How effective is Transfer Learning method for image classification

Abstract

This paper deals with retraining neural network-based image classification model, using so-called Transfer Learning approach. This method allows for creating a new image classifier, reusing pre-trained weights from a publicly available model. Our study gives some insight on accuracy of retrained models and provides guidelines concerning required number of training examples. Presented results may be useful for computer vision practitioners, who would like to adapt results of state-of-the-art research on neural networks for their own customized image recognition models.