Adaptive multi-source domain collaborative fine-tuning for transfer learning

Feng Le

doi:10.7717/peerj-cs.2107

Return

Adaptive multi-source domain collaborative fine-tuning for transfer learning

2024-06-21

DOI：10.7717/peerj-cs.2107

Original

Save

View PDF

Abstract

En 中文

Fine-tuning is an important technique in transfer learning that has achieved significant success in tasks that lack training data. However, as it is difficult to extract effective features for single -source domain fine-tuning when the data distribution difference between the source and the target domain is large, we propose a transfer learning framework based on multi -source domain called adaptive multi -source domain collaborative fine-tuning (AMCF) to address this issue. AMCF utilizes multiple source domain models for collaborative fine-tuning, thereby improving the feature extraction capability of model in the target task. Specifically, AMCF employs an adaptive multisource domain layer selection strategy to customize appropriate layer fine-tuning schemes for the target task among multiple source domain models, aiming to extract more efficient features. Furthermore, a novel multi -source domain collaborative loss function is designed to facilitate the precise extraction of target data features by each source domain model. Simultaneously, it works towards minimizing the output difference among various source domain models, thereby enhancing the adaptability of the source domain model to the target data. In order to validate the effectiveness of AMCF, it is applied to seven public visual classification datasets commonly used in transfer learning, and compared with the most widely used single -source domain fine-tuning methods. Experimental results demonstrate that, in comparison with the existing fine-tuning methods, our method not only enhances the accuracy of feature extraction in the model but also provides precise layer fine-tuning schemes for the target task, thereby significantly improving the fine-tuning performance.

Keywords:

Transfer learning

Fine-tuning

Multi-source domain collaborative fine-tuning

Fine-tuning layer selection

Feature extraction

Target task

Source domain models

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.