University of Illinois at Urbana-Champaign, Urbana.
IEEE Trans Pattern Anal Mach Intell. 2014 Feb;36(2):222-34. doi: 10.1109/TPAMI.2013.122.
We propose a category-independent method to produce a bag of regions and rank them, such that top-ranked regions are likely to be good segmentations of different objects. Our key objectives are completeness and diversity: Every object should have at least one good proposed region, and a diverse set should be top-ranked. Our approach is to generate a set of segmentations by performing graph cuts based on a seed region and a learned affinity function. Then, the regions are ranked using structured learning based on various cues. Our experiments on the Berkeley Segmentation Data Set and Pascal VOC 2011 demonstrate our ability to find most objects within a small bag of proposed regions.
我们提出了一种类别无关的方法来生成一组区域并对其进行排序，以便排名靠前的区域很可能是不同对象的良好分割。我们的主要目标是完整性和多样性：每个对象都应该至少有一个好的建议区域，并且应该将一组多样化的区域排在前列。我们的方法是通过基于种子区域和学习的亲和力函数执行图切割来生成一组分割。然后，使用基于各种线索的结构化学习对区域进行排名。我们在 Berkeley Segmentation Data Set 和 Pascal VOC 2011 上的实验表明，我们有能力在一小袋建议区域内找到大多数对象。
