Horizon 1 1 17 ACLN : Articles dans des revues avec comité de lecture non répertoriées par l'AERES Biodiversity Information Science and Standards e135629 [4 ] 2024 fdi:010095714 ENG Biodiversity Information Science and Standards 2535-0897 10.3897/biss.8.135629 https://www.documentation.ird.fr/hor/fdi:010095714 https://horizon.documentation.ird.fr/exl-doc/pleins_textes/2025-12/010095714.pdf 8 Horizon (IRD) 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). 122INTAR ; 076BOTA