Our abstract Towards Transformer-based Homogenization of Satellite Imagery for Landsat-8 and Sentinel-2 was accepted for presentation at the Transformers Workshop for Environmental Science.
In summary, we somewhat surprisingly found that transformers, a neural network architecture that achieves state-of-the-art results on most tasks it is applied to, does not outperform a vanilla U-Net model on our particular superresolution task.
Citation
@misc{sambandham2022transformer,
title = {Towards Transformer-based Homogenization of Satellite Imagery for {Landsat-8} and {Sentinel-2}},
author = {Sambandham, Venkatesh Thirugnana and Kirchheim, Konstantin and Mukhopadhaya, Sayan and Ortmeier, Frank},
year = {2022},
eprint = {2210.07654},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
doi = {10.48550/arXiv.2210.07654}
}