Exploring Clustering Capability of Inpainting Model Embeddings for Pattern-based Individual Identification

TL;DR

This study investigates how inpainting model embeddings can improve individual animal identification based on skin patterns, focusing on zebrafish, by enhancing feature extraction for better classification and clustering.

Contribution

It introduces a novel approach using inpainting as an auxiliary task to improve deep learning models' sensitivity to skin pattern features for animal identification.

Findings

Inpainting-based embeddings improve classification accuracy.

Enhanced clustering of individual skin patterns achieved.

GradCAM visualizations show better focus on skin patterns.

Abstract

In this paper, we explore deep learning techniques for individual identification of animals based on their skin patterns. Individual identification is crucial in biodiversity monitoring, since it enables analysis of decline or growth of populations, or intra-species interactions within populations. Models trained for the task of individual identification often do not focus on the skin pattern of animals, but on background details or body shape details. These characteristics are not individually specific, or can change drastically through time. We focus on techniques that will make machine learning models more responsive to skin pattern structure when extracting individual visual embeddings from images. For this, we explore image inpainting of task-specific masks as an auxiliary task to enhance ML-based individual identification from animal skin patterns. We propose a comparative analysis among four models as an encoder backbone for the individual identification task. We focus on the case study of zebrafish, which is a widely recognized biological model organism, and which exhibits individually identifying skin patterns. To evaluate encoder backbone performance, we present standard metrics for classification accuracy, embedding clustering metrics, and GradCAM visualizations.