caa a22 4500 605446709 CHVBK 20210128100128.0 cr unu---uuuuu 210128e20150101xx s 000 0 eng 10.1007/s11042-014-1967-5 doi (NATIONALLICENCE)springer-10.1007/s11042-014-1967-5 Boosted MIML method for weakly-supervised image semantic segmentation [Elektronische Daten] [Yang Liu, Zechao Li, Jing Liu, Hanqing Lu] Weakly-supervised image semantic segmentation aims to segment images into semantically consistent regions with only image-level labels are available, and is of great significance for fine-grained image analysis, retrieval and other possible applications. In this paper, we propose a Boosted Multi-Instance Multi-Label (BMIML) learning method to address this problem, the approach is built upon the following principles. We formulate the image semantic segmentation task as a MIML problem under the boosting framework, where the goal is to simultaneously split the superpixels obtained from over-segmented images into groups and train one classifier for each group. In the method, a loss function which uses the image-level labels as weakly-supervised constraints, is employed to suitable semantic labels to these classifiers. At the same time a contextual loss term is also combined to reduce the ambiguities existing in the training data. In each boosting round, we introduce an "objectness” measure to jointly reweigh the instances, in order to overcome the disturbance from highly frequent background superpixels. We demonstrate that BMIML outperforms the state-of-the-arts for weakly-supervised semantic segmentation on two widely used datasets, i.e., MSRC and LabelMe. Springer Science+Business Media New York, 2014 MIML nationallicence Weakly-supervised nationallicence Semantic segmentation nationallicence Objectness nationallicence Liu Yang National Laboratory of Pattern Recognition, Institution of Automation Chinese Academy of Sciences, Beijing, China aut Li Zechao School of Computer Science, Nanjing University of Science and Technology, Nanjing, China aut Liu Jing National Laboratory of Pattern Recognition, Institution of Automation Chinese Academy of Sciences, Beijing, China aut Lu Hanqing National Laboratory of Pattern Recognition, Institution of Automation Chinese Academy of Sciences, Beijing, China aut Multimedia Tools and Applications Springer US; http://www.springer-ny.com 74/2(2015-01-01), 543-559 1380-7501 74:2<543 2015 74 11042 https://doi.org/10.1007/s11042-014-1967-5 text/html Onlinezugriff via DOI BK010053 XK010053 XK010000 Metadata rights reserved Springer special CC-BY-NC licence nationallicence 1 research-article jats NATIONALLICENCE NATIONALLICENCE NL-springer NATIONALLICENCE 856 40 https://doi.org/10.1007/s11042-014-1967-5 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Liu Yang National Laboratory of Pattern Recognition, Institution of Automation Chinese Academy of Sciences, Beijing, China aut NATIONALLICENCE 700 1- Li Zechao School of Computer Science, Nanjing University of Science and Technology, Nanjing, China aut NATIONALLICENCE 700 1- Liu Jing National Laboratory of Pattern Recognition, Institution of Automation Chinese Academy of Sciences, Beijing, China aut NATIONALLICENCE 700 1- Lu Hanqing National Laboratory of Pattern Recognition, Institution of Automation Chinese Academy of Sciences, Beijing, China aut NATIONALLICENCE 773 0- Multimedia Tools and Applications Springer US; http://www.springer-ny.com 74/2(2015-01-01), 543-559 1380-7501 74:2<543 2015 74 11042