In recent years, convolutional neural networks have achieved state-of-the-art performance in a number of computer vision problems such as image classification. Prior research has shown that a transfer learning technique known as parameter fine-tuning wherein a network is pre-trained on a different dataset can boost the performance of these networks. However, the topic of identifying the best source dataset and learning strategy for a given target domain is largely unexplored. Thus, this research presents and evaluates various transfer learning methods for fine-grained image classification as well as the effect on ensemble networks. The results clearly demonstrate the effectiveness of parameter fine-tuning over random initialization. We find that training should not be reduced after transferring weights, larger, more similar networks tend to be the best source task, and parameter fine-tuning can often outperform randomly initialized ensembles. The experimental framework and findings will help to train models with improved accuracy.
Neural Computing and Applications
Becherer, N., Pecarina, J. M., Nykl, S. L., & Hopkinson, K. M. (2019). Improving Optimization of Convolutional Neural Networks through Parameter Fine-tuning. Neural Computing and Applications, 31(8), 3469–3479. https://doi.org/10.1007/s00521-017-3285-0