检索结果-内蒙古大学图书馆

EXplainable Neural-Symbolic Learning (X-NeSyL) methodology to fuse deep learning representations with expert knowledge graphs: The MonuMAI cultural heritage use case

arXiv

引用

arXiv 2021年

作者： Díaz-Rodríguez, Natalia Lamas, Alberto Sanchez, Jules Franchi, Gianni Donadello, Ivan Tabik, Siham Filliat, David Cruz, Policarpo Montes, Rosana Herrera, Francisco U2IS ENSTA Institut Polytechnique Paris Inria Flowers Palaiseau91762 France Free University of Bozen-Bolzano 39100 Italy DaSCI Andalusian Institute in Data Science and Computational Intelligence University of Granada Granada18071 Spain Faculty of Computing and Information Technology King Abdulaziz University Jeddah21589 Saudi Arabia Department of Art History University of Granada Granada18071 Spain Department of Computer Science and Artificial Intelligence University of Granada Granada18071 Spain Department of Software Engineering University of Granada Granada18071 Spain

The latest Deep Learning (DL) models for detection and classification have achieved an unprecedented performance over classical machine learning algorithms. However, DL models are black-box methods hard to debug, interpret, and certify. DL alone cannot provide explanations that can be validated by a non technical audience such as end-users or domain experts. In contrast, symbolic AI systems that convert concepts into rules or symbols –such as knowledge graphs– are easier to explain. However, they present lower generalisation and scaling capabilities. A very important challenge is to fuse DL representations with expert knowledge. One way to address this challenge, as well as the performance-explainability trade-off is by leveraging the best of both streams without obviating domain expert knowledge. In this paper, we tackle such problem by considering the symbolic knowledge is expressed in form of a domain expert knowledge graph. We present the eXplainable Neural-symbolic learning (X-NeSyL) methodology, designed to learn both symbolic and deep representations, together with an explainability metric to assess the level of alignment of machine and human expert explanations. The ultimate objective is to fuse DL representations with expert domain knowledge during the learning process so it serves as a sound basis for explainability. In particular, X-NeSyL methodology involves the concrete use of two notions of explanation, both at inference and training time respectively: 1) EXPLANet: Expert-aligned eXplainable Part-based cLAssifier NETwork Architecture, a compositional convolutional neural network that makes use of symbolic representations, and 2) SHAP-Backprop, an explainable AI-informed training procedure that corrects and guides the DL process to align with such symbolic representations in form of knowledge graphs. We showcase X-NeSyL methodology using MonuMAI dataset for monument facade image classification, and demonstrate that with our approach, it is possible to i

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

A Survey on Brain Tumor Diagnosis and Edema Detection Based on Machine Learning

引用

Journal of Physics: Conference Series 2021年第1期1892卷

作者： K Neamah F Mohamed M M Adnan S A Thajeel Faculty of Engineering School of Computing University Technology of Malaysia Johor Bahru Malaysia UTM-IRDA MaGICX Institute of Human Centered Engineering Universiti Teknologi Malaysia Johar Bahru Malaysia School of Computing Faculty of Engineering University Technology of Malaysia Johor Bahru Malaysia Islamic University Najaf Iraq Computer Science Department College of Education Mustansiriyah University Baghdad Iraq

Early brain tumor diagnosis has a significant role in reducing the risk of disease, as well as led to get better treatment results. Usually, magnetic resonance imaging (MRI) images are evaluated manually through visual inspection, which is difficult, time-consuming and often erroneous;this process is performed by radiologists or clinical experts, and its accuracy depends on their experience. Recently, computer-aided diagnosis (CAD) becomes very essential to overcome these limitations. This paper provides a comprehensive assessment of the existing techniques and methodologies for automated detection of brain tumor coupled with oedema detection methods utilisation, with an emphasis on machine learning models. Moreover, this paper provides an analysis of the integrated procedure that pertains to the retrieval of brain pictures by identifying particular data sets in the procedure to recognise the stipulated attributes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Facial Expression Recognition of facial variations using fusion of feature extraction with classification in end to end model 4

Deep Facial Expression Recognition of facial variations usin...

