The Choice of Feature Representation in Small-Scale MobileNet-Based Imbalanced Image Recognition

Michał Koziarski, Bogusław Cyganek, Kazimierz Wiatr

Abstract

Data imbalance remains one of the most wide-spread challenges in the contemporary machine learning. Presence of imbalanced data can affect the learning possibility of most traditional classification algorithms. One of the the strategies for handling data imbalance are data-level algorithms that modify the original data distribution. However, despite the amount of existing methods, most are ill-suited for handling image data. One of the possible solutions to this problem is using alternative feature representations, such as high-level features extracted from convolutional layers of a neural network. In this paper we experimentally evaluate the possibility of using both the high-level features, as well as the original image representation, on several popular benchmark datasets with artificially introduced data imbalance. We examine the impact of different data-level algorithms on both strategies, and base the classification on MobileNet neural architecture. Achieved results indicate that despite their theoretical advantages, high-level features extracted from a pretrained neural network result in a worse performance than end-to-end image classification.

Download


Paper Citation


in Harvard Style

Koziarski M., Cyganek B. and Wiatr K. (2020). The Choice of Feature Representation in Small-Scale MobileNet-Based Imbalanced Image Recognition.In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, ISBN 978-989-758-402-2, pages 633-638. DOI: 10.5220/0009357206330638


in Bibtex Style

@conference{visapp20,
author={Michał Koziarski and Bogusław Cyganek and Kazimierz Wiatr},
title={The Choice of Feature Representation in Small-Scale MobileNet-Based Imbalanced Image Recognition},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP,},
year={2020},
pages={633-638},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009357206330638},
isbn={978-989-758-402-2},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP,
TI - The Choice of Feature Representation in Small-Scale MobileNet-Based Imbalanced Image Recognition
SN - 978-989-758-402-2
AU - Koziarski M.
AU - Cyganek B.
AU - Wiatr K.
PY - 2020
SP - 633
EP - 638
DO - 10.5220/0009357206330638