The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLIII-B3-2021
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B3-2021, 829–836, 2021
https://doi.org/10.5194/isprs-archives-XLIII-B3-2021-829-2021
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B3-2021, 829–836, 2021
https://doi.org/10.5194/isprs-archives-XLIII-B3-2021-829-2021

  29 Jun 2021

29 Jun 2021

EVALUATION OF SEMI-SUPERVISED LEARNING FOR CNN-BASED CHANGE DETECTION

E. Bousias Alexakis and C. Armenakis E. Bousias Alexakis and C. Armenakis
  • Geomatics Engineering, GeoICT Lab, Department of Earth and Space Science and Engineering, Lassonde School of Engineering, York University, Toronto, Canada

Keywords: Change Detection, CNN, Encoder-Decoder, Semi-Supervised Learning, UNet, Mean Teacher, Self-Ensembling

Abstract. Over the past few years, many research works have utilized Convolutional Neural Networks (CNN) in the development of fully automated change detection pipelines from high resolution satellite imagery. Even though CNN architectures can achieve state-of-the-art results in a wide variety of vision tasks, including change detection applications, they require extensive amounts of labelled training examples in order to be able to generalize to new data through supervised learning. In this work we experiment with the implementation of a semi-supervised training approach in an attempt to improve the image semantic segmentation performance of models trained using a small number of labelled image pairs by leveraging information from additional unlabelled image samples. The approach is based on the Mean Teacher method, a semi-supervised approach, successfully applied for image classification and for sematic segmentation of medical images. Mean Teacher uses an exponential moving average of the model weights from previous epochs to check the consistency of the model’s predictions under various perturbations. Our goal is to examine whether its application in a change detection setting can result in analogous performance improvements. The preliminary results of the proposed method appear to be compatible to the results of the traditional fully supervised training. Research is continuing towards fine-tuning of the method and reaching solid conclusions with respect to the potential benefits of the semi-supervised learning approaches in image change detection applications.