This is yet another case where the CV needs to include the genus but can’t because of how the CV system is set up. See https://forum.inaturalist.org/t/allow-some-non-leaf-taxa-to-be-added-to-the-cv-model/63937, https://forum.inaturalist.org/t/allow-for-genus-level-cv-training-sets-irrespective-of-species-level-participation/63938, https://forum.inaturalist.org/t/computer-vision-should-take-into-account-fraction-identified-to-species/60097, https://forum.inaturalist.org/t/are-genus-level-rg-observations-used-for-cv-training/63859, and the many other discussions about this. Unfortunately, the person who developed iNaturalist’s CV system recently left, so this problem is unlikely to be addressed any time soon.
zygy
3
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| When the CV has confidently mis-learned a species | 65 | 1308 | August 15, 2026 | |
| CV not suggesting species-complexes | 22 | 555 | September 19, 2025 | |
| Are genus-level RG observations used for CV training? | 38 | 992 | April 16, 2025 | |
| Once something is incorrectly in the CV model, there's no removing it without diligent effort | 34 | 1086 | October 15, 2025 | |
| Leafminers have broken the CV | 68 | 2550 | October 6, 2024 |