引用

4th International Conference on Emerging Trends in engineering, sciences and Technology, ICEEST 2019

作者： Ullah, Asad Jami, Abid Aziz, Muhammad Waqas Naeem, Farhan Ahmad, Sadique Anwar, M. Shahid Jing, Wang Beijing Institute of Technology School of Information and Electronics Beijing China Riphah International University Riphah College of Computing Faisalabad Pakistan National University of Computer and Emerging Sciences Department of Computer Science Islamabad Pakistan City University of Science and Information Technology Department of Computer Science Peshawar Pakistan Iqra University Faculty of Engineering Sciences and Technology Karachi Pakistan

ISBN: (纸本)9781728151496

Expression recognition is an important direction for computers to understand human emotions and an important aspect of human-computer interaction. Expression recognition refers to the selection of an expression state from a still photo or video sequence to determine the emotional and psychological changes to the *** Supervised Canonical Correlation Analysis has been used for Feature extraction. For proper classification VGG119 and softmax has been used. Facial variations such as redundant information in image, illumination variance and overfitting have been addressed in this paper. The images have been preprocessed using face detection, data augmentation and image normalization. After down-sampling, Spectral Supervised Canonical Correlation Analysis (SSCCA) holds the dimensions with factor data which constructs affinity matrix that incorporates both the class information and local structure of the data points. Features with having massive discriminative details have been taken. In order to attain low frequency coefficients more effectively the local structural information will be effectively utilized using SSCCA. Data is further provided to VGG19 for proper training. Meanwhile, the proposed method is more effective and robust comparing other methods in the area. © 2019 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Optimization of laser-driven quantum beam generation and the applications with artificial intelligence

引用

Physics of Plasmas 2024年第5期31卷

作者： Kuramitsu, Y. Taguchi, T. Nikaido, F. Minami, T. Hihara, T. Suzuki, S. Oda, K. Kuramoto, K. Yasui, T. Abe, Y. Ibano, K. Takabe, H. Chu, C.M. Wu, K.T. Woon, W.Y. Chen, S.H. Jao, C.S. Chen, Y.C. Liu, Y.L. Morace, A. Yogo, A. Arikawa, Y. Kohri, H. Tokiyasu, A. Kodaira, S. Kusumoto, T. Kanasaki, M. Asai, T. Fukuda, Y. Kondo, K. Kiriyama, H. Hayakawa, T. Tanaka, S.J. Isayama, S. Watamura, N. Suzuki, H. Kumar, H.S. Ohnishi, N. Pikuz, T. Filippov, E. Sakai, K. Yasuhara, R. Nakata, M. Ishikawa, R. Hoshi, T. Mizuta, A. Bolouki, N. Saura, N. Benkadda, S. Koenig, M. Hamaguchi, S. Graduate School of Engineering Osaka University 2-1 Yamadaoka Osaka Suita565-0871 Japan Institute of Laser Engineering Osaka University 2-6 Yamadaoka Osaka Suita565-0871 Japan 8-1-7 Umemidai Kyoto Kizugawa619-0215 Japan Department of Physics National Central University No. 300 Jhongda Rd. Taoyuan Jhongli320 Taiwan Department of Physics National Cheng Kung University Tainan701 Taiwan National Center for High-Performance Computing National Applied Research Laboratories Tainan City711010 Taiwan Institute of Space and Plasma Sciences National Cheng Kung University Tainan701 Taiwan Research Center for Nuclear Physics Osaka University 10-1 Mihogaoka Osaka Ibaraki567-0047 Japan Research Center for Accelerator and Radioisotope Science Tohoku University 1-2-1 Mikamine Taihaku-ku Miyagi Sendai982-0826 Japan Inage Chiba263-8555 Japan Graduate School of Maritime Sciences Kobe University Kobe658-0022 Japan Department of Physical Sciences Aoyama Gakuin University 5-10-1 Fuchinobe Kanagawa Sagamihara252-5258 Japan Department of Advanced Environmental Science and Engineering Kyushu University 6-1 Kasuga-Kohen Fukuoka Kasuga816-8580 Japan Graduate School of Information Science and Technology Osaka University 2-1 Yamadaoka Suita565-0871 Japan Department of Aerospace Engineering Tohoku University 6-6-01 Aramakiazaaoba Aoba-ku Sendai980-8579 Japan Institute for Open and Transdisciplinary Research Initiatives Osaka University 2-1 Yamadaoka Osaka Suita565-0871 Japan Villamayor Salamanca37185 Spain National Institute for Fusion Science 322-6 Oroshicho Gifu Toki509-5292 Japan Faculty of Arts and Sciences Komazawa University 1-23-1 Komazawa Setagaya-ku Tokyo154-8525 Japan Astrophysical Big Bang Laboratory RIKEN Saitama Wako351-0198 Japan Department of Plasma Physics and Technology Faculty of Science Masaryk University Kotlářská 2 Brno611 37 Czech Republic Aix-Marseille Université CNRS PIIM UMR 7345 Marseille France LULI CN

