OneRosette to predict them all: single plant prompting on a visual foundation model to segment symptomatic Arabidopsis thaliana time series
This work provides a pipeline to segment symptomatic A. thaliana plants by leveraging a visual foundation model. The method has been used successfully on two different pathogens, is fast to train, and does not need a large dedicated graphical processing unit. Our method has characterized plant-pathogen interactions of two pathosystems without fine-tuning for the second pathosystem. Its ease of use and low computing requirements should make adapting our approach to other high-throughput phenotyping platforms easy.
Authors
- Nemo Peeters (ORCID: https://orcid.org/0000-0002-1802-0769)
- Felicià Maviane Maciá
- David Rousseau (ORCID: https://orcid.org/0000-0002-7935-1609)
- Sabine Wiedemann-Merdinoglu (ORCID: https://orcid.org/0000-0002-2531-9603)
Institutions
- Centre National de la Recherche Scientifique (FR)
- Institut National de Recherche pour l'Agriculture, l'Alimentation et l'Environnement (FR)
- Laboratoire des Interactions Plantes Microbes Environnement (FR)
- Institut de Recherche en Horticulture et Semences (FR)
- Université d'Angers (FR)
- Université de Strasbourg (FR)
Publication Details
- Journal
- Plant Methods
- Published
- 2025-10-09
- DOI
- https://doi.org/10.1186/s13007-025-01432-2
- Primary Topic
- Plant Pathogenic Bacteria Studies
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Agence Nationale de la Recherche
- Institut National de Recherche pour l'Agriculture, l'Alimentation et l'Environnement