@incollection{fdi:010091413,
  title = {{E}nhancing {YOLO}v7 for plant organs detection using attention-gate mechanism},
  author = {{A}riouat {S}klab, {H}anane and {S}klab, {Y}oucef and {P}ignal, {M}. and {J}abbour, {F}. and {V}ignes {L}ebbe, {R}. and {P}rifti, {E}di and {Z}ucker, {J}ean-{D}aniel and {C}henin, {E}ric},
  editor = {},
  language = {{ENG}},
  abstract = {{H}erbarium scans are valuable raw data for studying how plants adapt to climate change and respond to various factors. {C}haracterization of plant traits from these images is important for investigating such questions, thereby supporting plant taxonomy and biodiversity description. {H}owever, processing these images for meaningful data extraction is challenging due to scale variance, complex backgrounds that contain annotations, and the variability in specimen color, shape, and orientation of specimens. {I}n addition, the plant organs often appear compressed, deformed, or damaged, with overlapping occurrences that are common in scans. {T}raditional organ recognition techniques, while adept at segmenting discernible plant characteristics, are limited in herbarium scanning applications. {T}wo automated methods for plant organ identification have been previously reported. {H}owever, they show limited effectiveness, especially for small organs. {I}n this study we introduce {YOLO}v7-ag model, which is a novel model based on the {YOLO}v7 that incorporates an attention-gate mechanism, which enhances the detection of plant organs, including stems, leaves, flowers, fruits, and seeds. {YOLO}v7-ag significantly outperforms previous state of the art as well as the original {YOLO}v7 and {YOLO}v8 models with a precision and recall rate of 99.2% and 98.0%, respectively, particularly in identifying small plant organs.},
  keywords = {},
  booktitle = {{A}dvances in knowledge discovery and data mining ({PAKDD} 2024) : 28th {P}acific-{A}sia {C}onference on {K}nowledge {D}iscovery and {D}ata {M}ining},
  numero = {14646},
  pages = {223--234},
  address = {{S}ingapour},
  publisher = {{S}pringer},
  series = {{L}ecture {N}otes in {C}omputer {S}cience : {L}ecture {N}otes in {A}rtificial {I}ntelligence},
  year = {2024},
  DOI = {10.1007/978-981-97-2253-2_18},
  ISBN = {978-981-97-2252-5},
  URL = {https://www.documentation.ird.fr/hor/fdi:010091413},
}