Metraipolis › archive › dc_74eae4d09bf2

How Far Can INRs Go? Cross-Domain Parameter-efficient INR-Based Semantic Segmentation for Brain MRI — arXiv:2609.31573

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.31573
License (as archived): CC0-1.0
Archived: 2026-10-08T03:12:50.718Z
SHA-256 of the archived text: 6285bc0113a10c8c55983cad1a7e327e2b7654cde0da379a2f954a5c88b4d440
Stable URL of this page: https://metraipolis.com/documento/dc_74eae4d09bf2

How to cite

How Far Can INRs Go? Cross-Domain Parameter-efficient INR-Based Semantic Segmentation for Brain MRI — arXiv:2609.31573 — arXiv (en), https://arxiv.org/abs/2609.31573 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_74eae4d09bf2 (Metraipolis archive dc_74eae4d09bf2, sha256 6285bc0113a10c8c55983cad1a7e327e2b7654cde0da379a2f954a5c88b4d440)

BibTeX

@misc{dc74eae4d09bf2,
  title = {How Far Can INRs Go? Cross-Domain Parameter-efficient INR-Based Semantic Segmentation for Brain MRI — arXiv:2609.31573},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31573},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_74eae4d09bf2; sha256 6285bc0113a10c8c55983cad1a7e327e2b7654cde0da379a2f954a5c88b4d440},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31573. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Biomedical image segmentation is central to medical image analysis, but practical deployment often faces limited annotations, memory constraints, and cross-site distribution shifts. Implicit Neural Representations (INRs) have recently emerged as a lightweight alternative for semantic segmentation, achieving competitive performance with substantially fewer parameters than conventional architectures. However, the mechanisms, scaling behavior, and domain generalization abilities of INR-based segmentation remain insufficiently understood. In this work, we study these questions in the context of cross-domain brain MRI segmentation. We analyze INR-based segmentation across low-parameter regimes, comparing it with conventional pipelines in both in-domain and out-of-domain settings. Surprisingly, we find that INR-based models do not simply improve with increasing parameter budget. Their advantage is most pronounced under low-parameter and limited-augmentation settings, while U-Net-based models benefit more from larger capacity and standard augmentation. We also investigate how INRs encode semantic information in their hidden features and show that complementary segmentation-relevant structure is distributed across multiple INR layers. Building on this insight, we introduce HierINRSeg, a hierarchical INR-based architecture that aggregates multi-layer representations for improved robustness and generalization. Extensive experiments show that HierINRSeg consistently outperforms MetaSeg, a strong recent INR-based segmentation baseline, with an average improvement of 5.6 percentage points in Dice for the in-domain test set and 8.2 percentage points out-of-domain. Overall, our analysis identifies the conditions under which INR-based segmentation is most effective, providing concrete guidance for model selection and future research.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-28 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.31573 — 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 2026-10-08T02:50:19.123Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).