@inproceedings{follath2024multimodal,
    type = {inproceedings},
    key = {follath2024multimodal},
    title = {Multi-Modal Vision Transformers for Crop Mapping from Satellite Image Time Series},
    author = {Theresa Follath and David Mickisch and Jan Hemmerling and Stefan Erasmi and Marcel Schwieder and Begüm Demir},
    booktitle = {IEEE International Geoscience and Remote Sensing Symposium (IGARSS)},
    year = {2024},
    pages = {1937-1941},
    doi = {10.1109/IGARSS53475.2024.10641794},
    abstract = {Using images acquired by different satellite sensors has shown to improve classification performance in the framework of crop mapping from satellite image time series (SITS). Existing state-of-the-art architectures use self-attention mechanisms to process the temporal dimension and convolutions for the spatial dimension of SITS. Motivated by the success of purely attention-based architectures in crop mapping from single-modal SITS, we introduce several multi-modal multi-temporal transformer-based architectures. Specifically, we investigate the effectiveness of Early Fusion, Cross Attention Fusion and Synchronized Class Token Fusion within the Temporo-Spatial Vision Transformer (TSViT). Experimental results demonstrate significant improvements over state-of-the-art architectures with both convolutional and self-attention components.},
}