Convpaint - Universal framework for interactive pixel classification using pretrained neural networks
Lucien Hinderling, Guillaume Witz, Roman Schwob, Ana Stojiljković, Maciej Dobrzyński, Mykhailo Vladymyrov, Joël Frei, Benjamin Grädel, Agne Frismantiene, Olivier C. Pertz · bioRxiv (Cold Spring Harbor Laboratory) · 2024
We develop Convpaint, a universal computational framework for interactive pixel classification. Convpaint utilizes pretrained convolutional neural networks (CNNs) or vision transformers (ViTs) for feature extraction and enables easy segmentation across a wide variety of tasks. Available within the Python-based napari software ecosystem, Convpaint integrates seamlessly with other plugins into image processing pipelines, which we demonstrate with three workflows across different data modalities.