# P3CA: Encoder-Agnostic Interpretation of Vision Foundation Model Embeddings via Spatial Probing

arXiv: https://arxiv.org/abs/2608.10131 · HTML: https://mlsanity.com/paper/2608.10131/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 22 references that are in the map.
- First posted on arXiv 10 Aug 2026.

## Builds on (most cited first, 10 of 10)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Contrastive learning of global and local features for medical image segmentation with limited annotations](https://mlsanity.com/paper/2006.10511/) (2020)
- [Probing the 3D Awareness of Visual Foundation Models](https://mlsanity.com/paper/2404.08636/) (2024)
- [On the Challenges and Perspectives of Foundation Models for Medical Image Analysis](https://mlsanity.com/paper/2306.05705/) (2023)
- [Distilling foundation models for robust and efficient models in digital pathology](https://mlsanity.com/paper/2501.16239/) (2025)
- [A General Protocol to Probe Large Vision Models for 3D Physical Understanding](https://mlsanity.com/paper/2310.06836/) (2023)
- [Detecting Shortcuts in Medical Images -- A Case Study in Chest X-rays](https://mlsanity.com/paper/2211.04279/) (2022)

## Abstract (arXiv)

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.