arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.02776cs.CV
收藏

基于实例的深度迁移学习

Instance-based Deep Transfer Learning

Austin Peay State University(奥斯汀佩伊州立大学);Baidu Research(百度研究院);Montclair State University(蒙特克莱尔州立大学)

Tianyang Wang, Jun Huan, Michelle Zhu

摘要:

深度迁移学习最近获得了重大的研究兴趣。它利用从源域学习的预训练模型,并将这些模型用于目标域中的任务。基于模型的深度迁移学习可能是最常用的方法。然而,很少有研究工作致力于通过关注数据的影响来增强深度迁移学习。在本文中,我们提出了一种基于实例的方法来改进目标领域中的深度迁移学习。具体来说,我们从源域中选择一个预先训练好的模型,并应用这个模型来估计训练样本在目标域中的影响。然后,我们通过删除会降低预训练模型性能的训练样本来优化目标域的训练数据。我们稍后或者用目标域中的优化训练数据微调预训练模型,或者构建部分基于预训练模型初始化的新模型,并用目标域中的优化训练数据微调它。使用这种方法,迁移学习可以帮助深度学习模型捕获更多有用的特征。大量的实验证明了我们的方法在提高一些常见计算机视觉任务(如图像分类)的深度学习模型质量方面的有效性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