AuthorsO. Ostroukhova, K. Pogorelov, M. Riegler, D. Dang-Nguyen and P. Halvorsen
TitleTransfer learning with prioritized classification and training dataset equalization for medical objects detection
AfilliationCommunication Systems
Project(s)Efficient EONS: Execution of Large Workloads on Elastic Heterogeneous Resources, Department of Holistic Systems
StatusPublished
Publication TypeProceedings, refereed
Year of Publication2018
Conference NameWorking Notes Proceedings of the MediaEval 2018 Workshop
PublisherCEUR Workshop Proceedings
Abstract

This paper presents the method proposed by the organizer team (SIMULA) for MediaEval 2018 Multimedia for Medicine: the Medico Task. We utilized the recent transfer-learning-based image classification methodology and focused on how easy it is to implement multi-class image classifiers in general and how to improve the classification performance without deep neural network model redesign. The goal for this was both to provide a baseline for the Medico task and to show the  performance of out-of-the-box classifiers for the medical use-case scenario.

Citation Key26258

Contact person