WildlifeReID-10k: Wildlife re-identification dataset with 10k individual animals
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908319230197760 |
|---|---|
| author | Adam, Lukáš Čermák, Vojtěch Papafitsoros, Kostas Picek, Lukas |
| author_facet | Adam, Lukáš Čermák, Vojtěch Papafitsoros, Kostas Picek, Lukas |
| contents | This paper introduces WildlifeReID-10k, a new large-scale re-identification benchmark with more than 10k animal identities of around 33 species across more than 140k images, re-sampled from 37 existing datasets. WildlifeReID-10k covers diverse animal species and poses significant challenges for SoTA methods, ensuring fair and robust evaluation through its time-aware and similarity-aware split protocol. The latter is designed to address the common issue of training-to-test data leakage caused by visually similar images appearing in both training and test sets. The WildlifeReID-10k dataset and benchmark are publicly available on Kaggle, along with strong baselines for both closed-set and open-set evaluation, enabling fair, transparent, and standardized evaluation of not just multi-species animal re-identification models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_09211 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | WildlifeReID-10k: Wildlife re-identification dataset with 10k individual animals Adam, Lukáš Čermák, Vojtěch Papafitsoros, Kostas Picek, Lukas Computer Vision and Pattern Recognition This paper introduces WildlifeReID-10k, a new large-scale re-identification benchmark with more than 10k animal identities of around 33 species across more than 140k images, re-sampled from 37 existing datasets. WildlifeReID-10k covers diverse animal species and poses significant challenges for SoTA methods, ensuring fair and robust evaluation through its time-aware and similarity-aware split protocol. The latter is designed to address the common issue of training-to-test data leakage caused by visually similar images appearing in both training and test sets. The WildlifeReID-10k dataset and benchmark are publicly available on Kaggle, along with strong baselines for both closed-set and open-set evaluation, enabling fair, transparent, and standardized evaluation of not just multi-species animal re-identification models. |
| title | WildlifeReID-10k: Wildlife re-identification dataset with 10k individual animals |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.09211 |