Instance-based Deep Transfer Learning

TL;DR

This paper introduces an instance-based method to enhance deep transfer learning by optimizing target domain training data, leading to improved model performance in computer vision tasks.

Contribution

It proposes a novel instance-based approach that refines training data for transfer learning, which has been less explored compared to model-based methods.

Findings

Improved accuracy in image classification tasks.

Effective data optimization enhances transfer learning performance.

Method outperforms traditional transfer learning approaches.

Abstract

Deep transfer learning recently has acquired significant research interest. It makes use of pre-trained models that are learned from a source domain, and utilizes these models for the tasks in a target domain. Model-based deep transfer learning is probably the most frequently used method. However, very little research work has been devoted to enhancing deep transfer learning by focusing on the influence of data. In this paper, we propose an instance-based approach to improve deep transfer learning in a target domain. Specifically, we choose a pre-trained model from a source domain and apply this model to estimate the influence of training samples in a target domain. Then we optimize the training data of the target domain by removing the training samples that will lower the performance of the pre-trained model. We later either fine-tune the pre-trained model with the optimized training data in the target domain, or build a new model which is initialized partially based on the pre-trained model, and fine-tune it with the optimized training data in the target domain. Using this approach, transfer learning can help deep learning models to capture more useful features. Extensive experiments demonstrate the effectiveness of our approach on boosting the quality of deep learning models for some common computer vision tasks, such as image classification.