Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Self-supervised Pairing Image Clustering and its Application in Cyber Manufacturing

: Dai, Wenting; Jiao, Yutao; Erdt, Marius; Sourin, Alexei


Sourin, Alexei (Ed.) ; Institute of Electrical and Electronics Engineers -IEEE-; European Association for Computer Graphics -EUROGRAPHICS-:
International Conference on Cyberworlds, CW 2020. Proceedings : 29 September - 1 October 2020, Caen, France, online
Los Alamitos, Calif.: IEEE Computer Society Conference Publishing Services (CPS), 2020
ISBN: 978-1-7281-6497-7
ISBN: 978-1-7281-6498-4
International Conference on Cyberworlds (CW) <19, 2020, Online>
Conference Paper
Fraunhofer Singapore ()
image clustering; Lead Topic: Digitized Work; Research Line: Machine Learning (ML); Research Line: Computer vision (CV); industrial quality control; clustering; Artificial Neural Networks

Artificial intelligence is being increasingly applied in manufacturing to maximize industrial productivity. Image clustering, as a fundamental research direction in unsupervised learning, has been used in various fields. Since no label information is required in clustering, it can perform a preliminary analysis of the data while saving lots of manpower. In this paper, we propose a novel end-to-end clustering network called Self-supervised Pairing Image Clustering (SPIC) for industrial application, which produces clustering prediction for input images in an advanced pair classification network. For training this network, a self-supervised pairing module is built to form balanced pairs accurately and efficiently without label information. Since the existence of trivial solutions cannot be avoided in most of unsupervised learning methods, two additional information theoretic-constraints regularize the training that ensures the clustering prediction to be unambiguous and close to the real data distribution during training. Experimental results indicate that the proposed SPIC outperforms the state-of-art approaches on manufacturing datasets–NEU and DAGM. It also shows the execellent generalization capability on other genral public datasets, such as MNIST, Omniglot, CIFAR10, and CIFAR100.