dorsal/arxiv
View SchemaNear-perfect photo-ID of the Hula painted frog with zero-shot deep local-feature matching
| Authors | Maayan Yesharim, R. G. Bina Perl, Uri Roll, Sarig Gafny, Eli Geffen, Yoav Ram |
|---|---|
| Categories | |
| ArXiv ID | 2601.08798vv1 |
| URL | https://arxiv.org/abs/2601.08798 |
| License | http://creativecommons.org/licenses/by-sa/4.0/ |
Abstract
Accurate individual identification is essential for monitoring rare amphibians, yet invasive marking is often unsuitable for critically endangered species. We evaluate state-of-the-art computer-vision methods for photographic re-identification of the Hula painted frog (Latonia nigriventer) using 1,233 ventral images from 191 individuals collected during 2013-2020 capture-recapture surveys. We compare deep local-feature matching in a zero-shot setting with deep global-feature embedding models. The local-feature pipeline achieves 98% top-1 closed-set identification accuracy, outperforming all global-feature models; fine-tuning improves the best global-feature model to 60% top-1 (91% top-10) but remains below local matching. To combine scalability with accuracy, we implement a two-stage workflow in which a fine-tuned global-feature model retrieves a short candidate list that is re-ranked by local-feature matching, reducing end-to-end runtime from 6.5-7.8 hours to ~38 minutes while maintaining ~96% top-1 closed-set accuracy on the labeled dataset. Separation of match scores between same- and different-individual pairs supports thresholding for open-set identification, enabling practical handling of novel individuals. We deploy this pipeline as a web application for routine field use, providing rapid, standardized, non-invasive identification to support conservation monitoring and capture-recapture analyses. Overall, in this species, zero-shot deep local-feature matching outperformed global-feature embedding and provides a strong default for photo-identification.
{
"annotation_id": "ea4be436-5ca7-47c7-957f-2a73188371fa",
"date_created": "2026-02-17T05:53:16.089000Z",
"date_modified": "2026-02-17T05:53:16.089000Z",
"file_hash": "4d67937c3905c1ab7c9fb607bb50378a31db29e7591aa2ad4d5bdb98cc57b653",
"private": false,
"record": {
"abstract": "Accurate individual identification is essential for monitoring rare amphibians, yet invasive marking is often unsuitable for critically endangered species. We evaluate state-of-the-art computer-vision methods for photographic re-identification of the Hula painted frog (Latonia nigriventer) using 1,233 ventral images from 191 individuals collected during 2013-2020 capture-recapture surveys. We compare deep local-feature matching in a zero-shot setting with deep global-feature embedding models. The local-feature pipeline achieves 98% top-1 closed-set identification accuracy, outperforming all global-feature models; fine-tuning improves the best global-feature model to 60% top-1 (91% top-10) but remains below local matching. To combine scalability with accuracy, we implement a two-stage workflow in which a fine-tuned global-feature model retrieves a short candidate list that is re-ranked by local-feature matching, reducing end-to-end runtime from 6.5-7.8 hours to ~38 minutes while maintaining ~96% top-1 closed-set accuracy on the labeled dataset. Separation of match scores between same- and different-individual pairs supports thresholding for open-set identification, enabling practical handling of novel individuals. We deploy this pipeline as a web application for routine field use, providing rapid, standardized, non-invasive identification to support conservation monitoring and capture-recapture analyses. Overall, in this species, zero-shot deep local-feature matching outperformed global-feature embedding and provides a strong default for photo-identification.",
"arxiv_id": "2601.08798",
"authors": [
"Maayan Yesharim",
"R. G. Bina Perl",
"Uri Roll",
"Sarig Gafny",
"Eli Geffen",
"Yoav Ram"
],
"categories": [
"cs.CV",
"q-bio.QM"
],
"license": "http://creativecommons.org/licenses/by-sa/4.0/",
"title": "Near-perfect photo-ID of the Hula painted frog with zero-shot deep local-feature matching",
"url": "https://arxiv.org/abs/2601.08798",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "55f2ef09-5534-4149-9a1d-83dbf19e2ba2",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}