Work

Weakly supervised food image segmentation using class activation maps

Year: 2017

Type: conference-paper

Abstract: 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.

Source: Proceedings - International Conference on Image Processing

DOI: 10.1109/icip.2017.8296487

Authors: Yu Wang, Fengqing Zhu, Carol J. Boushey, Edward J. Delp

Institutions: Purdue University West Lafayette, University of Hawaii Cancer Center

Language: English

Topic: Advanced Neural Network Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: National Heart, Lung, and Blood Institute, National Cancer Institute, National Institute of Diabetes and Digestive and Kidney Diseases

Awards: Improving Dietary Assessment Methods Using the Cell Phone and Digital Imaging, Improving Diet Assessment in Adolescents, Multiscale Predictive Modeling of Blood Cell Damage with Experimental Verification, Improving Diet Assessment in Adolescents