We have investigated space and astrophysical phenomena in nonrelativistic laboratory plasmas with long high-power lasers, such as collisionless shocks and magnetic reconnections, and have been exploring relativistic regimes with intense short pulse lasers, such as energetic ion acceleration using large-area suspended graphene. Increasing the intensity and repetition rate of the intense lasers, we have to handle large amounts of data from the experiments as well as the control parameters of laser beamlines. Artificial intelligence (AI) such as machine learning and neural networks may play essential roles in optimizing the laser and target conditions for efficient laser ion acceleration. Implementing AI into the laser system in mind, as the first step, we are introducing machine learning in ion etch pit analyses detected on plastic nuclear track detectors. Convolutional neural networks allow us to analyze big ion etch pit data with high precision and recall. We introduce one of the applications of laser-driven ion beams using AI to reconstruct vector electric and magnetic fields in laser-produced turbulent plasmas in three dimensions. © 2024 Author(s).

关键词： Ions

来源：评论

学校读者我要写书评

暂无评论

JCave: A 3D interactive game to assist home physiotherapy rehabilitation

arXiv

引用

arXiv 2019年

作者： Elrefaei, Lamiaa A. Azan, Bshaer Hakami, Sameera Melebari, Safiah Computer Science Department Faculty of Computing and Information Technology King Abdulaziz University Jeddah Saudi Arabia Electrical Engineering Department Faculty of Engineering at Shoubra Benha University Cairo Egypt

The purpose of this paper is to investigate the applicability of applying gamification approach on the physiotherapy rehabilitation. A new developing game called JCave was designed and developed for the prove of concept. The propose game target the children from six to twelve years of age who need physical therapy in their upper limbs. JCave is a finite and multilevel single-player 3D video game. The player’s role is to collect jewels from a cave and increase his/her score by performing physical therapy exercises. The game uses Xbox360 Kinect as a motion capture camera to observe gestures and track the child. Automatic gesture recognition algorithms are implemented for elbow flexion-extension exercises and shoulder flexion, which are the active range of motion (AROM) exercises for both the right and left arms. The JCave game is implemented using Unity3D and Blender to design 3D model objects. Copyright © 2019, The Authors. All rights reserved.

