Instance-Based Deep Transfer Learning
Tianyang Wang, Jun Huan, Michelle Zhu · IEEE Winter Conference on Applications of Computer Vision · 2019
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.
Cited by 48 works. doi:10.1109/wacv.2019.00045 Open-access PDF
Authors
References
- Deep Residual Learning for Image Recognition
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- ImageNet: A large-scale hierarchical image database
- AutoResearch Lite: a reproducible paper-inspired experiment runner (Adam mechanism reproduction and convergence-speed comparison)
- Learning Multiple Layers of Features from Tiny Images
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
- Densely Connected Convolutional Networks
- Rectified Linear Units Improve Restricted Boltzmann Machines
- Understanding the difficulty of training deep feedforward neural networks
- A Survey on Transfer Learning