Update README.md

README.md

@@ -9,10 +9,9 @@ license: mit
 For more details and results, please check out our [github](https://github.com/gastruc/AnySat) and [project page](https://gastruc.github.io/projects/omnisat.html).
 
 <p align="center">
-  <img src=".media/image.png" alt="AnySat Architecture" width="500">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/662b7fba68ed7bbf40bfb0df/m1IY9HfCD8NAeykZxqWSb.png" alt="AnySat Architecture" width="500">
 </p>
 
-
 # Abstract
 
 **AnySat** is a versatile Earth Observation model designed to handle diverse data across resolutions, scales, and modalities. Using a **scale-adaptive joint embedding predictive architecture** (JEPA), AnySat can train in a self-supervised manner on highly heterogeneous datasets.
@@ -20,7 +19,7 @@ For more details and results, please check out our [github](https://github.com/g
 We train a single AnySat model on **GeoPlex**, a collection of 5 multimodal datasets spanning 11 sensors with varying characteristics. In fine-tuning or linear probing, AnySat achieves SOTA or near-SOTA performance for land cover segmentation, crop type classification, change detection, tree species identification, and flood mapping.
 
 <p align="center">
-  <img src=".media/teaser.png" alt="AnySat Teaser" width="500">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/662b7fba68ed7bbf40bfb0df/mENiGjg5gfKH27vqr8xuB.png" alt="AnySat Teaser" width="500">
 </p>
 
 # Key Features
@@ -150,7 +149,7 @@ python src/train.py exp=BraDD_AnySAT_LP
 Our implementation already supports 9 datasets:
 
 <p align="center">
-  <img src=".media/datasets.png" alt="AnySat Datasets" width="500">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/662b7fba68ed7bbf40bfb0df/nGGz8kiDdeTJqIPSdrlSz.png" alt="AnySat Datasets" width="500">
 </p>
 
 ## GeoPlex Datasets
@@ -217,10 +216,4 @@ Please use the following bibtex:
   journal={arXiv preprint arXiv:2412.XXXX},
   year={2024}
 }
-```
-
-# Acknowledgements
-- The code is conducted on the same base as [OmniSat](https://github.com/gastruc/OmniSat)
-- The JEPA implementation comes from [JEPA](https://github.com/facebookresearch/ijepa)
-- The code from Pangaea datasets comes from [Pangaea](https://github.com/VMarsocci/pangaea-bench)
-<br>
+```