关键词： Physical therapy

来源：评论

学校读者我要写书评

暂无评论

Preface

Advances in Intelligent Systems and Computing

引用

Advances in Intelligent Systems and computing 2021年 1232卷 v-vi页

作者： Wani, M. Arif Khoshgoftaar, Taghi M. Palade, Vasile Department of Computer Science University of Kashmir Srinagar India Faculty of Engineering and Computing Coventry University Coventry United Kingdom Computer and Electrical Engineering Florida Atlantic University Boca RatonFL United States

来源：评论

学校读者我要写书评

暂无评论

Analysis of variance of graph-clique mining for scalable proof of work 14th

Analysis of variance of graph-clique mining for scalable pro...

引用

14th International Conference on Information Security and Cryptology, Inscrypt 2018

作者： Anada, Hiroaki Matsushima, Tomohiro Su, Chunhua Meng, Weizhi Kawamoto, Junpei Bag, Samiran Sakurai, Kouichi Department of Information Security University of Nagasaki Nagasaki Japan Department of Informatics Graduate School and Faculty of Information Science and Electrical Engineering Kyushu University Fukuoka Japan Division of Computer Science University of Aizu Aizuwakamatsu Japan Department of Applied Mathematics and Computer Science Technical University of Denmark Kongens Lyngby Denmark School of Computing Science Newcastle University Newcastle upon Tyne United Kingdom

ISBN: (纸本)9783030142339

Recently, Bitcoin is becoming one of the most popular decentralized cryptographic currency technologies, and Bitcoin mining is a process of adding transaction records to Bitcoin’s public ledger of past transactions or blockchain. To obtain a bitcoin, the mining process involves compiling recent transactions into blocks and trying to solve a computationally difficult puzzle, e.g., proof of work puzzle. A proof of work allows miners the ability to quantify how much work a given proof contains. Basically, the required time for mining is decided in advance, but problems will occur if the value is large for dispersion. In this paper, we first accept that the required time between consecutive blocks follows the exponential distribution. That is, the variance is stable as long as the expected time is fixed. Then, we focus on the graph clique mining technique proposed by the literature, like Tromp (BITCOIN 2015) and Bag-Ruj-Sakurai (Inscrypt 2015), which is based on a computational difficulty problem of searching cliques of undirected graphs, where a clique is a subset of vertices. In particular, when the clique size is two, graph clique mining can be used to gain Bitcoins. The previous work also claimed that if the clique size is parameterized and increased, even if the expected time is fixed, the variance would not be stable. However, no qualitative or quantitative results were given to support their claim. Motivated by this issue, in this work, we propose a simple search algorithm for graph cliques mining, and perform a small scale evaluation on Bitcoin and Graph cliques’s solo mining to investigate the variance issue. © 2019, Springer Nature Switzerland AG.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Why is the Winner the Best?

Why is the Winner the Best?

