Home Publications Research Grants Inventions & Patents Awards Additional Research Activities Faculties & Institutions Research Areas

Leveraging pre-trained Segmentation Networks for Anomaly Segmentation

Rippel O, Merhof D (2021)

---

Publication Type: Conference contribution

Publication year: 2021

Publisher: Institute of Electrical and Electronics Engineers Inc.

Book Volume: 2021-September

Conference Proceedings Title: IEEE International Conference on Emerging Technologies and Factory Automation, ETFA

Event location: Virtual, Vasteras, SWE

ISBN: 9781728129891

DOI: 10.1109/ETFA45728.2021.9613387

Abstract

Employing representations generated by large-scale training in a transfer-learning setting achieves state-of-the-art anomaly segmentation results when applied to the visual inspection task. Current approaches, however, focus exclusively on features of pre-trained classification networks, which are known to posess lower spatial resolution than segmentation or object detection networks. In our work, we investigate whether features extracted from pre-trained segmentation networks can be used to further improve anomaly segmentation performance in the transfer-learning setting. To this end, we apply state-of-the-art transfer-learning methods to encoder-decoder based segmentation networks. Results show that the encoders of pre-trained segmentation networks yield improved anomaly segmentation performance compared to their pre-trained classification counterparts. However, no consistent improvements can be observed yet regarding the decoders of the pre-trained segmentation networks. Together, this demonstrates that pre-trained segmentation networks can be used to further improve transfer-learned anomaly segmentation performance and that additional research is required to fully unleash their potential.

Involved external institutions

How to cite

APA:

Rippel, O., & Merhof, D. (2021). Leveraging pre-trained Segmentation Networks for Anomaly Segmentation. In IEEE International Conference on Emerging Technologies and Factory Automation, ETFA. Virtual, Vasteras, SWE: Institute of Electrical and Electronics Engineers Inc..

MLA:

Rippel, Oliver, and Dorit Merhof. "Leveraging pre-trained Segmentation Networks for Anomaly Segmentation." Proceedings of the 26th IEEE International Conference on Emerging Technologies and Factory Automation, ETFA 2021, Virtual, Vasteras, SWE Institute of Electrical and Electronics Engineers Inc., 2021.

BibTeX: Download