Vision Transformers reduce computational operations by an order of magnitude for spatio-temporal vegetation pixel classification while maintaining competitive accuracy and constant parameter count independent of time series length.
Applying machine learning based on multiscale classifiers to detect remote phenology patterns in cerrado savanna trees
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Efficient Spatio-Temporal Vegetation Pixel Classification with Vision Transformers
Vision Transformers reduce computational operations by an order of magnitude for spatio-temporal vegetation pixel classification while maintaining competitive accuracy and constant parameter count independent of time series length.