TL;DR
This paper introduces Thermal Positional Encoding (TPE), a novel method for attention-based crop classification that improves generalization across regions by accounting for thermal time instead of calendar time.
Contribution
The paper proposes TPE, a new positional encoding based on thermal time, enhancing the robustness of crop classifiers to regional temporal shifts in growing seasons.
Findings
TPE outperforms traditional encodings in cross-region generalization.
Multiple TPE strategies further improve classification accuracy.
Achieved state-of-the-art results on European crop datasets.
Abstract
Large-scale crop type classification is a task at the core of remote sensing efforts with applications of both economic and ecological importance. Current state-of-the-art deep learning methods are based on self-attention and use satellite image time series (SITS) to discriminate crop types based on their unique growth patterns. However, existing methods generalize poorly to regions not seen during training mainly due to not being robust to temporal shifts of the growing season caused by variations in climate. To this end, we propose Thermal Positional Encoding (TPE) for attention-based crop classifiers. Unlike previous positional encoding based on calendar time (e.g. day-of-year), TPE is based on thermal time, which is obtained by accumulating daily average temperatures over the growing season. Since crop growth is directly related to thermal time, but not calendar time, TPE addresses…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
