用专家数据+大模型知识，让小模型高效识别野外蛾类。
Bridging Domain Gaps for Fine-Grained Moth Classification Through Expert-Informed Adaptation and Foundation Model Priors
- 用生物大模型知识蒸馏，指导小模型学习野外蛾类特征。
- 在101种丹麦蛾类上，小模型准确率接近大模型，计算量大幅降低。
- 适合需要低成本、高效率昆虫监测的科研与环保项目。
利用自动化相机系统采集鳞翅目（蛾类）图像进行标注，对理解昆虫衰退至关重要。然而，由于精心标注图像与嘈杂野外图像之间存在领域差异，准确的物种识别极具挑战。本文提出一种轻量级分类方法，结合少量专家标注的野外数据与高性能生物大模型BioCLIP2的知识蒸馏，将其迁移到ConvNeXt-tiny架构中。在丹麦AMI相机系统采集的101种蛾类数据集上的实验表明，BioCLIP2显著优于其他方法，而蒸馏后的轻量模型在保持相近准确率的同时，计算成本大幅降低。这些发现为高效昆虫监测系统的开发及细粒度分类中的领域差距弥合提供了实用指导。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。