Weakly supervised image semantic segmentation based on clustering superpixels

Xiong Yan; Xiaohua Liu

doi:10.1117/12.2302479

10 April 2018 Weakly supervised image semantic segmentation based on clustering superpixels

Xiong Yan, Xiaohua Liu

Proceedings Volume 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017); 106151Y (2018) https://doi.org/10.1117/12.2302479
Event: Ninth International Conference on Graphic and Image Processing, 2017, Qingdao, China

Abstract

In this paper, we propose an image semantic segmentation model which is trained from image-level labeled images. The proposed model starts with superpixel segmenting, and features of the superpixels are extracted by trained CNN. We introduce a superpixel-based graph followed by applying the graph partition method to group correlated superpixels into clusters. For the acquisition of inter-label correlations between the image-level labels in dataset, we not only utilize label co-occurrence statistics but also exploit visual contextual cues simultaneously. At last, we formulate the task of mapping appropriate image-level labels to the detected clusters as a problem of convex minimization. Experimental results on MSRC-21 dataset and LableMe dataset show that the proposed method has a better performance than most of the weakly supervised methods and is even comparable to fully supervised methods.

Citation Download Citation

Xiong Yan and Xiaohua Liu "Weakly supervised image semantic segmentation based on clustering superpixels", Proc. SPIE 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017), 106151Y (10 April 2018); https://doi.org/10.1117/12.2302479

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available