The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLII-2/W13
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2/W13, 111–117, 2019
https://doi.org/10.5194/isprs-archives-XLII-2-W13-111-2019
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2/W13, 111–117, 2019
https://doi.org/10.5194/isprs-archives-XLII-2-W13-111-2019

  04 Jun 2019

04 Jun 2019

COMPARISON OF TRAINING STRATEGIES FOR CONVNETS ON MULTIPLE SIMILAR DATASETS FOR FACADE SEGMENTATION

M. Schmitz, H. Huang, and H. Mayer M. Schmitz et al.
  • Institute for Applied Computer Science, Bundeswehr University Munich, Neubiberg, Germany

Keywords: Convolutional Network, Facade Segmentation, Fine-Tuning, Multi-Task Learning

Abstract. In this paper, we analyze different training strategies and accompanying architectures for Convolutional Networks (ConvNets) when multiple similar datasets are available using the semantic segmentation of rectified facade images as example. Additionally to direct training on the target dataset we analyze multi-task learning and fine-tuning. When using multi-task learning to train a ConvNet, multiple objectives are optimized in parallel. Fine-tuning optimizes these objectives sequentially. For both strategies, the tasks share a common part of the ConvNet for which we vary the depth. We present results for all strategies and compare them regarding the overall pixel-wise accuracy and show that for the special case of facade segmentation there are no significant differences using multiple datasets or not or training a ConvNet with different strategies.