Rethinking Pre-Training in Industrial Quality Control

Yesilbas D, Arnold S, Felker A (2022)

Publication Type: Conference contribution

Publication year: 2022

Publisher: Association for Information Systems

Conference Proceedings Title: 17th International Conference on Wirtschaftsinformatik, WI 2022

Event location: Nürnberg DE

Abstract

The application of machine learning is of high significance for quality control tasks in the manufacturing industry due to large volumes of machine-generated data. However, labeling data is costly and labor-intensive. In this study, we evaluate the role of manual labeling and the moderating effect of autoencoder-based pre-training in optical quality control using real-world industrial data. We observe that pre-training substantially elevates the classification accuracy for small amounts of labeled data. With increasing amounts of labeled data available during fine-tuning, however, we find diminishing returns, analogous to recent concerns raised in non-industrial applications.

Authors with CRIS profile

Dilara Yesilbas Lehrstuhl für Wirtschaftsinformatik, insbesondere IT-Management Stefan Arnold Lehrstuhl für Wirtschaftsinformatik, insbesondere IT-Management Alex Felker Lehrstuhl für Wirtschaftsinformatik, insbesondere IT-Management

How to cite

APA:

Yesilbas, D., Arnold, S., & Felker, A. (2022). Rethinking Pre-Training in Industrial Quality Control. In 17th International Conference on Wirtschaftsinformatik, WI 2022. Nürnberg, DE: Association for Information Systems.

MLA:

Yesilbas, Dilara, Stefan Arnold, and Alex Felker. "Rethinking Pre-Training in Industrial Quality Control." Proceedings of the 17th International Conference on Wirtschaftsinformatik, WI 2022, Nürnberg Association for Information Systems, 2022.

BibTeX: Download