Addressing the Elephant in the Room: Robust Animal Re-Identification with Unsupervised Part-Based Feature Alignment

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yu, Yingxue, Vidit, Vidit, Davydov, Andrey, Engilberge, Martin, Fua, Pascal
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929354116694016
author Yu, Yingxue
Vidit, Vidit
Davydov, Andrey
Engilberge, Martin
Fua, Pascal
author_facet Yu, Yingxue
Vidit, Vidit
Davydov, Andrey
Engilberge, Martin
Fua, Pascal
contents Animal Re-ID is crucial for wildlife conservation, yet it faces unique challenges compared to person Re-ID. First, the scarcity and lack of diversity in datasets lead to background-biased models. Second, animal Re-ID depends on subtle, species-specific cues, further complicated by variations in pose, background, and lighting. This study addresses background biases by proposing a method to systematically remove backgrounds in both training and evaluation phases. And unlike prior works that depend on pose annotations, our approach utilizes an unsupervised technique for feature alignment across body parts and pose variations, enhancing practicality. Our method achieves superior results on three key animal Re-ID datasets: ATRW, YakReID-103, and ELPephants.
format Preprint
id arxiv_https___arxiv_org_abs_2405_13781
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Addressing the Elephant in the Room: Robust Animal Re-Identification with Unsupervised Part-Based Feature Alignment
Yu, Yingxue
Vidit, Vidit
Davydov, Andrey
Engilberge, Martin
Fua, Pascal
Computer Vision and Pattern Recognition
Animal Re-ID is crucial for wildlife conservation, yet it faces unique challenges compared to person Re-ID. First, the scarcity and lack of diversity in datasets lead to background-biased models. Second, animal Re-ID depends on subtle, species-specific cues, further complicated by variations in pose, background, and lighting. This study addresses background biases by proposing a method to systematically remove backgrounds in both training and evaluation phases. And unlike prior works that depend on pose annotations, our approach utilizes an unsupervised technique for feature alignment across body parts and pose variations, enhancing practicality. Our method achieves superior results on three key animal Re-ID datasets: ATRW, YakReID-103, and ELPephants.
title Addressing the Elephant in the Room: Robust Animal Re-Identification with Unsupervised Part-Based Feature Alignment
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.13781