2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2013)
Portland, OR, USA
June 23, 2013 to June 28, 2013
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/CVPR.2013.265
We propose SCALPEL, a flexible method for object segmentation that integrates rich region-merging cues with mid- and high-level information about object layout, class, and scale into the segmentation process. Unlike competing approaches, SCALPEL uses a cascade of bottom-up segmentation models that is capable of learning to ignore boundaries early on, yet use them as a stopping criterion once the object has been mostly segmented. Furthermore, we show how such cascades can be learned efficiently. When paired with a novel method that generates better localized shape priors than our competitors, our method leads to a concise, accurate set of segmentation proposals, these proposals are more accurate on the PASCAL VOC2010 dataset than state-of-the-art methods that use re-ranking to filter much larger bags of proposals. The code for our algorithm is available online.
D. Weiss and B. Taskar, "SCALPEL: Segmentation Cascades with Localized Priors and Efficient Learning," 2013 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Portland, OR, USA USA, 2013, pp. 2035-2042.