loading
Papers Papers/2020

Research.Publish.Connect.

Paper

Authors: Pascal Colling 1 ; 2 ; Lutz Roese-Koerner 1 ; Hanno Gottschalk 2 and Matthias Rottmann 2

Affiliations: 1 Aptiv, Wuppertal, Germany ; 2 University of Wuppertal, School of Mathematics and Natural Sciences, IMACM & IZMD, Germany

Keyword(s): Active Learning, Semantic Segmentation, Priority Maps via Meta Regression, Cost Estimation.

Abstract: We present a novel region based active learning method for semantic image segmentation, called MetaBox+. For acquisition, we train a meta regression model to estimate the segment-wise Intersection over Union (IoU) of each predicted segment of unlabeled images. This can be understood as an estimation of segment-wise prediction quality. Queried regions are supposed to minimize to competing targets, i.e., low predicted IoU values / segmentation quality and low estimated annotation costs. For estimating the latter we propose a simple but practical method for annotation cost estimation. We compare our method to entropy based methods, where we consider the entropy as uncertainty of the prediction. The comparison and analysis of the results provide insights into annotation costs as well as robustness and variance of the methods. Numerical experiments conducted with two different networks on the Cityscapes dataset clearly demonstrate a reduction of annotation effort compared to random acquisition. Noteworthily, we achieve 95% of the mean Intersection over Union (mIoU), using MetaBox+ compared to when training with the full dataset, with only 10.47% / 32.01% annotation effort for the two networks, respectively (More)

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 3.235.176.80

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:
Colling, P.; Roese-Koerner, L.; Gottschalk, H. and Rottmann, M. (2021). MetaBox+: A New Region based Active Learning Method for Semantic Segmentation using Priority Maps. In Proceedings of the 10th International Conference on Pattern Recognition Applications and Methods - ICPRAM, ISBN 978-989-758-486-2; ISSN 2184-4313, pages 51-62. DOI: 10.5220/0010227500510062

@conference{icpram21,
author={Pascal Colling. and Lutz Roese{-}Koerner. and Hanno Gottschalk. and Matthias Rottmann.},
title={MetaBox+: A New Region based Active Learning Method for Semantic Segmentation using Priority Maps},
booktitle={Proceedings of the 10th International Conference on Pattern Recognition Applications and Methods - ICPRAM,},
year={2021},
pages={51-62},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010227500510062},
isbn={978-989-758-486-2},
issn={2184-4313},
}

TY - CONF

JO - Proceedings of the 10th International Conference on Pattern Recognition Applications and Methods - ICPRAM,
TI - MetaBox+: A New Region based Active Learning Method for Semantic Segmentation using Priority Maps
SN - 978-989-758-486-2
IS - 2184-4313
AU - Colling, P.
AU - Roese-Koerner, L.
AU - Gottschalk, H.
AU - Rottmann, M.
PY - 2021
SP - 51
EP - 62
DO - 10.5220/0010227500510062