Category-Independent Object Proposals with Diverse Ranking

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 36; no. 2; pp. 222 - 234
• Main Authors: Endres, Ian, Hoiem, Derek
• Format: Journal Article
• Language: English
• Published: Los Alamitos, CA IEEE 01.02.2014; IEEE Computer Society
• Subjects: Algorithms; Applied sciences; Artificial Intelligence; Computer science; control theory; systems; Exact sciences and technology; Image color analysis; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Image segmentation; Layout; Learning and adaptive systems; Object recognition; Object segmentation; Pattern Recognition, Automated - methods; Pattern recognition. Digital image processing. Computational geometry; Proposals; Reproducibility of Results; Sensitivity and Specificity; Shape; Training; Computer vision; Image segmentation; Hierarchical classification; Graph cut; Internal structure; Object segmentation; Graph theory; Pattern recognition; Data structure; Object recognition; Learning algorithm; Mesh generation
• ISSN: 0162-8828; 1939-3539; 2160-9292; 1939-3539
• 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.