10 April 2018 Weakly supervised image semantic segmentation based on clustering superpixels
Author Affiliations +
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.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xiong Yan, Xiong Yan, Xiaohua Liu, 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); doi: 10.1117/12.2302479; https://doi.org/10.1117/12.2302479
PROCEEDINGS
10 PAGES


SHARE
RELATED CONTENT

Image segmentation on adaptive sub-region smoothing
Proceedings of SPIE (January 22 2017)
Length estimation of digital curves
Proceedings of SPIE (September 22 1999)
Attention trees and semantic paths
Proceedings of SPIE (February 11 2007)

Back to Top