Metraipolis › archive › dc_828edcc7e238

CoRe-SAM3: Conditional Semantic--Visual Reconciliation for SAM3 Crack Segmentation — arXiv:2609.05816

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.05816
License (as archived)
CC0-1.0
Archived
2026-10-16T15:06:37.750Z
SHA-256 of the archived text
1dafb7cbbd32062e31b1dcc737a6c2c335320d6b7435d7b3cdfa316640440df4
Stable URL of this page
https://metraipolis.com/documento/dc_828edcc7e238

How to cite

CoRe-SAM3: Conditional Semantic--Visual Reconciliation for SAM3 Crack Segmentation — arXiv:2609.05816 — arXiv (en), https://arxiv.org/abs/2609.05816 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_828edcc7e238 (Metraipolis archive dc_828edcc7e238, sha256 1dafb7cbbd32062e31b1dcc737a6c2c335320d6b7435d7b3cdfa316640440df4)
BibTeX
@misc{dc828edcc7e238,
  title = {CoRe-SAM3: Conditional Semantic--Visual Reconciliation for SAM3 Crack Segmentation — arXiv:2609.05816},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.05816},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_828edcc7e238; sha256 1dafb7cbbd32062e31b1dcc737a6c2c335320d6b7435d7b3cdfa316640440df4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05816. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Crack segmentation requires a model to recognize target semantics while accurately recovering thin, low-contrast, and topologically continuous local structures. Although SAM3 provides strong open-concept segmentation, its direct application to the crack domain still misses weak cracks, activates crack-like background regions, and produces local boundary errors. We first diagnose the functional differences between the internal prompt-conditioned semantic representation and native visual representation of SAM3 on five crack datasets. The results show that the semantic representation already carries most task information for crack prediction, whereas the utility of the visual representation depends on the current semantic state. Directly combining the two representations does not yield consistent gains. Based on this finding, we propose Conditional Semantic--Visual Reconciliation, termed CoRe. CoRe retains semantic prediction as the primary decision path, applies lightweight semantic calibration to adjust the target-domain decision mapping, and uses spatially aligned native visual evidence to generate a zero-initialized, bounded, and regularized conditional residual that selectively corrects existing predictions. Across five domains, CoRe-SAM3 improves the average Crack IoU from 62.34% to 70.47% and clDice from 81.98% to 89.24%, while introducing only 18.914 K trainable parameters. Prediction-transition analysis further shows that CoRe corrects an average of 34.38% of native errors, with a damage rate of only 0.23% on pixels correctly classified by native SAM3. These results demonstrate that constrained prediction correction based on the functional differences between internal representations provides an effective and parameter-efficient target-domain adaptation strategy for vision foundation models with strong task-specific semantic priors.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.05816 — 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 2026-10-16T14:49:57.004Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).