Bio-inspired fine-tuning for selective transfer learning in image classification
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Image ClassificationTransfer LearningSimilar Papers 제목 키워드 기반
Transfer learning optimization based on evolutionary selective fine tuning
Deep learning has shown substantial progress in image analysis. However, the computational demands of large, fully trained models remain a consideration. Transfer learning offers a strategy for adapting pre-trained model…
Image ClassificationTransfer LearningAdaFilter: Adaptive Filter Fine-tuning for Deep Transfer Learning
There is an increasing number of pre-trained deep neural network models. However, it is still unclear how to effectively use these models for a new task. Transfer learning, which aims to transfer knowledge from source ta…
General Classificationimage-classificationImage ClassificationTransfer LearningSelectiveFinetuning: Enhancing Transfer Learning in Sleep Staging through Selective Domain Alignment
In practical sleep stage classification, a key challenge is the variability of EEG data across different subjects and environments. Differences in physiology, age, health status, and recording conditions can lead to doma…
EEGSleep StagingTransfer LearningZero-Shot Adaptation of Parameter-Efficient Fine-Tuning in Diffusion Models
We introduce ProLoRA, enabling zero-shot adaptation of parameter-efficient fine-tuning in text-to-image diffusion models. ProLoRA transfers pre-trained low-rank adjustments (e.g., LoRA) from a source to a target model wi…
parameter-efficient fine-tuningTransfer LearningImproving Image Classification Robustness through Selective CNN-Filters Fine-Tuning
Image quality plays a big role in CNN-based image classification performance. Fine-tuning the network with distorted samples may be too costly for large networks. To solve this issue, we propose a transfer learning appro…
ClassificationGeneral Classificationimage-classificationImage Classification+1