Metraipolis › archive › dc_2145df85095d

Cross-Dataset Transfer and Unknown-Class Detection in Imbalanced SAR Ship Classification — arXiv:2609.31658

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.31658
License (as archived)
CC0-1.0
Archived
2026-10-07T20:59:17.686Z
SHA-256 of the archived text
a7dd38c37e74f0c3650ce2a2182e4e6862c30329bece763a745a234b4e57aa02
Stable URL of this page
https://metraipolis.com/documento/dc_2145df85095d

How to cite

Cross-Dataset Transfer and Unknown-Class Detection in Imbalanced SAR Ship Classification — arXiv:2609.31658 — arXiv (en), https://arxiv.org/abs/2609.31658 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2145df85095d (Metraipolis archive dc_2145df85095d, sha256 a7dd38c37e74f0c3650ce2a2182e4e6862c30329bece763a745a234b4e57aa02)
BibTeX
@misc{dc2145df85095d,
  title = {Cross-Dataset Transfer and Unknown-Class Detection in Imbalanced SAR Ship Classification — arXiv:2609.31658},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31658},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2145df85095d; sha256 a7dd38c37e74f0c3650ce2a2182e4e6862c30329bece763a745a234b4e57aa02},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31658. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Ship classification from Synthetic Aperture Radar (SAR) imagery is a critical computer vision task, yet the robustness of models under deployment shifts remains unclear. While models are often trained on one dataset and deployed on another, we lack a comprehensive understanding of their cross-dataset generalization. To address this, we evaluate six pretrained models on two SAR ship datasets in three settings: in-domain classification, cross-dataset transfer, and unknown-class detection. For unknown detection, we hold out all classes one at a time. In-domain, SARDet100K gives the best balanced accuracy on both datasets (73.4\% on FUSARShip and 53.2\% on OpenSARShip). In cross-dataset transfer, we observe strong failures: some models show moderate accuracy but near-chance balanced accuracy (for example, 64.5\% accuracy but 33.3\% balanced accuracy for OpenSARShip to FUSARShip). In unknown detection, performance depends on the held-out class and dataset, while MC-dropout variance is often close to random. These findings show that cross-dataset generalization in SAR remains limited and that task-specific uncertainty scores are often more informative than MC-dropout variance for held-out-class detection, although their relative ranking depends on the dataset and held-out class.

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/2609.31658 — 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 2026-10-07T20:29:02.004Z 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).