Bio-inspired fine-tuning for selective transfer learning in image classification
arXiv:2601.11235 · doi:10.1109/ACCESS.2025.3587524
Abstract
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.
References in corpus (9)
- A Survey on Deep Learning in Medical Image Analysis
- Deep learning in agriculture: A survey
- Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?
- Towards Better Exploiting Convolutional Neural Networks for Remote Sensing Scene Classification
- Skin Lesion Analysis toward Melanoma Detection: A Challenge at the International Symposium on Biomedical Imaging (ISBI) 2016, hosted by the International Skin Imaging Collaboration (ISIC)
- Transfer Learning with Dynamic Distribution Adaptation
- Comparison of fine-tuning strategies for transfer learning in medical image classification
- Targeted transfer learning to improve performance in small medical physics datasets
- Task segmentation based on transition state clustering for surgical robot assistance