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

TL;DR

This paper introduces an unsupervised, part-based feature alignment method to improve animal re-identification by removing background biases and handling pose variations, achieving superior results on multiple datasets.

Contribution

It presents a novel unsupervised approach for feature alignment and background removal in animal Re-ID, addressing dataset bias and pose variation challenges.

Findings

Achieved superior accuracy on ATRW, YakReID-103, and ELPephants datasets.

Effectively removes background bias during training and evaluation.

Handles pose and lighting variations without relying on pose annotations.

Abstract

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.