Metraipolis › archive › dc_6944e3967378

Enhancing Foundation Models for Imbalanced SAR Ship Classification via Targeted Oversampling — arXiv:2609.31657

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.31657
License (as archived)
CC0-1.0
Archived
2026-10-07T20:59:17.173Z
SHA-256 of the archived text
40f4993318e559d31fc62eb3966ec1b9cbd5ff77b5935ec359d0b6e04d064fc4
Stable URL of this page
https://metraipolis.com/documento/dc_6944e3967378

How to cite

Enhancing Foundation Models for Imbalanced SAR Ship Classification via Targeted Oversampling — arXiv:2609.31657 — arXiv (en), https://arxiv.org/abs/2609.31657 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6944e3967378 (Metraipolis archive dc_6944e3967378, sha256 40f4993318e559d31fc62eb3966ec1b9cbd5ff77b5935ec359d0b6e04d064fc4)
BibTeX
@misc{dc6944e3967378,
  title = {Enhancing Foundation Models for Imbalanced SAR Ship Classification via Targeted Oversampling — arXiv:2609.31657},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31657},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6944e3967378; sha256 40f4993318e559d31fc62eb3966ec1b9cbd5ff77b5935ec359d0b6e04d064fc4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31657. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Remote-sensing foundation models offer strong representations for SAR imagery, but their behavior under severe long-tail class imbalance is still not well characterized. We benchmark DOFA and SAR-JEPA on the imbalanced OpenSARShip dataset and compare them with ImageNet-pretrained baselines under a fixed, training-efficient protocol that keeps the backbone frozen. To mitigate imbalance without fine-tuning, we apply four oversampling methods in embedding space exclusively to minority classes and train a lightweight classifier head on the augmented embeddings. Across both foundation models, oversampling improves Macro-F1 and test accuracy relative to their respective baselines, with the largest Macro-F1 gains observed for DOFA using ADASYN (34.39 to 38.56) and for SAR-JEPA using SVM-SMOTE (25.89 to 32.30). We also report class-wise behavior, showing that aggregate improvements can coexist with persistent failures on specific rare classes. Code for embedding extraction and reproducible multi-seed evaluation is provided to support rapid experimentation on free-tier hardware.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.31657 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T20:29:02.003Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).