speillet alabatie commited on
Commit
fa7d35c
·
verified ·
1 Parent(s): f1365d5

Update README.md (#1)

Browse files

- Update README.md (25b5a583f4023c44cb539d3f807333f5103644c5)


Co-authored-by: Antoine Labatie <alabatie@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +7 -3
README.md CHANGED
@@ -1,11 +1,15 @@
1
  ---
2
- license: etalab-2.0
3
  pipeline_tag: image-segmentation
4
  tags:
5
- - semantic segmentation
6
  - pytorch
7
- - landcover
 
 
 
8
  library_name: pytorch
 
 
9
  ---
10
 
11
  We introduce **MAESTRO**, a tailored adaptation of the Masked Autoencoder (MAE) framework that effectively orchestrates the use of multimodal, multitemporal, and multispectral Earth Observation (EO) data. Evaluated on four EO datasets, MAESTRO sets a new state-of-the-art on tasks that strongly rely on multitemporal dynamics, while remaining highly competitive on tasks dominated by a single monotemporal modality.
 
1
  ---
2
+ license: apache-2.0
3
  pipeline_tag: image-segmentation
4
  tags:
 
5
  - pytorch
6
+ - self-supervised
7
+ - transformers
8
+ - multimodal
9
+ - remote sensing
10
  library_name: pytorch
11
+ datasets:
12
+ - allenai/s2-naip
13
  ---
14
 
15
  We introduce **MAESTRO**, a tailored adaptation of the Masked Autoencoder (MAE) framework that effectively orchestrates the use of multimodal, multitemporal, and multispectral Earth Observation (EO) data. Evaluated on four EO datasets, MAESTRO sets a new state-of-the-art on tasks that strongly rely on multitemporal dynamics, while remaining highly competitive on tasks dominated by a single monotemporal modality.