Enhancing Fine-Grained Cat Classification with Layer-Wise Transfer Learning

Rui Wang

2024

Abstract

In the field of machine learning, transfer learning is a frequently employed technique. It aims to improve a model's performance and learning efficiency by focusing on tasks through feature extraction or fine-tuning. Compared to training a model from scratch, transfer learning can more effectively leverage the knowledge from the source task to achieve superior outcomes on the target task. This paper presents two experiments. The first investigates the impact of unfreezing different numbers of convolutional layers on model performance. The second compares the outcomes of fine-tuning a portion of the convolutional layers after initially training the weights of the fully connected layers with those of unfreezing an equal number of convolutional and fully connected layers simultaneously. The experimental results suggest that adding more convolutional layers to the unfreezing sequence can typically help the model learn finer and more specific features, thereby enhancing performance metrics. It is crucial to find a balance between the model's generalization capability and its learning capacity, as excessive unfreezing can increase the risk of overfitting. Moreover, the more efficient approach of unfreezing the convolutional layers after first training the weights of the fully connected layers confirms the feasibility of transfer learning and the advantages of a step-by-step transfer learning strategy.

Paper Citation

in Harvard Style

Wang R. (2024). Enhancing Fine-Grained Cat Classification with Layer-Wise Transfer Learning. In Proceedings of the 1st International Conference on Modern Logistics and Supply Chain Management - Volume 1: MLSCM; ISBN 978-989-758-738-2, SciTePress, pages 167-171. DOI: 10.5220/0013246200004558

in Bibtex Style

@conference{mlscm24,
author={Rui Wang},
title={Enhancing Fine-Grained Cat Classification with Layer-Wise Transfer Learning},
booktitle={Proceedings of the 1st International Conference on Modern Logistics and Supply Chain Management - Volume 1: MLSCM},
year={2024},
pages={167-171},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013246200004558},
isbn={978-989-758-738-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Modern Logistics and Supply Chain Management - Volume 1: MLSCM
TI - Enhancing Fine-Grained Cat Classification with Layer-Wise Transfer Learning
SN - 978-989-758-738-2
AU - Wang R.
PY - 2024
SP - 167
EP - 171
DO - 10.5220/0013246200004558
PB - SciTePress