Capsule Networks with Intersection over Union Loss for Binary Image Segmentation

Floris Van Beers

2021

Abstract

With the development of Capsule Networks and their adaptation to the task of semantic segmentation, it has become important to determine which hyperparameters perform best for this new type of image processing model. One such parameter is the loss function, for which the baseline is usually cross entropy loss. In recent work on other models, Intersection over Union (IoU) loss has been shown to be effective. This work explores the application of IoU loss to segmentational capsule networks. For this purpose experiments are performed on two datasets: a medical dataset, LUNA16, and a dataset of faces (LFW). Results show marginal to significant improvements when using the IoU loss function as compared to the baseline Binary Cross-Entropy. From this can be concluded that the search for optimal loss functions is not finished and new loss functions may further improve performance of existing models.

Paper Citation

in Harvard Style

Van Beers F. (2021). Capsule Networks with Intersection over Union Loss for Binary Image Segmentation.In Proceedings of the 10th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-486-2, pages 71-78. DOI: 10.5220/0010301300710078

in Bibtex Style

@conference{icpram21,
author={Floris Van Beers},
title={Capsule Networks with Intersection over Union Loss for Binary Image Segmentation},
booktitle={Proceedings of the 10th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2021},
pages={71-78},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010301300710078},
isbn={978-989-758-486-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 10th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Capsule Networks with Intersection over Union Loss for Binary Image Segmentation
SN - 978-989-758-486-2
AU - Van Beers F.
PY - 2021
SP - 71
EP - 78
DO - 10.5220/0010301300710078