Overview of PlantCLEF 2025: Multi-Species Plant Identification in Vegetation Quadrat Images
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915506583240704 |
|---|---|
| author | Martellucci, Giulio Goeau, Herve Bonnet, Pierre Vinatier, Fabrice Joly, Alexis |
| author_facet | Martellucci, Giulio Goeau, Herve Bonnet, Pierre Vinatier, Fabrice Joly, Alexis |
| contents | Quadrat images are essential for ecological studies, as they enable standardized sampling, the assessment of plant biodiversity, long-term monitoring, and large-scale field campaigns. These images typically cover an area of fifty centimetres or one square meter, and botanists carefully identify all the species present. Integrating AI could help specialists accelerate their inventories and expand the spatial coverage of ecological studies. To assess progress in this area, the PlantCLEF 2025 challenge relies on a new test set of 2,105 high-resolution multi-label images annotated by experts and covering around 400 species. It also provides a large training set of 1.4 million individual plant images, along with vision transformer models pre-trained on this data. The task is formulated as a (weakly labelled) multi-label classification problem, where the goal is to predict all species present in a quadrat image using single-label training data. This paper provides a detailed description of the data, the evaluation methodology, the methods and models used by participants, and the results achieved. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17602 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Overview of PlantCLEF 2025: Multi-Species Plant Identification in Vegetation Quadrat Images Martellucci, Giulio Goeau, Herve Bonnet, Pierre Vinatier, Fabrice Joly, Alexis Computer Vision and Pattern Recognition Quadrat images are essential for ecological studies, as they enable standardized sampling, the assessment of plant biodiversity, long-term monitoring, and large-scale field campaigns. These images typically cover an area of fifty centimetres or one square meter, and botanists carefully identify all the species present. Integrating AI could help specialists accelerate their inventories and expand the spatial coverage of ecological studies. To assess progress in this area, the PlantCLEF 2025 challenge relies on a new test set of 2,105 high-resolution multi-label images annotated by experts and covering around 400 species. It also provides a large training set of 1.4 million individual plant images, along with vision transformer models pre-trained on this data. The task is formulated as a (weakly labelled) multi-label classification problem, where the goal is to predict all species present in a quadrat image using single-label training data. This paper provides a detailed description of the data, the evaluation methodology, the methods and models used by participants, and the results achieved. |
| title | Overview of PlantCLEF 2025: Multi-Species Plant Identification in Vegetation Quadrat Images |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.17602 |