TY - CONF
T1 - FeaBoost
T2 - 31st AAAI Conference on Artificial Intelligence, AAAI 2017
AU - Niu, Yulei
AU - Lu, Zhiwu
AU - Huang, Songfang
AU - Gao, Xin
AU - Wen, Ji Rong
N1 - Funding Information:
This work was partially supported by National Natural Science Foundation of China (61573363 and 61573026), 973 Program of China (2014CB340403 and 2015CB352502), the Fundamental Research Funds for the Central Universities and the Research Funds of Renmin University of China (15XNLQ01), the Outstanding Innovative Talents Cultivation Funded Programs 2016 of Renmin Univertity of China, and IBM Global SUR Award Program.
Publisher Copyright:
Copyright © 2017, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
PY - 2017
Y1 - 2017
N2 - We propose a novel approach, called FeaBoost, to image semantic segmentation with only image-level labels taken as weakly-supervised constraints. Our approach is motivated from two evidences: 1) each superpixel can be represented as a linear combination of basic components (e.g., predefined classes); 2) visually similar superpixels have high probability to share the same set of labels, i.e., they tend to have common combination of predefined classes. By taking these two evidences into consideration, semantic segmentation is formulated as joint feature and label refinement over superpixels. Furthermore, we develop an efficient FeaBoost algorithm to solve such optimization problem. Extensive experiments on the MSRC and LabelMe datasets demonstrate the superior performance of our FeaBoost approach in comparison with the state-of-the-art methods, especially when noisy labels are provided for semantic segmentation.
AB - We propose a novel approach, called FeaBoost, to image semantic segmentation with only image-level labels taken as weakly-supervised constraints. Our approach is motivated from two evidences: 1) each superpixel can be represented as a linear combination of basic components (e.g., predefined classes); 2) visually similar superpixels have high probability to share the same set of labels, i.e., they tend to have common combination of predefined classes. By taking these two evidences into consideration, semantic segmentation is formulated as joint feature and label refinement over superpixels. Furthermore, we develop an efficient FeaBoost algorithm to solve such optimization problem. Extensive experiments on the MSRC and LabelMe datasets demonstrate the superior performance of our FeaBoost approach in comparison with the state-of-the-art methods, especially when noisy labels are provided for semantic segmentation.
UR - http://www.scopus.com/inward/record.url?scp=85030460818&partnerID=8YFLogxK
M3 - Paper
AN - SCOPUS:85030460818
SP - 1474
EP - 1480
Y2 - 4 February 2017 through 10 February 2017
ER -