Authors:
Michał Koziarski
1
;
2
;
Bogusław Cyganek
1
;
2
and
Kazimierz Wiatr
1
;
2
Affiliations:
1
Academic Computer Center Cyfronet AGH, Ul. Nawojki 11, 30-950 Kraków, Poland
;
2
AGH University of Science and Technology, Al. Mickiewicza 30, 30-059 Kraków, Poland
Keyword(s):
Imbalanced Data Classification, Small-Scale Image Recognition, Convolutional Neural Networks, Feature Representation, MobileNet.
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 th
at despite their theoretical advantages, high-level features extracted from a pretrained neural network result in a worse performance than end-to-end image classification.
(More)