Capturing long-tail distributions of object subcategories
We argue that object subcategories follow a long-tail distribution:
a few subcategories are common, while many are
rare. We describe distributed algorithms for learning large-mixture
models that capture long-tail distributions, which
are hard to model with current approaches. We introduce a
generalized notion of mixtures (or subcategories) that allow
for examples to be shared across multiple subcategories. We
optimize our models with a discriminative clustering algorithm
that searches over mixtures in a distributed, “bruteforce”
fashion. We used our scalable system to train tens
of thousands of deformable mixtures for VOC objects. We
demonstrate significant performance improvements, particularly
for object classes that are characterized by large appearance
variation.
Download: pdf
Text Reference
Xiangxin Zhu, Dragomir Anguelov, and Deva Ramanan. Capturing long-tail distributions of object subcategories. In Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on, 915–922. IEEE, 2014.BibTeX Reference
@inproceedings{ZhuAR_CVPR_2014,author = "Zhu, Xiangxin and Anguelov, Dragomir and Ramanan, Deva",
title = "Capturing long-tail distributions of object subcategories",
booktitle = "Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on",
pages = "915--922",
year = "2014",
organization = "IEEE"
}