Metraipolis › archive › dc_cf208cba83ec
SAM3-LoRA: Parameter-Efficient Adaptation of a Concept-Promptable Foundation Model for Multi-Class Structural Defect Segmentation — arXiv:2609.00469
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.00469
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T07:10:37.226Z
- SHA-256 of the archived text
b7fb47b6e1a70e69384022a48c231a55f1a0a5c94c729c9d9d9f20df80ba2f9c- Stable URL of this page
https://metraipolis.com/documento/dc_cf208cba83ec
How to cite
SAM3-LoRA: Parameter-Efficient Adaptation of a Concept-Promptable Foundation Model for Multi-Class Structural Defect Segmentation — arXiv:2609.00469 — arXiv (en), https://arxiv.org/abs/2609.00469 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cf208cba83ec (Metraipolis archive dc_cf208cba83ec, sha256 b7fb47b6e1a70e69384022a48c231a55f1a0a5c94c729c9d9d9f20df80ba2f9c)
BibTeX
@misc{dccf208cba83ec,
title = {SAM3-LoRA: Parameter-Efficient Adaptation of a Concept-Promptable Foundation Model for Multi-Class Structural Defect Segmentation — arXiv:2609.00469},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.00469},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cf208cba83ec; sha256 b7fb47b6e1a70e69384022a48c231a55f1a0a5c94c729c9d9d9f20df80ba2f9c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00469. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Promptable segmentation foundation models such as SAM3 accept an open-vocabulary text concept and return every instance matching it, but adapting them to a specialized domain by full fine-tuning is computationally prohibitive for the organizations that would benefit most. This study applies Low-Rank Adaptation (LoRA) to SAM3 for multi-class structural defect segmentation and examines both how such a model can be supervised from conventional annotation and whether the resulting efficiency gain transfers across datasets. Two contributions are methodological. First, we describe a supervision procedure that trains a concept-promptable model directly from COCO-style class-labeled instance segmentation by using the category name itself as the prompt, requiring no prompt templates, no synonym expansion, and no learned class embeddings. Second, we identify and mitigate a failure mode specific to this setting: because a conventional annotation file yields positive prompts exclusively, the model's presence prediction decouples from the text condition and degenerates into responding to any prompt, a collapse that is invisible to every metric computed on positive prompts alone. Exhaustive hard-negative prompting, in which every dataset category absent from an image is issued as a zero-detection query, addresses this at no annotation cost. Two adapter placements were compared under an identical protocol, updating 0.121% and 1.341% of model parameters. On a purpose-built tunnel lining dataset, pixel intersection-over-union improved from 0.017 to 0.338 and instance-level recall from 0.375 to 0.672; on the independent public Structural Defects Dataset, from 0.017 to 0.855 and from 0.574 to 1.000. Improvements were directionally consistent across ten metrics on both datasets, and the largest per-category gains occurred precisely where zero-shot competence was absent. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-02 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.00469 — 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 2026-10-17T07:00:58.905Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).