Metraipolis › archive › dc_549a76d65306
DINO-Nucleus: Multi-Level Self-Supervised Features for Nucleus Instance Segmentation — arXiv:2611.09133
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.09133
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-09T22:45:16.904Z
- SHA-256 of the archived text
5a4954066717b51e45e07b6f79a09e0fc770a64978183fe0fbcbea8e9aadb7cd- Stable URL of this page
https://metraipolis.com/documento/dc_549a76d65306
How to cite
DINO-Nucleus: Multi-Level Self-Supervised Features for Nucleus Instance Segmentation — arXiv:2611.09133 — arXiv (en), https://arxiv.org/abs/2611.09133 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_549a76d65306 (Metraipolis archive dc_549a76d65306, sha256 5a4954066717b51e45e07b6f79a09e0fc770a64978183fe0fbcbea8e9aadb7cd)
BibTeX
@misc{dc549a76d65306,
title = {DINO-Nucleus: Multi-Level Self-Supervised Features for Nucleus Instance Segmentation — arXiv:2611.09133},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.09133},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_549a76d65306; sha256 5a4954066717b51e45e07b6f79a09e0fc770a64978183fe0fbcbea8e9aadb7cd},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09133. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Nucleus instance segmentation and counting are essential for quantitative microscopy, enabling reliable analysis of cell populations, tissue organization, and disease-related changes. However, accurately separating touching nuclei remains difficult, and many existing approaches rely on complex models or sensitive post-processing procedures. We present DINO-Nucleus, a parameter-efficient framework that leverages multi-level self-supervised DINOv2 representations for nucleus instance segmentation and counting. The model jointly predicts nucleus regions, pixel-wise instance flows, and explicit nucleus centers, while a consistency objective encourages the predicted flows to converge toward their corresponding centers. Multi-level transformer features provide complementary spatial and semantic information, and the pretrained backbone is adapted using lightweight LoRA modules to reduce fine-tuning cost. Experimental results show that DINO-Nucleus achieves strong segmentation and counting performance with parameter-efficient backbone adaptation. These findings demonstrate that parameter-efficient adaptation of multi-level self-supervised features can provide an effective solution for nucleus instance segmentation in microscopy images. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2611.09133 — 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 2026-11-09T22:37:47.224Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).