Feature Forest

A napari plugin for making image annotation using feature space of vision transformers and random forest classifier.
We developed a napari plugin to train a Random Forest model using extracted features of vision foundation models and just a few scribble labels provided by the user as input. This approach can do the segmentation of desired objects almost as well as manual segmentations but in a much shorter time with less manual effort.

---

Documentation

You can check the documentation here (⚠️ work in progress!).

Installation

We provided install.sh for Linux & Mac OS users, and install.bat for Windows users.
First you need to clone the repo:

git clone https://github.com/juglab/featureforest
cd ./featureforest

Now run the installation script:

# Linux or Mac OS
sh ./install.sh

# Windows
./install.bat

For developers that want to contribute to FeatureForest, you need to use this command to install the dev dependencies:

pip install -U "featureforest[dev]"

And make sure you have pre-commit installed in your environment, before committing changes:

pre-commit install

For more detailed installation guide, check out here.

Cite us

Seifi, Mehdi, Damian Dalle Nogare, Juan Battagliotti, Vera Galinova, Ananya Kediga Rao, Pierre-Henri Jouneau, Anwai Archit, AI4Life Horizon Europe Programme Consortium, Constantin Pape, Johan Decelle, Florian Jug, and Joran Deschamps. FeatureForest: the power of foundation models, the usability of random forests. npj Imaging 3, 32 (2025). DOI: 10.1038/s44303-025-00089-9

License

Distributed under the terms of the BSD-3 license, "featureforest" is free and open source software.

Issues

If you encounter any problems, please file an issue along with a detailed description.