Siamese Networks for Cat Re-Identification: Exploring Neural Models for Cat Instance Recognition

TL;DR

This paper presents a deep learning approach using Siamese Networks with EfficientNetB0, MobileNet, and VGG16 to automate street cat re-identification, achieving high accuracy and aiding population management efforts.

Contribution

It introduces a novel application of Siamese Networks for cat re-identification with optimized configurations, demonstrating high accuracy on a limited dataset.

Findings

VGG16 with contrastive loss achieved 97% accuracy

The model attained an F1 score of 0.9344

Image augmentation improved model robustness

Abstract

Street cats in urban areas often rely on human intervention for survival, leading to challenges in population control and welfare management. In April 2023, Hello Inc., a Chinese urban mobility company, launched the Hello Street Cat initiative to address these issues. The project deployed over 21,000 smart feeding stations across 14 cities in China, integrating livestreaming cameras and treat dispensers activated through user donations. It also promotes the Trap-Neuter-Return (TNR) method, supported by a community-driven platform, HelloStreetCatWiki, where volunteers catalog and identify cats. However, manual identification is inefficient and unsustainable, creating a need for automated solutions. This study explores Deep Learning-based models for re-identifying street cats in the Hello Street Cat initiative. A dataset of 2,796 images of 69 cats was used to train Siamese Networks with EfficientNetB0, MobileNet and VGG16 as base models, evaluated under contrastive and triplet loss functions. VGG16 paired with contrastive loss emerged as the most effective configuration, achieving up to 97% accuracy and an F1 score of 0.9344 during testing. The approach leverages image augmentation and dataset refinement to overcome challenges posed by limited data and diverse visual variations. These findings underscore the potential of automated cat re-identification to streamline population monitoring and welfare efforts. By reducing reliance on manual processes, the method offers a scalable and reliable solution for communitydriven initiatives. Future research will focus on expanding datasets and developing real-time implementations to enhance practicality in large-scale deployments.