WildlifeReID-10k: Wildlife Re-Identification Dataset with 10k Individual Animals
Abstract
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.
Cite
Text
Adam et al. "WildlifeReID-10k: Wildlife Re-Identification Dataset with 10k Individual Animals." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2025.Markdown
[Adam et al. "WildlifeReID-10k: Wildlife Re-Identification Dataset with 10k Individual Animals." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2025.](https://mlanthology.org/cvprw/2025/adam2025cvprw-wildlifereid10k/)BibTeX
@inproceedings{adam2025cvprw-wildlifereid10k,
title = {{WildlifeReID-10k: Wildlife Re-Identification Dataset with 10k Individual Animals}},
author = {Adam, Lukás and Cermák, Vojtech and Papafitsoros, Kostas and Picek, Lukás},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2025},
pages = {2099-2109},
url = {https://mlanthology.org/cvprw/2025/adam2025cvprw-wildlifereid10k/}
}