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

arXiv: https://arxiv.org/abs/2508.20089 · HTML: https://mlsanity.com/paper/2508.20089/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 36 references that are in the map.
- First posted on arXiv 27 Aug 2025.

## Builds on (most cited first, 13 of 13)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Deep Visual Domain Adaptation: A Survey](https://mlsanity.com/paper/1802.03601/) (2018)
- [BioCLIP: A Vision Foundation Model for the Tree of Life](https://mlsanity.com/paper/2311.18803/) (2023)
- [BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive Learning](https://mlsanity.com/paper/2505.23883/) (2025)
- [Data-Free Knowledge Transfer: A Survey](https://mlsanity.com/paper/2112.15278/) (2021)
- [Insect-Foundation: A Foundation Model and Large-scale 1M Dataset for Visual Insect Understanding](https://mlsanity.com/paper/2311.15206/) (2023)
- [BioTrove: A Large Curated Image Dataset Enabling AI for Biodiversity](https://mlsanity.com/paper/2406.17720/) (2024)
- [CLIBD: Bridging Vision and Genomics for Biodiversity Monitoring at Scale](https://mlsanity.com/paper/2405.17537/) (2024)
- [Insect Identification in the Wild: The AMI Dataset](https://mlsanity.com/paper/2406.12452/) (2024)
- [Towards Zero-Shot Camera Trap Image Categorization](https://mlsanity.com/paper/2410.12769/) (2024)
- [Towards Scalable Insect Monitoring: Ultra-Lightweight CNNs as On-Device Triggers for Insect Camera Traps](https://mlsanity.com/paper/2411.14467/) (2024)
- [Performance of computer vision algorithms for fine-grained classification using crowdsourced insect images](https://mlsanity.com/paper/2404.03474/) (2024)

## Abstract (arXiv)

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.