用低秩适配微调大模型，提升细胞学分类准确率
Exploring Foundation Models Fine-Tuning for Cytology Classification
- 采用低秩适配（LoRA）高效微调预训练模型骨干网络
- 在四个数据集上显著优于仅微调分类头，且少样本下表现更优
- 适合医疗图像少样本场景，尤其适用于资源有限的研究者
细胞学切片是癌症诊断与分期的关键工具，但其分析耗时且成本高。基础模型在辅助此类任务方面展现出巨大潜力。本文探索现有基础模型在细胞学分类中的应用，重点关注参数高效微调方法——低秩适配（LoRA），该方法特别适合少样本学习。我们在四个细胞学分类数据集上评估了五种基础模型。结果表明，使用LoRA微调预训练骨干网络相比仅微调分类头，显著提升了模型性能，在简单和复杂分类任务上均达到当前最优水平，且所需数据样本更少。
原文摘要 · Abstract (English)
Cytology slides are essential tools in diagnosing and staging cancer, but their analysis is time-consuming and costly. Foundation models have shown great potential to assist in these tasks. In this paper, we explore how existing foundation models can be applied to cytological classification. More particularly, we focus on low-rank adaptation, a parameter-efficient fine-tuning method suited to few-shot learning. We evaluated five foundation models across four cytological classification datasets. Our results demonstrate that fine-tuning the pre-trained backbones with LoRA significantly improves model performance compared to fine-tuning only the classifier head, achieving state-of-the-art results on both simple and complex classification tasks while requiring fewer data samples.
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。