PetFace: A Large-Scale Dataset and Benchmark for Animal Identification

TL;DR

PetFace introduces a large-scale, annotated animal face dataset and benchmarks, significantly advancing research in animal identification and verification, especially for unseen individuals and multiple species.

Contribution

The paper presents the PetFace dataset with extensive annotations and benchmarks, enabling new research in animal face recognition across diverse species and unseen individuals.

Findings

Models trained on PetFace outperform prior datasets.

The dataset supports verification of unseen animals.

Room for improvement in multi-family animal identification.

Abstract

Automated animal face identification plays a crucial role in the monitoring of behaviors, conducting of surveys, and finding of lost animals. Despite the advancements in human face identification, the lack of datasets and benchmarks in the animal domain has impeded progress. In this paper, we introduce the PetFace dataset, a comprehensive resource for animal face identification encompassing 257,484 unique individuals across 13 animal families and 319 breed categories, including both experimental and pet animals. This large-scale collection of individuals facilitates the investigation of unseen animal face verification, an area that has not been sufficiently explored in existing datasets due to the limited number of individuals. Moreover, PetFace also has fine-grained annotations such as sex, breed, color, and pattern. We provide multiple benchmarks including re-identification for seen individuals and verification for unseen individuals. The models trained on our dataset outperform those trained on prior datasets, even for detailed breed variations and unseen animal families. Our result also indicates that there is some room to improve the performance of integrated identification on multiple animal families. We hope the PetFace dataset will facilitate animal face identification and encourage the development of non-invasive animal automatic identification methods.