A Transfer Learning Evaluation of Deep Neural Networks for Image Classification

TL;DR

This paper evaluates the effectiveness of transfer learning using eleven pre-trained image models on five datasets, focusing on model selection, performance metrics, and training efficiency.

Contribution

It provides a systematic comparison of pre-trained models for image classification, refining output layers and parameters to meet target domain needs.

Findings

Pre-trained models vary significantly in accuracy and efficiency across datasets.

Refined output layers improve model performance in target domains.

Evaluation metrics include accuracy, accuracy density, training time, and model size.

Abstract

Transfer learning is a machine learning technique that uses previously acquired knowledge from a source domain to enhance learning in a target domain by reusing learned weights. This technique is ubiquitous because of its great advantages in achieving high performance while saving training time, memory, and effort in network design. In this paper, we investigate how to select the best pre-trained model that meets the target domain requirements for image classification tasks. In our study, we refined the output layers and general network parameters to apply the knowledge of eleven image processing models, pre-trained on ImageNet, to five different target domain datasets. We measured the accuracy, accuracy density, training time, and model size to evaluate the pre-trained models both in training sessions in one episode and with ten episodes.