WildlifeReID-10k: Wildlife re-identification dataset with 10k individual animals

TL;DR

WildlifeReID-10k is a comprehensive large-scale dataset for animal re-identification, designed to facilitate fair evaluation of models across diverse species with robust protocols to prevent data leakage.

Contribution

It introduces a new extensive wildlife re-identification dataset with a novel split protocol to improve evaluation fairness and robustness.

Findings

Provides over 140k images of 10k+ animals across 37 species.

Includes strong baseline models for evaluation.

Ensures fair comparison through time-aware and similarity-aware splits.

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.