Sklab Youcef auteur aut IRD Ariaout Sklab Hanane auteur aut IRD Boujydah Y. auteur aut IRD Qacami Y. auteur aut IRD Prifti Edi auteur aut IRD Zucker Jean-Daniel auteur aut IRD Vignes Lebbe R. auteur aut IRD Chenin Eric auteur aut IRD text journalArticle eng text/pdf reformatted digital access Global digitization efforts have archived millions of specimen scans worldwide in herbarium collections, which are essential for studying plant evolution and biodiversity. ReColNat hosts, at present, over 10 million images. However, analyzing these datasets poses crucial challenges for botanical research. The application of deep learning in biodiversity analyses, particularly in analyzing herbarium scans, has shown promising results across numerous tasks (Ariouat et al. 2023, Ariouat et al. 2024, Groom et al. 2023, Sahraoui et al. 2023). specialized 122INTAR 076BOTA 8 e135629 [4 ] 2024 2535-0897 https://www.documentation.ird.fr/hor/fdi:010095714 10.3897/biss.8.135629 2535-0897 [F B010095714] https://www.documentation.ird.fr/hor/fdi:010095714 https://horizon.documentation.ird.fr/exl-doc/pleins_textes/2025-12/010095714.pdf IRD - Base Horizon / Pleins textes 2025-11-21 2025-12-03 fdi:010095714 fre