1. Multi-Modal Vision Transformers for Crop Mapping from Satellite Image Time Series
- Author
-
Follath, Theresa, Mickisch, David, Hemmerling, Jan, Erasmi, Stefan, Schwieder, Marcel, and Demir, Begüm
- Subjects
Computer Science - Computer Vision and Pattern Recognition - 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., Comment: 5 pages, 2 figures, 1 table. Accepted at IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2024. Our code is available at https://git.tu-berlin.de/rsim/mmtsvit
- Published
- 2024