Weak supervised instance segmentation for food image recognition
Daoxin ZHANG

Speaker Event details

Daoxin ZHANG
Graduate Student, Computer Vision
College of Computer Science and Technology
Zhejiang University

Date:

Time:

Venue:








26 April 2018, Thursday

10.30am 11.30am

Meeting Room 4-4, Level 4
School of Information Systems
Singapore Management University
80 Stamford Road
Singapore 178902

We look forward to seeing you at this research seminar.

Allow us to share this seminar with your co-workers

Abstract

Instance semantic segmentation aims to detect objects in images outputting both bounding box and segmentation mask. Recent deep learning methods to tackle this problem leverage modern detection and semantic segmentation technique achieving impressive results. However, costly semantic mask labels limit the applications. In this talk, we discuss weak supervised learning for image segmentation and its application to food image recognition tasks. Training single-model instance segmentation DCNN with only bounding box annotations enables state-of-art instance segmentation methods to apply to much more image domains like foods, which provides deeper understanding of food images.

About the speaker

Daoxin Zhang is a research assistant in LARC and graduate student major in computer vision, College of computer science and technology, Zhejiang University. He received his Bachelor degree from School of mathematical Science, Zhejiang University. Before join LARC, he is a research student in Alibaba Zhejiang university Joint laboratory (AZFT). His research area includes semantic segmentation and its applications. And he has been focusing on weak supervised segmentation task recently.

 

 
 
 
 
This research is supported by the National Research Foundation, Prime Minister's Office, Singapore under its International Research Centres in Singapore Funding Initiative.
 

If you wish to unsubscribe from the Living Analytics Research Centre mailing list, please click here
© Copyright 2016 by Singapore Management University. All Rights Reserved. In order to enhance user experience and
improve our provided services, some usage data may be collected. For more information, please refer to our Privacy Policy
     
SMU SIS LARC CMU Heinz College