# Bridging Domain Gaps for Fine-Grained Moth Classification Through Expert-Informed Adaptation and Foundation Model Priors

## TL;DR

This paper introduces a lightweight moth classification method that combines expert-labelled field data with foundation model knowledge distillation, effectively bridging domain gaps and enabling efficient insect monitoring.

## Contribution

It presents a novel approach integrating foundation model priors with expert data to improve fine-grained moth classification across domain shifts.

## Key findings

- BioCLIP2 outperforms other models in species identification.
- The distilled model achieves high accuracy with lower computational cost.
- Practical guidelines for insect monitoring system development.

## Abstract

Labelling images of Lepidoptera (moths) from automated camera systems is vital for understanding insect declines. However, accurate species identification is challenging due to domain shifts between curated images and noisy field imagery. We propose a lightweight classification approach, combining limited expert-labelled field data with knowledge distillation from the high-performance BioCLIP2 foundation model into a ConvNeXt-tiny architecture. Experiments on 101 Danish moth species from AMI camera systems demonstrate that BioCLIP2 substantially outperforms other methods and that our distilled lightweight model achieves comparable accuracy with significantly reduced computational cost. These insights offer practical guidelines for the development of efficient insect monitoring systems and bridging domain gaps for fine-grained classification.