Title :
BiCoS: A Bi-level co-segmentation method for image classification
Author :
Chai, Yuning ; Lempitsky, Victor ; Zisserman, Andrew
Author_Institution :
Electr. Eng. Dept., ETH Zurich, Zurich, Switzerland
Abstract :
The objective of this paper is the unsupervised segmentation of image training sets into foreground and background in order to improve image classification performance. To this end we introduce a new scalable, alternation-based algorithm for co-segmentation, BiCoS, which is simpler than many of its predecessors, and yet has superior performance on standard benchmark image datasets.
Keywords :
image classification; image segmentation; BiCoS; alternation-based algorithm; background; bilevel cosegmentation method; foreground; image classification; image training sets; unsupervised segmentation; Accuracy; Birds; Image color analysis; Image segmentation; Support vector machines; Training; Visualization;
Conference_Titel :
Computer Vision (ICCV), 2011 IEEE International Conference on
Conference_Location :
Barcelona
Print_ISBN :
978-1-4577-1101-5
DOI :
10.1109/ICCV.2011.6126546
