Feature-Aware Noise Contrastive Learning for Unsupervised Red Panda Re-Identification

TL;DR

This paper introduces FANCL, an unsupervised contrastive learning method with feature-aware noise addition, to improve red panda re-identification by extracting deeper features without labeled data.

Contribution

The paper presents a novel unsupervised learning approach with feature-aware noise contrastive learning specifically designed for animal re-ID tasks.

Findings

FANCL outperforms existing unsupervised methods on red panda re-ID.

FANCL achieves comparable performance to supervised methods.

The method effectively extracts deep features from noised images.

Abstract

To facilitate the re-identification (re-ID) of individual animals, existing methods primarily focus on maximizing feature similarity within the same individual and enhancing distinctiveness between different individuals. However, most of them still rely on supervised learning and require substantial labeled data, which is challenging to obtain. To avoid this issue, we propose Feature-Aware Noise Contrastive Learning (FANCL) method to explore an unsupervised learning solution, which is then validated on the task of red panda re-ID. FANCL designs a Feature-Aware Noise Addition module to produce noised images that conceal critical features, and employs two contrastive learning modules to calculate the losses. Firstly, a feature consistency module is designed to bridge the gap between the original and noised features. Secondly, the neural networks are trained through a cluster contrastive learning module. Through these more challenging learning tasks, FANCL can adaptively extract deeper representations of red pandas. The experimental results on a set of red panda images collected in both indoor and outdoor environments prove that FANCL outperforms several related state-of-the-art unsupervised methods, achieving high performance comparable to supervised learning methods.