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： M. Eisenmann A. Reinke V. Weru M. D. Tizabi F. Isensee T. J. Adler S. Ali V. Andrearczyk M. Aubreville U. Baid S. Bakas N. Balu S. Bano J. Bernal S. Bodenstedt A. Casella V. Cheplygina M. Daum M. De Bruijne A. Depeursinge R. Dorent J. Egger D. G. Ellis S. Engelhardt M. Ganz N. Ghatwary G. Girard P. Godau A. Gupta L. Hansen K. Harada M. Heinrich N. Heller A. Hering A. Huaulmé P. Jannin A. E. Kavur O. Kodym M. Kozubek J. Li H. Li J. Ma C. Martín-Isla B. Menze A. Noble V. Oreiller N. Padoy S. Pati K. Payette T. Rädsch J. Rafael-Patiño V. Singh Bawa S. Speidel C. H. Sudre K. Van Wijnen M. Wagner D. Wei A. Yamlahi M. H. Yap C. Yuan M. Zenk A. Zia D. Zimmerer D. Aydogan B. Bhattarai L. Bloch R. Brüngel J. Cho C. Choi Q. Dou I. Ezhov C. M. Friedrich C. Fuller R. R. Gaire A. Galdran Á. García Faura M. Grammatikopoulou S. Hong M. Jahanifar I. Jang A. Kadkhodamohammadi I. Kang F. Kofler S. Kondo H. Kuijf M. Li M. Luu T. Martinčič P. Morais M. A. Naser B. Oliveira D. Owen S. Pang J. Park S. Park S. Płotka E. Puybareau N. Rajpoot K. Ryu N. Saeed A. Shephard P. Shi D. Štepec R. Subedi G. Tochon H. R. Torres H. Urien J. L. Vilaça K. A. Wahid H. Wang J. Wang L. Wang X. Wang B. Wiestler M. Wodzinski F. Xia J. Xie Z. Xiong S. Yang Y. Yang Z. Zhao K. Maier-Hein P. F. Jäger A. Kopp-Schneider L. Maier-Hein Division of Intelligent Medical Systems German Cancer Research Center (DKFZ) Heidelberg Germany Helmholtz Imaging German Cancer Research Center (DKFZ) Heidelberg Germany Faculty of Mathematics and Computer Science Heidelberg University Heidelberg Germany Division of Biostatistics German Cancer Research Center (DKFZ) Heidelberg Germany Division of Medical Image Computing German Cancer Research Center (DKFZ) Heidelberg Germany Faculty of Engineering and Physical Sciences School of Computing University of Leeds Leeds UK Institute of Informatics School of Management HES-SO Valais-Wallis University of Applied Sciences and Arts Western Switzerland Sierre Switzerland Department of Nuclear Medicine and Molecular Imaging Lausanne University Hospital Lausanne Switzerland Technische Hochschule Ingolstadt Ingolstadt Germany Center for Artificial Intelligence and Data Science for Integrated Diagnostics (AI2D) and Center for Biomedical Image Computing and Analytics (CBICA) University of Pennsylvania Philadelphia PA USA Department of Pathology and Laboratory Medicine Perelman School of Medicine University of Pennsylvania Philadelphia PA USA Department of Radiology Perelman School of Medicine University of Pennsylvania Philadelphia PA USA Department of Radiology University of Washington Seattle WA USA Department of Computer Science Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS) University College London London UK Universitat Autònoma de Barcelona & Computer Vision Center Barcelona Spain Division of Translational Surgical Oncology National Center for Tumor Diseases (NCT/UCC) Dresden Dresden Germany Department of Advanced Robotics Istituto Italiano di Tecnologia Italy Department of Electronics Information and Bioengineering Politecnico di Milano Milan Italy IT University of Copenhagen Copenhagen Denmark Department of General Visceral and Transplantation Surgery Heidelberg University Hospital Heidelberg Germany Department of Radiology and Nuc

International benchmarking competitions have become fundamental for the comparative performance assessment of image analysis methods. However, little attention has been given to investigating what can be learnt from these competitions. Do they really generate scientific progress? What are common and successful participation strategies? What makes a solution superior to a competing method? To address this gap in the literature, we performed a multicenter study with all 80 competitions that were conducted in the scope of IEEE ISBI 2021 and MICCAI 2021. Statistical analyses performed based on comprehensive descriptions of the submitted algorithms linked to their rank as well as the underlying participation strategies revealed common characteristics of winning solutions. These typically include the use of multi-task learning (63%) and/or multi-stage pipelines (61%), and a focus on augmentation (100%), image preprocessing (97%), data curation (79%), and post-processing (66%). The “typical” lead of a winning team is a computer scientist with a doctoral degree, five years of experience in biomedical image analysis, and four years of experience in deep learning. Two core general development strategies stood out for highly-ranked teams: the reflection of the metrics in the method design and the focus on analyzing and handling failure cases. According to the organizers, 43% of the winning algorithms exceeded the state of the art but only 11% completely solved the respective domain problem. The insights of our study could help researchers (1) improve algorithm development strategies when approaching new problems, and (2) focus on open research questions revealed by this work.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Precision tomography of a three-qubit donor quantum processor in silicon

