Please use this identifier to cite or link to this item: http://dx.doi.org/10.18419/opus-10882
Authors: Maschler, Benjamin
Kamm, Simon
Nasser, Jazdi
Weyrich, Michael
Title: Distributed cooperative deep transfer learning for industrial image recognition
Issue Date: 2020
metadata.ubs.publikation.typ: Preprint
metadata.ubs.publikation.seiten: 6
URI: http://elib.uni-stuttgart.de/handle/11682/10899
http://nbn-resolving.de/urn:nbn:de:bsz:93-opus-ds-108998
http://dx.doi.org/10.18419/opus-10882
Abstract: In this paper, a novel light-weight incremental class learning algorithm for live image recognition is presented. It features a dual memory architecture and is capable of learning formerly unknown classes as well as conducting its learning across multiple instances at multiple locations without storing any images. In addition to tests on the ImageNet dataset, a prototype based upon a Raspberry Pi and a webcam is used for further evaluation: The proposed algorithm successfully allows for the performant execution of image classification tasks while learning new classes at several sites simultaneously, thereby enabling its application to various industry use cases, e.g. predictive maintenance or self-optimization.
Appears in Collections:05 Fakultät Informatik, Elektrotechnik und Informationstechnik

Files in This Item:
File Description SizeFormat 
Distributed Cooperative Deep Transfer Learning for Industrial Image Recognition.pdf519,23 kBAdobe PDFView/Open


Items in OPUS are protected by copyright, with all rights reserved, unless otherwise indicated.