Applying Center Loss to Multidimensional Feature Space in Deep Neural Networks for Open-set Recognition

Daiju Kanaoka, Yuichiro Tanaka, Hakaru Tamukoh, Hakaru Tamukoh

2022

Abstract

With the advent of deep learning, significant improvements in image recognition performance have been achieved. In image recognition, it is generally assumed that all the test data are composed of known classes. This approach is termed as closed-set recognition. In closed-set recognition, when an untrained, unknown class is input, it is recognized as one of the trained classes. The method whereby an unknown image is recognized as unknown when it is input is termed as open-set recognition. Although several open-set recognition methods have been proposed, none of these previous methods excel in terms of all three evaluation items: learning cost, recognition performance, and scalability from closed-set recognition models. To address this, we propose an open-set recognition method using the distance between features in the multidimensional feature space of neural networks. By applying center loss to the feature space, we aim to maintain the classification accuracy of closed-set recognition and improve the unknown detection performance. In our experiments, we achieved state-of-the-art performance on the MNIST, SVHN, and CIFAR-10 datasets. In addition, the proposed approach shows excellent performance in terms of the three evaluation items.

Download


Paper Citation


in Harvard Style

Kanaoka D., Tanaka Y. and Tamukoh H. (2022). Applying Center Loss to Multidimensional Feature Space in Deep Neural Networks for Open-set Recognition. In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, ISBN 978-989-758-555-5, pages 359-365. DOI: 10.5220/0010816600003124


in Bibtex Style

@conference{visapp22,
author={Daiju Kanaoka and Yuichiro Tanaka and Hakaru Tamukoh},
title={Applying Center Loss to Multidimensional Feature Space in Deep Neural Networks for Open-set Recognition},
booktitle={Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP,},
year={2022},
pages={359-365},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010816600003124},
isbn={978-989-758-555-5},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP,
TI - Applying Center Loss to Multidimensional Feature Space in Deep Neural Networks for Open-set Recognition
SN - 978-989-758-555-5
AU - Kanaoka D.
AU - Tanaka Y.
AU - Tamukoh H.
PY - 2022
SP - 359
EP - 365
DO - 10.5220/0010816600003124