loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Robby Neven and Toon Goedemé

Affiliation: PSI-EAVISE, KU Leuven, Jan Pieter De Nayerlaan, Sint-Katelijne-Waver, Belgium

Keyword(s): Deep Learning, Machine Learning, Computer Vision, Active Learning.

Abstract: Recently, deep learning approaches excel in important computer vision tasks like classification and segmentation. The downside, however, is that they are very data hungry, which is very costly. One way to address this issue is by using active learning: only label and train on diverse and informative data points, not wasting any effort on redundant data. While recent active learning approaches have difficulty combining diversity and informativeness, we propose a sampling technique which efficiently combines these two metrics into a single algorithm. This is achieved by adapting a Determinantal Point Process to also consider model uncertainty. We first show competitive results on the academic classification datasets CIFAR10 and CalTech101, and the CityScapes segmentation task. To further increase the performance of our sampler on segmentation tasks, we extend our method to a patch-based active learning approach, improving the performance by not wasting labelling effort on redundant ima ge regions. Lastly, we demonstrate our method on a more challenging realworld industrial use-case, segmenting defects in steel sheet material, which greatly benefits from an active learning approach due to a vast amount of redundant data, and show promising results. (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 3.148.117.237

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:
Neven, R. and Goedemé, T. (2023). Uncertainty-Aware DPP Sampling for Active Learning. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP; ISBN 978-989-758-634-7; ISSN 2184-4321, SciTePress, pages 95-104. DOI: 10.5220/0011680100003417

@conference{visapp23,
author={Robby Neven. and Toon Goedemé.},
title={Uncertainty-Aware DPP Sampling for Active Learning},
booktitle={Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP},
year={2023},
pages={95-104},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011680100003417},
isbn={978-989-758-634-7},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP
TI - Uncertainty-Aware DPP Sampling for Active Learning
SN - 978-989-758-634-7
IS - 2184-4321
AU - Neven, R.
AU - Goedemé, T.
PY - 2023
SP - 95
EP - 104
DO - 10.5220/0011680100003417
PB - SciTePress