AAitorG/napari-DINOSim
This repository provides DINOSim, a method that leverages the DINOv2 foundation model for zero-shot object detection and segmentation in bioimage analysis. DINOSim uses pretrained DINOv2 embeddings to compare patch similarities, allowing it to detect and segment unseen objects in complex datasets with minimal annotations.
GitHub repository with 22 stars and 4 forks.
Language: Python
Topics: biomedical-imaging, computer-vision, deep-learning, microscopy, pytorch