WildFusion: Individual Animal Identification with Calibrated Similarity Fusion
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917756346040320 |
|---|---|
| author | Cermak, Vojtěch Picek, Lukas Adam, Lukáš Neumann, Lukáš Matas, Jiří |
| author_facet | Cermak, Vojtěch Picek, Lukas Adam, Lukáš Neumann, Lukáš Matas, Jiří |
| contents | We propose a new method - WildFusion - for individual identification of a broad range of animal species. The method fuses deep scores (e.g., MegaDescriptor or DINOv2) and local matching similarity (e.g., LoFTR and LightGlue) to identify individual animals. The global and local information fusion is facilitated by similarity score calibration. In a zero-shot setting, relying on local similarity score only, WildFusion achieved mean accuracy, measured on 17 datasets, of 76.2%. This is better than the state-of-the-art model, MegaDescriptor-L, whose training set included 15 of the 17 datasets. If a dataset-specific calibration is applied, mean accuracy increases by 2.3% percentage points. WildFusion, with both local and global similarity scores, outperforms the state-of-the-art significantly - mean accuracy reached 84.0%, an increase of 8.5 percentage points; the mean relative error drops by 35%. We make the code and pre-trained models publicly available5, enabling immediate use in ecology and conservation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_12934 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | WildFusion: Individual Animal Identification with Calibrated Similarity Fusion Cermak, Vojtěch Picek, Lukas Adam, Lukáš Neumann, Lukáš Matas, Jiří Computer Vision and Pattern Recognition We propose a new method - WildFusion - for individual identification of a broad range of animal species. The method fuses deep scores (e.g., MegaDescriptor or DINOv2) and local matching similarity (e.g., LoFTR and LightGlue) to identify individual animals. The global and local information fusion is facilitated by similarity score calibration. In a zero-shot setting, relying on local similarity score only, WildFusion achieved mean accuracy, measured on 17 datasets, of 76.2%. This is better than the state-of-the-art model, MegaDescriptor-L, whose training set included 15 of the 17 datasets. If a dataset-specific calibration is applied, mean accuracy increases by 2.3% percentage points. WildFusion, with both local and global similarity scores, outperforms the state-of-the-art significantly - mean accuracy reached 84.0%, an increase of 8.5 percentage points; the mean relative error drops by 35%. We make the code and pre-trained models publicly available5, enabling immediate use in ecology and conservation. |
| title | WildFusion: Individual Animal Identification with Calibrated Similarity Fusion |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.12934 |