FeaBoost: Joint feature and label refinement for semantic segmentation

Yulei Niu, Zhiwu Lu*, Songfang Huang, Xin Gao, Ji Rong Wen

*Corresponding author for this work

Research output: Contribution to conferencePaperpeer-review

5 Scopus citations


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 languageEnglish (US)
Number of pages7
StatePublished - 2017
Event31st AAAI Conference on Artificial Intelligence, AAAI 2017 - San Francisco, United States
Duration: Feb 4 2017Feb 10 2017


Conference31st AAAI Conference on Artificial Intelligence, AAAI 2017
Country/TerritoryUnited States
CitySan Francisco

Bibliographical note

Publisher Copyright:
Copyright © 2017, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

ASJC Scopus subject areas

  • Artificial Intelligence


Dive into the research topics of 'FeaBoost: Joint feature and label refinement for semantic segmentation'. Together they form a unique fingerprint.

Cite this