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
Description
Summary:© 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.