Metraipolis › archive › dc_df522b871aa1
Pix2Rep-v2: Data-Efficient Representation Learning for Dense Medical Imaging Applications — arXiv:2609.01427
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.01427
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T07:13:57.085Z
- SHA-256 of the archived text
992b8a57547e118c7c4dea0cb2485e275f20d8af4a4cc8999364bf46fcdde4da- Stable URL of this page
https://metraipolis.com/documento/dc_df522b871aa1
How to cite
Pix2Rep-v2: Data-Efficient Representation Learning for Dense Medical Imaging Applications — arXiv:2609.01427 — arXiv (en), https://arxiv.org/abs/2609.01427 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_df522b871aa1 (Metraipolis archive dc_df522b871aa1, sha256 992b8a57547e118c7c4dea0cb2485e275f20d8af4a4cc8999364bf46fcdde4da)
BibTeX
@misc{dcdf522b871aa1,
title = {Pix2Rep-v2: Data-Efficient Representation Learning for Dense Medical Imaging Applications — arXiv:2609.01427},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.01427},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_df522b871aa1; sha256 992b8a57547e118c7c4dea0cb2485e275f20d8af4a4cc8999364bf46fcdde4da},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01427. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Dense self-supervised learning (SSL) is a powerful paradigm for learning without annotations the local descriptors required to solve dense medical imaging tasks. We present Pix2Rep-v2, a framework for SSL of pixel- and voxel-level representations suitable for few-shot downstream applications. Pix2Rep-v2 addresses the main challenges of dense SSL by leveraging a redundancy reduction objective at the pixel-level with a principle of equivariance of dense representations, that scales efficiently to 3D or wide field-of-view applications. We evaluate our method on four datasets, across multiple tasks, multiple modalities and anatomical structures using multiple backbones in 2D and 3D, and under various data regimes. As an alternative to linear probing or full fine-tuning on the downstream task, we also propose an in-context variant, without downstream training, based on a dense prototype approach. Pix2Rep-v2 shows substantially higher data-efficiency in few-shot scenarios compared to fully supervised baselines, and is competitive with the state-of-the-art e.g., +9.3 Dice points in one-shot segmentation on the M&Ms-2 dataset. Our code and pre-trained models are publicly available at this https URL . 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/2609.01427 — 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 2026-10-17T07:00:58.988Z 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).