HierNet: Image Recognition with Hierarchical Convolutional Networks

Levente Tempfli, Csanád Sándor

2024

Abstract

Convolutional Neural Networks (CNNs) have proven to be an effective method for image recognition due to their ability to extract features and learn the internal representation of the input data. However, traditional CNNs disregard the hierarchy of the input data, which can lead to suboptimal performance. In this paper, we propose a novel method of organizing a CNN into a quasi-decision tree, where the edges represent the feature-extracting layers of a CNN and the nodes represent the classifiers. The structure of the decision tree corresponds to the hierarchical relationships between the label classes, meaning that the visually similar classes are located in the same subtree. We also introduce a simple semi-supervised method to determine these hierarchical relations to avoid having to manually construct such a hierarchy between a large number of classes. We evaluate our method on the CIFAR-100 dataset using ResNet as our base CNN model. Our results show that the proposed method outperforms this base CNN between 2.12-3.77% (depending on the version of the architecture), demonstrating the effectiveness of incorporating input hierarchy into CNNs. Code is available at https://github.com/levtempfli/HierNet.

Paper Citation

in Harvard Style

Tempfli L. and Sándor C. (2024). HierNet: Image Recognition with Hierarchical Convolutional Networks. In Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART; ISBN 978-989-758-680-4, SciTePress, pages 147-155. DOI: 10.5220/0012321100003636

in Bibtex Style

@conference{icaart24,
author={Levente Tempfli and Csanád Sándor},
title={HierNet: Image Recognition with Hierarchical Convolutional Networks},
booktitle={Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART},
year={2024},
pages={147-155},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012321100003636},
isbn={978-989-758-680-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART
TI - HierNet: Image Recognition with Hierarchical Convolutional Networks
SN - 978-989-758-680-4
AU - Tempfli L.
AU - Sándor C.
PY - 2024
SP - 147
EP - 155
DO - 10.5220/0012321100003636
PB - SciTePress