Weakly supervised food image segmentation using class activation maps

© 2017 IEEE. Food image segmentation plays a crucial role in image-based dietary assessment and management. Successful methods for object segmentation generally rely on a large amount of labeled data on the pixel level. However, such training data are not yet available for food images and expensive...

Full description

Bibliographic Details
Main Authors: Wang, Y., Zhu, F., Boushey, Carol, Delp, E.
Format: Conference Paper
Published: 2018
Online Access:http://hdl.handle.net/20.500.11937/67520
_version_ 1848761587200950272
author Wang, Y.
Zhu, F.
Boushey, Carol
Delp, E.
author_facet Wang, Y.
Zhu, F.
Boushey, Carol
Delp, E.
author_sort Wang, Y.
building Curtin Institutional Repository
collection Online Access
description © 2017 IEEE. Food image segmentation plays a crucial role in image-based dietary assessment and management. Successful methods for object segmentation generally rely on a large amount of labeled data on the pixel level. However, such training data are not yet available for food images and expensive to obtain. In this paper, we describe a weakly supervised convolutional neural network (CNN) which only requires image level annotation. We propose a graph based segmentation method which uses the class activation maps trained on food datasets as a top-down saliency model. We evaluate the proposed method for both classification and segmentation tasks. We achieve competitive classification accuracy compared to the previously reported results.
first_indexed 2025-11-14T10:34:02Z
format Conference Paper
id curtin-20.500.11937-67520
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T10:34:02Z
publishDate 2018
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-675202018-05-18T08:05:32Z Weakly supervised food image segmentation using class activation maps Wang, Y. Zhu, F. Boushey, Carol Delp, E. © 2017 IEEE. Food image segmentation plays a crucial role in image-based dietary assessment and management. Successful methods for object segmentation generally rely on a large amount of labeled data on the pixel level. However, such training data are not yet available for food images and expensive to obtain. In this paper, we describe a weakly supervised convolutional neural network (CNN) which only requires image level annotation. We propose a graph based segmentation method which uses the class activation maps trained on food datasets as a top-down saliency model. We evaluate the proposed method for both classification and segmentation tasks. We achieve competitive classification accuracy compared to the previously reported results. 2018 Conference Paper http://hdl.handle.net/20.500.11937/67520 10.1109/ICIP.2017.8296487 restricted
spellingShingle Wang, Y.
Zhu, F.
Boushey, Carol
Delp, E.
Weakly supervised food image segmentation using class activation maps
title Weakly supervised food image segmentation using class activation maps
title_full Weakly supervised food image segmentation using class activation maps
title_fullStr Weakly supervised food image segmentation using class activation maps
title_full_unstemmed Weakly supervised food image segmentation using class activation maps
title_short Weakly supervised food image segmentation using class activation maps
title_sort weakly supervised food image segmentation using class activation maps
url http://hdl.handle.net/20.500.11937/67520