arXiv

引用

arXiv 2021年

作者： Mądzik, Mateusz T. Asaad, Serwan Youssry, Akram Joecker, Benjamin Rudinger, Kenneth M. Nielsen, Erik Young, Kevin C. Proctor, Timothy J. Baczewski, Andrew D. Laucht, Arne Schmitt, Vivien Hudson, Fay E. Itoh, Kohei M. Jakob, Alexander M. Johnson, Brett C. Jamieson, David N. Dzurak, Andrew S. Ferrie, Christopher Blume-Kohout, Robin Morello, Andrea School of Electrical Engineering and Telecommunications UNSW Sydney SydneyNSW2052 Australia Centre for Quantum Software and Information University of Technology Sydney UltimoNSW2007 Australia Department of Electronics and Communication Engineering Faculty of Engineering Ain Shams University Cairo Egypt Quantum Performance Laboratory Sandia National Laboratories Albuquerque NM 87185 LivermoreCA94550 United States Center for Computing Research Sandia National Laboratories AlbuquerqueNM87185 United States School of Fundamental Science and Technology Keio University Kohoku-ku Yokohama Japan School of Physics University of Melbourne MelbourneVIC3010 Australia

Nuclear spins were among the first physical platforms to be considered for quantum information processing[1, 2], because of their exceptional quantum coherence[3] and atomic-scale footprint. However, their full potential for quantum computing has not yet been realized, due to the lack of methods to link nuclear qubits within a scalable device combined with multi-qubit operations with sufficient fidelity to sustain fault-tolerant quantum computation. Here we demonstrate universal quantum logic operations using a pair of ion-implanted 31P donor nuclei in a silicon nanoelectronic device. A nuclear two-qubit controlled-Z gate is obtained by imparting a geometric phase to a shared electron spin[4], and used to prepare entangled Bell states with fidelities up to 94.2(2.7)%. The quantum operations are precisely characterised using gate set tomography (GST)[5], yielding one-qubit average gate fidelities up to 99.95(2)%, two-qubit average gate fidelity of 99.37(11)% and two-qubit preparation/measurement fidelities of 98.95(4)%. These three metrics indicate that nuclear spins in silicon are approaching the performance demanded in fault-tolerant quantum processors [6]. We then demonstrate entanglement between the two nuclei and the shared electron by producing a Greenberger-Horne-Zeilinger three-qubit state with 92.5(1.0)% fidelity. Since electron spin qubits in semiconductors can be further coupled to other electrons[7, 8, 9] or physically shuttled across different locations[10, 11], these results establish a viable route for scalable quantum information processing using donor nuclear and electron spins. Copyright © 2021, The Authors. All rights reserved.

