A Comprehensive Study on Torchvision Pre-trained Models for Fine-grained Inter-species Classification

TL;DR

This paper evaluates various Torchvision pre-trained models for fine-grained inter-species classification, comparing their effectiveness across multiple datasets and assessing the impact of SpinalNet layers.

Contribution

It provides a comprehensive comparison of Torchvision pre-trained models on diverse fine-grained datasets and explores the benefits of SpinalNet layers for improved accuracy.

Findings

SpinalNet layers generally improve model performance.

Model effectiveness varies across datasets with different complexities.

Guidelines for selecting suitable transfer learning models are proposed.

Abstract

This study aims to explore different pre-trained models offered in the Torchvision package which is available in the PyTorch library. And investigate their effectiveness on fine-grained images classification. Transfer Learning is an effective method of achieving extremely good performance with insufficient training data. In many real-world situations, people cannot collect sufficient data required to train a deep neural network model efficiently. Transfer Learning models are pre-trained on a large data set, and can bring a good performance on smaller datasets with significantly lower training time. Torchvision package offers us many models to apply the Transfer Learning on smaller datasets. Therefore, researchers may need a guideline for the selection of a good model. We investigate Torchvision pre-trained models on four different data sets: 10 Monkey Species, 225 Bird Species, Fruits 360, and Oxford 102 Flowers. These data sets have images of different resolutions, class numbers, and different achievable accuracies. We also apply their usual fully-connected layer and the Spinal fully-connected layer to investigate the effectiveness of SpinalNet. The Spinal fully-connected layer brings better performance in most situations. We apply the same augmentation for different models for the same data set for a fair comparison. This paper may help future Computer Vision researchers in choosing a proper Transfer Learning model.