Logo image
Enhanced transfer learning with ImageNet trained classification layer
Journal article   Peer reviewed

Enhanced transfer learning with ImageNet trained classification layer

T. Shermin, S.W. Teng, M. Murshed, G. Lu, F. Sohel and M. Paul
Image and Video Technology, Vol.11854, pp.142-155
2019
url
Link to Published Version *Subscription may be requiredView

Abstract

Parameter fine tuning is a transfer learning approach whereby learned parameters from pre-trained source network are transferred to the target network followed by fine-tuning. Prior research has shown that this approach is capable of improving task performance. However, the impact of the ImageNet pre-trained classification layer in parameter fine-tuning is mostly unexplored in the literature. In this paper, we propose a fine-tuning approach with the pre-trained classification layer. We employ layer-wise fine-tuning to determine which layers should be frozen for optimal performance. Our empirical analysis demonstrates that the proposed fine-tuning performs better than traditional fine-tuning. This finding indicates that the pre-trained classification layer holds less category-specific or more global information than believed earlier. Thus, we hypothesize that the presence of this layer is crucial for growing network depth to adapt better to a new task. Our study manifests that careful normalization and scaling are essential for creating harmony between the pre-trained and new layers for target domain adaptation. We evaluate the proposed depth augmented networks for fine-tuning on several challenging benchmark datasets and show that they can achieve higher classification accuracy than contemporary transfer learning approaches.

Details

UN Sustainable Development Goals (SDGs)

This output has contributed to the advancement of the following goals:

#3 Good Health and Well-Being

Source: InCites

Metrics

Logo image