Firstly, we show that the classical Frobenius norm regularization effectively enforces the network to be insensitive to input perturbation and that the Frobenius norm regularization is a special case of the proposed stochastic sensitivity regularization which enables the proposed method to train an autoencoder for robust feature learning. Secondly, we also show that the stochastic sensitivity regularization attempts to drive the network to learn a set of decorrelated feature maps which removes redundant information and thus improves generalization capabilities. These two properties enable the autoencoder to learn a set of robust and diverse feature maps. Finally, the efficacy and the robustness of the proposed regularization method are confirmed a nd quantified by comparing it against existing regularized auto encoders over a range of tasks.

关键词： Representation learning Sensitivity Perturbation methods Robustness Decorrelation Task analysis Covariance matrices

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：