Capturing Long-Tail Distributions of Object Subcategories

Authors:
  • XZXiangxin Zhu
    Xiangxin Zhu
  • DADragomir Anguelov
    Dragomir Anguelov
  • DRDeva Ramanan
    Deva Ramanan

Abstract
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, "brute-force" 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.

This publication has 13 references indexed in Scilit: