عرض بسيط للتسجيلة

المؤلفAl-Kababji, Ayman
المؤلفBensaali, Faycal
المؤلفDakua, Sarada Prasad
تاريخ الإتاحة2022-12-29T07:34:43Z
تاريخ النشر2022
اسم المنشورCommunications in Computer and Information Science
المصدرScopus
معرّف المصادر الموحدhttp://dx.doi.org/10.1007/978-3-031-08277-1_17
معرّف المصادر الموحدhttp://hdl.handle.net/10576/37819
الملخصMachine learning and computer vision techniques have influenced many fields including the biomedical one. The aim of this paper is to investigate the important concept of schedulers in manipulating the learning rate (LR), for the liver segmentation task, throughout the training process, focusing on the newly devised OneCycleLR against the ReduceLRonPlateau. A dataset, published in 2018 and produced by the Medical Segmentation Decathlon Challenge organizers, called Task 8 Hepatic Vessel (MSDC-T8) has been used for testing and validation. The reported results that have the same number of maximum epochs (75), and are the average of 5-fold cross-validation, indicate that ReduceLRonPlateau converges faster while maintaining a similar or even better loss score on the validation set when compared to OneCycleLR. The epoch at which the peak LR occurs perhaps should be made early for the OneCycleLR such that the super-convergence feature can be observed. Moreover, the overall results outperform the state-of-the-art results from the researchers who published the liver masks for this dataset. To conclude, both schedulers are suitable for medical segmentation challenges, especially the MSDC-T8 dataset, and can be used confidently in rapidly converging the validation loss with a minimal number of epochs. 2022, Springer Nature Switzerland AG.
راعي المشروعThis publication was made possible by an Award [GSRA6-2-0521-19034] from Qatar National Research Fund (a member of Qatar Foundation). The contents herein are solely the responsibility of the authors. Moreover, the HPC resources and services used in this work were provided by the Research Computing group in Texas A&M University at Qatar. Research Computing is funded by the Qatar Foundation for Education, Science and Community Development (http://www.qf.org.qa).
اللغةen
الناشرSpringer Science and Business Media Deutschland GmbH
الموضوعConvolutional neural network
Dice score
Learning rate
Liver delineation
Schedulers
Semantic segmentation
العنوانScheduling Techniques for Liver Segmentation: ReduceLRonPlateau vs OneCycleLR
النوعConference Paper
الصفحات204-212
رقم المجلد1589 CCIS
dc.accessType Abstract Only


الملفات في هذه التسجيلة

الملفاتالحجمالصيغةالعرض

لا توجد ملفات لها صلة بهذه التسجيلة.

هذه التسجيلة تظهر في المجموعات التالية

عرض بسيط للتسجيلة