OceanSAR-1-TenGeoP is a linear probing head for classifying ocean geophysical phenomena, built on top of the OceanSAR-1 foundation model. It leverages the powerful features extracted by OceanSAR-1 to accurately identify 10 different geophysical phenomena in Synthetic Aperture Radar (SAR) imagery.
This model is designed for automated classification of geophysical phenomena in SAR imagery over ocean surfaces. It can be used for:
The model achieves state-of-the-art performance on TenGeoP classification, with performance varying by backbone architecture:
1import torch
2from transformers import AutoModelForImageClassification
3
4# Load the foundation model and classification head
5oceansar = AutoModelForImageClassification.from_pretrained("galeio-research/OceanSAR-1-tengeop")
6
7# Prepare your SAR image (should be single-channel VV polarization)
8dummy_image = torch.randn(1, 1, 256, 256) # (B, C, H, W)
9
10# Extract features and classify geophysical phenomena
11with torch.no_grad():
12 outputs = oceansar(dummy_image)
13 predicted_class = torch.argmax(outputs.logits, dim=1).item()
1@article{kerdreux2025efficientselfsupervisedlearningearth,
2 title={Efficient Self-Supervised Learning for Earth Observation via Dynamic Dataset Curation},
3 author={Kerdreux, Thomas and Tuel, Alexandre and Febvre, Quentin and Mouche, Alexis and Chapron, Bertrand},
4 journal={arXiv preprint arXiv:2504.06962},
5 year={2025},
6 eprint={2504.06962},
7 archivePrefix={arXiv},
8 primaryClass={cs.CV},
9 url={https://arxiv.org/abs/2504.06962},
10}
This work was granted access to the HPC resources of IDRIS and TGCC under the allocation 2025-[A0171015666] made by GENCI.
