One-shot method adapts vision models for varied scientific images

One-Shot Adaptive Segmentation For Scientific Images

Computer Vision and Pattern Recognition

Summary

Segmenting scientific images usually needs lots of labeled examples and training for each kind of image. The authors created a method that only needs one labeled image to adjust general vision models to new scientific images without retraining. Their technique uses smart features to ignore unwanted parts and then finds regions to segment. It worked well on different types of scientific images, improving accuracy especially where previous methods struggled.

What this means in practice

  • For medical imaging analysts: Accurately segment different medical images using only one annotated example to adapt existing models quickly to new conditions.
  • For laboratory technicians: Segment microscopy images across different experimental setups without needing extensive retraining for each dataset.

Authors

Tejaswi V. Panchagnula, Allison M. Davis, Fengqing Zhu

Abstract

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.