loading
Papers

Research.Publish.Connect.

Paper

Authors: Floris van Beers ; Arvid Lindström ; Emmanuel Okafor and Marco Wiering

Affiliation: Bernoulli Institute, Department of Artificial Intelligence, University of Groningen, Nijenborgh 9, Groningen and The Netherlands

ISBN: 978-989-758-351-3

Keyword(s): Deep Learning, Image Segmentation, Loss Function, Intersection over Union, Jaccard Index.

Abstract: In semantic segmentation tasks the Jaccard Index, or Intersection over Union (IoU), is often used as a measure of success. While this measure is more representative than per-pixel accuracy, state-of-the-art deep neural networks are still trained on accuracy by using Binary Cross Entropy loss. In this research, an alternative is used where deep neural networks are trained for a segmentation task of human faces by optimizing directly an approximation of IoU. When using this approximation, IoU becomes differentiable and can be used as a loss function. The comparison between IoU loss and Binary Cross Entropy loss is made by testing two deep neural network models on multiple datasets and data splits. The results show that training directly on IoU significantly increases performance for both models compared to training on conventional Binary Cross Entropy loss.

PDF ImageFull Text

Download
CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.85.245.126

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
van Beers, F.; Lindström, A.; Okafor, E. and Wiering, M. (2019). Deep Neural Networks with Intersection over Union Loss for Binary Image Segmentation.In Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-351-3, pages 438-445. DOI: 10.5220/0007347504380445

@conference{icpram19,
author={Floris van Beers. and Arvid Lindström. and Emmanuel Okafor. and Marco A. Wiering.},
title={Deep Neural Networks with Intersection over Union Loss for Binary Image Segmentation},
booktitle={Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2019},
pages={438-445},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007347504380445},
isbn={978-989-758-351-3},
}

TY - CONF

JO - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Deep Neural Networks with Intersection over Union Loss for Binary Image Segmentation
SN - 978-989-758-351-3
AU - van Beers, F.
AU - Lindström, A.
AU - Okafor, E.
AU - Wiering, M.
PY - 2019
SP - 438
EP - 445
DO - 10.5220/0007347504380445

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.