Panoptic Segmentation of satellite image TImes Series
PASTIS is a benchmark dataset for panoptic and semantic segmentation of agricultural parcels from satellite image time series. It is composed of 2433 one square kilometer-patches in the French metropolitan territory for which sequences of satellite observations are assembled into a four-dimensional spatio-temporal tensor. The dataset contains both semantic and instance annotations, assigning to each pixel a semantic label and an instance id. There is an official 5 fold split provided in the dataset's metadata.
Image source: https://github.com/VSainteuf/pastis-benchmark
Variants: PASTIS
This dataset is used in 2 benchmarks:
| Task | Model | Paper | Date |
|---|---|---|---|
| Semantic Segmentation | Exchanger+Mask2Former | Revisiting the Encoding of Satellite … | 2023-05-03 |
| Semantic Segmentation | Exchanger+Unet | Revisiting the Encoding of Satellite … | 2023-05-03 |
| Panoptic Segmentation | Exchanger+Mask2Former | Revisiting the Encoding of Satellite … | 2023-05-03 |
| Panoptic Segmentation | Exchanger+Unet+PaPs | Revisiting the Encoding of Satellite … | 2023-05-03 |
| Semantic Segmentation | U-TAE | Panoptic Segmentation of Satellite Image … | 2021-07-16 |
| Panoptic Segmentation | U-TAE + PaPs | Panoptic Segmentation of Satellite Image … | 2021-07-16 |
Recent papers with results on this dataset: