Unsupervised Joint Object Discovery and Segmentation in Internet Images
CVPR, pp. 1939-1946, 2013.
We present a new unsupervised algorithm to discover and segment out common objects from large and diverse image collections. In contrast to previous co-segmentation methods, our algorithm performs well even in the presence of significant amounts of noise images (images not containing a common object), as typical for datasets collected fro...More
PPT (Upload PPT)