关键词： Spin dynamics

来源：评论

学校读者我要写书评

暂无评论

Metrics Reloaded: Recommendations for image analysis validation

arXiv

引用

arXiv 2022年

作者： Maier-Hein, Lena Reinke, Annika Godau, Patrick Tizabi, Minu D. Buettner, Florian Christodoulou, Evangelia Glocker, Ben Isensee, Fabian Kleesiek, Jens Kozubek, Michal Reyes, Mauricio Riegler, Michael A. Wiesenfarth, Manuel Emre Kavur, A. Sudre, Carole H. Baumgartner, Michael Eisenmann, Matthias Heckmann-Nötzel, Doreen Rädsch, Tim Acion, Laura Antonelli, Michela Arbel, Tal Bakas, Spyridon Benis, Arriel Blaschko, Matthew B. Jorge Cardoso, M. Cheplygina, Veronika Cimini, Beth A. Collins, Gary S. Farahani, Keyvan Ferrer, Luciana Galdran, Adrian Ginneken, Bram Van Haase, Robert Hashimoto, Daniel A. Hoffman, Michael M. Huisman, Merel Jannin, Pierre Kahn, Charles E. Kainmueller, Dagmar Kainz, Bernhard Karargyris, Alexandros Karthikesalingam, Alan Kenngott, Hannes Kofler, Florian Kopp-Schneider, Annette Kreshuk, Anna Kurc, Tahsin Landman, Bennett A. Litjens, Geert Madani, Amin Maier-Hein, Klaus Martel, Anne L. Mattson, Peter Meijering, Erik Menze, Bjoern Moons, Karel G.M. Müller, Henning Nichyporuk, Brennan Nickel, Felix Petersen, Jens Rajpoot, Nasir Rieke, Nicola Saez-Rodriguez, Julio Sánchez, Clara I. Shetty, Shravya Smeden, Maarten Van Summers, Ronald M. Taha, Abdel A. Tiulpin, Aleksei Tsaftaris, Sotirios A. Calster, Ben Van Varoquaux, Gaël Jäger, Paul F. Heidelberg Division of Intelligent Medical Systems and HI Helmholtz Imaging Germany Faculty of Mathematics and Computer Science and Medical Faculty Heidelberg University Heidelberg Germany NCT Heidelberg a partnership between DKFZ University Medical Center Heidelberg Germany Faculty of Mathematics and Computer Science Heidelberg University Heidelberg Germany Heidelberg Division of Intelligent Medical Systems Germany partner site Frankfurt/Mainz a partnership between DKFZ and UCT Frankfurt-Marburg Germany Heidelberg Goethe University Frankfurt Germany Department of Medicine Goethe University Frankfurt Germany Department of Informatics Frankfurt Cancer Insititute Germany Department of Computing Imperial College London London United Kingdom Heidelberg Division of Medical Image Computing and HI Applied Computer Vision Lab Germany Institute for AI in Medicine University Medicine Essen Essen Germany Centre for Biomedical Image Analysis Faculty of Informatics Masaryk University Brno Czech Republic ARTORG Center for Biomedical Engineering Research University of Bern Bern Switzerland Department of Radiation Oncology University Hospital Bern University of Bern Bern Switzerland Simula Metropolitan Center for Digital Engineering Oslo Norway UiT The Arctic University of Norway Romsø Norway Heidelberg Division of Biostatistics Germany Heidelberg Division of Intelligent Medical Systems Division of Medical Image Computing HI Applied Computer Vision Lab Germany MRC Unit for Lifelong Health and Ageing UCL Centre for Medical Image Computing Department of Computer Science University College London London United Kingdom School of Biomedical Engineering and Imaging Science King’s College London London United Kingdom Heidelberg Division of Medical Image Computing Germany Instituto de Cálculo CONICET – Universidad de Buenos Aires Buenos Aires Argentina Centre for Medical Image Computing University College London London United Kingdom McGill University Montréal

Increasing evidence shows that flaws in machine learning (ML) algorithm validation are an underestimated global problem. Particularly in automatic biomedical image analysis, chosen performance metrics often do not reflect the domain interest, thus failing to adequately measure scientific progress and hindering translation of ML techniques into practice. To overcome this, we created Metrics Reloaded, a comprehensive framework guiding researchers in the problem-aware selection of metrics. It was developed by a large international consortium in a multi-stage Delphi process and is based on the novel concept of a problem fingerprint – a structured representation of the given problem that captures all aspects that are relevant for metric selection, from the domain interest to the properties of the target structure(s), data set and algorithm output. Based on the problem fingerprint, users are guided through the process of choosing and applying appropriate validation metrics while being made aware of potential pitfalls. Metrics Reloaded targets image analysis problems that can be interpreted as a classification task at image, object or pixel level, namely image-level classification, object detection, semantic segmentation, and instance segmentation tasks. To improve the user experience, we implemented the framework in the Metrics Reloaded online tool. Following the convergence of ML methodology across application domains, Metrics Reloaded fosters the convergence of validation methodology. Its applicability is demonstrated for various biomedical use cases. © 2022, CC BY.

关键词： Semantic Segmentation

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：