Unsupervised co-segmentation through region matching

Jose C. Rubio, Joan Serrat, Antonio Lopez, Nikos Paragios

Research output: Contribution to journalArticleResearchpeer-review

135 Citations (Scopus)


Co-segmentation is defined as jointly partitioning multiple images depicting the same or similar object, into foreground and background. Our method consists of a multiple-scale multiple-image generative model, which jointly estimates the foreground and background appearance distributions from several images, in a non-supervised manner. In contrast to other co-segmentation methods, our approach does not require the images to have similar foregrounds and different backgrounds to function properly. Region matching is applied to exploit inter-image information by establishing correspondences between the common objects that appear in the scene. Moreover, computing many-to-many associations of regions allow further applications, like recognition of object parts across images. We report results on iCoseg, a challenging dataset that presents extreme variability in camera viewpoint, illumination and object deformations and poses. We also show that our method is robust against large intra-class variability in the MSRC database.
Original languageEnglish
Pages (from-to)749-756
Number of pages8
Journal2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Publication statusPublished - 2012


Dive into the research topics of 'Unsupervised co-segmentation through region matching'. Together they form a unique fingerprint.

Cite this