loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Matthias Körschens 1 ; Paul Bodesheim 1 and Joachim Denzler 2 ; 1

Affiliations: 1 Friedrich Schiller University Jena, Fürstengraben 1, Jena, Germany ; 2 DLR Institute of Data Science, Mälzerstraße 3-5, Jena, Germany

Keyword(s): Computer Vision, Pooling, Weakly Supervised Object Localization, Weakly Supervised Segmentation.

Abstract: Weakly supervised object localization (WSOL) enables the detection and segmentation of objects in applications where localization annotations are hard or too expensive to obtain. Nowadays, most relevant WSOL approaches are based on class activation mapping (CAM), where a classification network utilizing global average pooling is trained for object classification. The classification layer that follows the pooling layer is then repurposed to generate segmentations using the unpooled features. The resulting localizations are usually imprecise and primarily focused around the most discriminative areas of the object, making a correct indication of the object location difficult. We argue that this problem is inherent in training with global average pooling due to its averaging operation. Therefore, we investigate two alternative pooling strategies: global max pooling and global log-sum-exp pooling. Furthermore, to increase the crispness and resolution of localization maps, we also investig ate the application of Feature Pyramid Networks, which are commonplace in object detection. We confirm the usefulness of both alternative pooling methods as well as the Feature Pyramid Network on the CUB-200-2011 and OpenImages datasets. (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 18.97.14.87

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:
Körschens, M. ; Bodesheim, P. and Denzler, J. (2022). Beyond Global Average Pooling: Alternative Feature Aggregations for Weakly Supervised Localization. In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP; ISBN 978-989-758-555-5; ISSN 2184-4321, SciTePress, pages 180-191. DOI: 10.5220/0010871700003124

@conference{visapp22,
author={Matthias Körschens and Paul Bodesheim and Joachim Denzler},
title={Beyond Global Average Pooling: Alternative Feature Aggregations for Weakly Supervised Localization},
booktitle={Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP},
year={2022},
pages={180-191},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010871700003124},
isbn={978-989-758-555-5},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP
TI - Beyond Global Average Pooling: Alternative Feature Aggregations for Weakly Supervised Localization
SN - 978-989-758-555-5
IS - 2184-4321
AU - Körschens, M.
AU - Bodesheim, P.
AU - Denzler, J.
PY - 2022
SP - 180
EP - 191
DO - 10.5220/0010871700003124
PB - SciTePress