# One-Shot Adaptive Segmentation For Scientific Images

arXiv: https://arxiv.org/abs/2610.10306 · HTML: https://mlsanity.com/paper/2610.10306/

## Key facts

- No citing papers in the map yet (data through 7 Oct 2026).
- Builds on 3 of its 13 references that are in the map.
- First posted on arXiv 7 Oct 2026.

## Builds on (most cited first, 3 of 3)

- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [INSID3: Training-Free In-Context Segmentation with DINOv3](https://mlsanity.com/paper/2603.28480/) (2026)
- [Deep Learning Segmentation and Classification of Red Blood Cells Using a Large Multi-Scanner Dataset](https://mlsanity.com/paper/2403.18468/) (2024)

## Abstract (arXiv)

Scientific image segmentation methods rely on extensive annotation and task-specific training, limiting adaptation across imaging modalities and experimental conditions. We present a training-free, one-shot framework that specializes vision foundation models using a single annotated reference image. The framework combines DINOv3 representations with background-adaptive feature orthogonalization to suppress artifact-related feature directions, after which cosine similarity localizes candidate regions for SAM segmentation. We evaluate the framework on red-blood-cell microscopy, structured-illumination pool boiling, and chest radiography. Relative to the strongest baseline, the proposed method improves mean IoU by 5.91% and 78.62% on the microscopy and pool-boiling datasets, respectively, while achieving comparable performance on chest radiographs. These results demonstrate that one-shot reference conditioning can adapt general-purpose vision models to specialized scientific segmentation tasks.