The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLIII-B2-2022
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2022, 601–607, 2022
https://doi.org/10.5194/isprs-archives-XLIII-B2-2022-601-2022
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2022, 601–607, 2022
https://doi.org/10.5194/isprs-archives-XLIII-B2-2022-601-2022
 
30 May 2022
30 May 2022

EVALUATION OF SELF-SUPERVISED LEARNING APPROACHES FOR SEMANTIC SEGMENTATION OF INDUSTRIAL BURNER FLAMES

S. Landgraf1, L. Kühnlein2, M. Hillemann1, M. Hoyer2, S. Keller1,2, and M. Ulrich1 S. Landgraf et al.
  • 1Institute of Photogrammetry and Remote Sensing (IPF), Karlsruhe Institute of Technology (KIT), Germany
  • 2ci-tec GmbH, Germany

Keywords: Semantic Segmentation, Self-Supervised Learning, Deep Learning, Industrial Burner, Flame Segmentation, Industrial Automation

Abstract. In recent years, self-supervised learning has made tremendous progress in closing the gap to supervised learning due to the rapid development of more sophisticated approaches like SimCLR, MoCo, and SwAV. However, these achievements are primarily evaluated on common benchmark datasets. In this paper, we focus on evaluating self-supervised learning for semantic segmentation of industrial burner flames. Our goal is to build an intuition on how self-supervision performs in a scenario relevant for industrial application where training labels and the opportunities for hyperparameter tuning are limited. We demonstrate that self-supervised pre-training can constitute an alternative to the state-of-the-art approach of pre-training on ImageNet. Across all scenarios, the self-supervised approaches are less susceptible to sub-optimal learning rates and achieve higher mean accuracies than ImageNet pre-training, especially when training labels are scarce.