用生物演化思路优化模型微调，提升小数据图像分类准确率
Bio-inspired fine-tuning for selective transfer learning in image classification
- 模仿生物进化选择最优层冻结与学习率配置
- 在9个数据集上优于AutoRGN和LoRA等方法
- 适配多种网络结构和医学图像等特殊场景
深度学习在图像分析中取得显著进展，但通常依赖大规模标注数据。迁移学习通过使用预训练模型，在少量标注数据下解决新任务。然而源域与目标域差异常阻碍有效迁移。本文提出BioTune，一种基于进化优化的自适应微调技术，通过最优选择冻结层并调整未冻结层的学习率来提升迁移效果。在涵盖自然图像与医学影像等领域的9个图像分类数据集上，BioTune在准确率和效率上均优于当前最优微调方法（如AutoRGN和LoRA），展现出对不同数据特征和分布变化的强适应性。此外，其在四种不同CNN架构上均保持领先性能，验证了高灵活性。消融实验揭示了关键组件对整体表现的影响。代码已开源：https://github.com/davilac/BioTune。
原文摘要 · Abstract (English)
Deep learning has significantly advanced image analysis across diverse domains but often depends on large, annotated datasets for success. Transfer learning addresses this challenge by utilizing pre-trained models to tackle new tasks with limited labeled data. However, discrepancies between source and target domains can hinder effective transfer learning. We introduce BioTune, a novel adaptive fine-tuning technique utilizing evolutionary optimization. BioTune enhances transfer learning by optimally choosing which layers to freeze and adjusting learning rates for unfrozen layers. Through extensive evaluation on nine image classification datasets, spanning natural and specialized domains such as medical imaging, BioTune demonstrates superior accuracy and efficiency over state-of-the-art fine-tuning methods, including AutoRGN and LoRA, highlighting its adaptability to various data characteristics and distribution changes. Additionally, BioTune consistently achieves top performance across four different CNN architectures, underscoring its flexibility. Ablation studies provide valuable insights into the impact of BioTune's key components on overall performance. The source code is available at https://github.com/davilac/BioTune.
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。