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.
|Original language||English (US)|
|Number of pages||7|
|State||Published - 2017|
|Event||31st AAAI Conference on Artificial Intelligence, AAAI 2017 - San Francisco, United States|
Duration: Feb 4 2017 → Feb 10 2017
|Conference||31st AAAI Conference on Artificial Intelligence, AAAI 2017|
|Period||02/4/17 → 02/10/17|
Bibliographical noteFunding 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.
Copyright © 2017, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
ASJC Scopus subject areas
- Artificial Intelligence