AdaFilter: Adaptive Filter Fine-Tuning for Deep Transfer Learning


  • Yunhui Guo University of California, San Diego
  • Yandong Li University of Central Florida
  • Liqiang Wang University of Central Florida
  • Tajana Rosing University of California, San Diego



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 tasks to a target task, is an effective solution to this problem. Fine-tuning is a popular transfer learning technique for deep neural networks where a few rounds of training are applied to the parameters of a pre-trained model to adapt them to a new task. Despite its popularity, in this paper we show that fine-tuning suffers from several drawbacks. We propose an adaptive fine-tuning approach, called AdaFilter, which selects only a part of the convolutional filters in the pre-trained model to optimize on a per-example basis. We use a recurrent gated network to selectively fine-tune convolutional filters based on the activations of the previous layer. We experiment with 7 public image classification datasets and the results show that AdaFilter can reduce the average classification error of the standard fine-tuning by 2.54%.




How to Cite

Guo, Y., Li, Y., Wang, L., & Rosing, T. (2020). AdaFilter: Adaptive Filter Fine-Tuning for Deep Transfer Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 34(04), 4060-4066.



AAAI Technical Track: Machine Learning