Metraipolis › archive › dc_0f2dcbcd0871

P3CA: Encoder-Agnostic Interpretation of Vision Foundation Model Embeddings via Spatial Probing — arXiv:2608.10131

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.10131
License (as archived)
CC0-1.0
Archived
2026-10-19T06:19:40.683Z
SHA-256 of the archived text
c10cb410b6bd3e51c3aee262cc49e5793487873aa63d6d9367f340d6d5745e55
Stable URL of this page
https://metraipolis.com/documento/dc_0f2dcbcd0871

How to cite

P3CA: Encoder-Agnostic Interpretation of Vision Foundation Model Embeddings via Spatial Probing — arXiv:2608.10131 — arXiv (en), https://arxiv.org/abs/2608.10131 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0f2dcbcd0871 (Metraipolis archive dc_0f2dcbcd0871, sha256 c10cb410b6bd3e51c3aee262cc49e5793487873aa63d6d9367f340d6d5745e55)
BibTeX
@misc{dc0f2dcbcd0871,
  title = {P3CA: Encoder-Agnostic Interpretation of Vision Foundation Model Embeddings via Spatial Probing — arXiv:2608.10131},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.10131},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0f2dcbcd0871; sha256 c10cb410b6bd3e51c3aee262cc49e5793487873aa63d6d9367f340d6d5745e55},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10131. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision foundation models are increasingly used as reusable encoders in medical image computing, yet their high-dimensional spatial embeddings are difficult to inspect beyond downstream task performance or global dimensionality reduction. We propose position-prompted PCA (P3CA), an encoder-agnostic method for local probing of channel-rich spatial tensors. Given a user-selected spatial prompt, P3CA estimates the feature normalization and dominant covariance directions within that region, then applies the resulting projection to the full tensor to visualize where locally informative directions are expressed. This produces a region-conditioned representation lens without modifying the encoder, retraining, or requiring task-specific labels. We implement P3CA in EmbedVision, an interactive 3D Slicer-based workflow, and evaluate it across natural images, colorectal pathology foundation-model embeddings, and spatial transcriptomic tensors. Across these settings, prompted projections reveal local structure suppressed by global PCA, improve prompt-matched pathology discrimination from frozen three-dimensional projections, and support comparison between learned and measured spatial representations.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.LG).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.10131 — 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 2026-10-19T06:11:45.123Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).