Leveraging pre-trained Segmentation Networks for Anomaly Segmentation

IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), vol. 33, pp. 01–04

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.

Authors 2

1. Oliver Rippel Aachen Institute of Imaging & Computer Vision

   RWTH Aachen University

   Affiliation as printed

   Institute of Imaging & Computer Vision, RWTH Aachen University, Aachen, Germany

2. Dorit Merhof Aachen Institute of Imaging & Computer Vision

   RWTH Aachen University

   Affiliation as printed

   Institute of Imaging & Computer Vision, RWTH Aachen University, Aachen, Germany