A case study on transfer learning in convolutional neural networks
Cahit Deniz Gürkaynak, Nafiz Arıca · 2018
In this work, a case study is performed on transfer learning approach in convolutional neural networks. Transfer learning parameters are examined on AlexNet, VGGNet and ResNet architectures for marine vessel classification task on MARVEL dataset. The results confirmed that transferring the parameter values of the first layers and fine-tuning the other layers, whose weights are initialized from pre-trained weights, performs better than training network from scratch. It's also observed that preprocessing and regularization improves overall scores significantly.