Investigating Different Geo Priors for Image Classification
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914000624680960 |
|---|---|
| author | Zhu, Angela Lange, Christian Hamilton, Max |
| author_facet | Zhu, Angela Lange, Christian Hamilton, Max |
| contents | Species distribution models encode spatial patterns of species occurrence making them effective priors for vision-based species classification when location information is available. In this study, we evaluate various SINR (Spatial Implicit Neural Representations) models as a geographical prior for visual classification of species from iNaturalist observations. We explore the impact of different model configurations and adjust how we handle predictions for species not included in Geo Prior training. Our analysis reveals factors that contribute to the effectiveness of these models as Geo Priors, factors that may differ from making accurate range maps. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_15946 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Investigating Different Geo Priors for Image Classification Zhu, Angela Lange, Christian Hamilton, Max Computer Vision and Pattern Recognition Species distribution models encode spatial patterns of species occurrence making them effective priors for vision-based species classification when location information is available. In this study, we evaluate various SINR (Spatial Implicit Neural Representations) models as a geographical prior for visual classification of species from iNaturalist observations. We explore the impact of different model configurations and adjust how we handle predictions for species not included in Geo Prior training. Our analysis reveals factors that contribute to the effectiveness of these models as Geo Priors, factors that may differ from making accurate range maps. |
| title | Investigating Different Geo Priors for Image Classification |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.15946 |