TransJury: Towards Explainable Transfer Learning through Selection of Layers from Deep Neural Networks
Md Adnan Arefeen, Sumaiya Tabassum Nimi, Md Yusuf Sarwar Uddin, Yugyung Lee · 2021 IEEE International Conference on Big Data (Big Data) · 2021
Training a neural network model from scratch is a computationally intensive operation. To alleviate this issue, researchers often employ "transfer learning" that transfers knowledge from a source data distribution to a target data distribution, instead of training the whole model from scratch. Typically, the last few layers of a pretrained convolutional neural network (CNN) are chosen for many transfer learning tasks where the outputs of those selected layers are combined to construct a feature space based on which a task-specific classification n etwork i s t rained o r fi ne-tuned. Th is arbitrary way of selecting layers, however, often fails to achieve the desired accuracy for the target task. What we need is an intelligent way of selecting layers from a pretrained model for a given task so that the additional overhead of successive training remains low. To this end, we propose a novel method, called TransJury, to find t he m ost s ignificant la yers from a pretrained mo del for transfer learning along with preserving the knowledge for the source domain. Through extensive experimentation on several target domain datasets, we show the supremacy of our approach in terms of lower training overhead and improved accuracy. By deploying MobileNet-v2, a lightweight CNN model pretrained on the ImageNet dataset on an edge device, we also discuss the future direction of this research.