Improving optimization of convolutional neural networks through parameter fine-tuning

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.