One-Shot Adaptive Segmentation For Scientific Images
Scientific image segmentation methods rely on extensive annotation and task-specific training, limiting adaptation across imaging modalities and experimental conditions.
ProofPaper ↗
Key points
- 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.
- These results demonstrate that one-shot reference conditioning can adapt general-purpose vision models to specialized scientific segmentation tasks.
Sources (1)
- [1]One-Shot Adaptive Segmentation For Scientific ImagesarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 04:02 PM
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.
Extractive summary: sentences quoted from the sources.