%0 Generic %1 maschler2020distributed %A Maschler, Benjamin %A Kamm, Simon %A Jazdi, Nasser %A Weyrich, Michael %B 53rd CIRP Conference on Manufacturing Systems (Virtual Conference), 1-3 July 2020, Chicago, pp. 437-442, %D 2020 %K 2020ias 2020kiundmachinelearning ias %R 10.1016/j.procir.2020.03.056 %T Distributed Cooperative Deep Transfer Learning for Industrial Image Recognition %U https://www.sciencedirect.com/science/article/pii/S2212827120306648?via%3Dihub %X 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.

@conference{maschler2020distributed, 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.}, added-at = {2020-09-24T14:49:56.000+0200}, author = {Maschler, Benjamin and Kamm, Simon and Jazdi, Nasser and Weyrich, Michael}, biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2126e775a9d95024d73fd39a8de718da8/taylansngerli}, booktitle = {53rd CIRP Conference on Manufacturing Systems (Virtual Conference), 1-3 July 2020, Chicago, pp. 437-442,}, doi = {10.1016/j.procir.2020.03.056}, interhash = {3be1f15298ec5dd2aec2d254b2b8ffdb}, intrahash = {126e775a9d95024d73fd39a8de718da8}, keywords = {2020ias 2020kiundmachinelearning ias}, timestamp = {2021-04-06T09:51:33.000+0200}, title = {Distributed Cooperative Deep Transfer Learning for Industrial Image Recognition}, url = {https://www.sciencedirect.com/science/article/pii/S2212827120306648?via%3Dihub}, year = 2020 }