The color out of space: learning self-supervised representations for Earth Observation imagery
Abstract: The recent growth in the number of satellite images fosters the development of effective deep-learning techniques for Remote Sensing (RS). However, their full potential is untapped due to the lack of large annotated datasets. Such a problem is usually countered by fine-tuning a feature extractor that is previously trained on the ImageNet dataset. Unfortunately, the domain of natural images differs from the RS one, which hinders the final performance. In this work, we propose to learn meaningful representations from satellite imagery, leveraging its high-dimensionality spectral bands to reconstruct the visible colors. We conduct experiments on land cover classification (BigEarthNet) and West Nile Virus detection, showing that colorization is a solid pretext task for training a feature extractor. Furthermore, we qualitatively observe that guesses based on natural images and colorization rely on different parts of the input. This paves the way to an ensemble model that eventually outperforms both the above-mentioned techniques.
Citation:
Vincenzi, Stefano; Porrello, Angelo; Buzzega, Pietro; Cipriano, Marco; Fronte, Pietro; Cuccu, Roberto; Ippoliti, Carla; Conte, Annamaria; Calderara, Simone "The color out of space: learning self-supervised representations for Earth Observation imagery" Proceedings of the 25th International Conference on Pattern Recognition, Milan, Italy, pp. 3034 -3041 , 10-15 January 2021, 2021 DOI: 10.1109/ICPR48806.2021.9413112
not available
Paper download:
- Author version:
- DOI: 10.1109/ICPR48806.2021.9413112