Capturing Long-Tail Distributions of Object Subcategories
Authors:
- Xiangxin ZhuXZXiangxin Zhu
- Dragomir AnguelovDADragomir Anguelov
- Deva RamananDRDeva Ramanan
- 1 June 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 915-922
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.Keywords
This publication has 13 references indexed in Scilit:
- Fast, Accurate Detection of 100,000 Object Classes on a Single Machine2013
- Subcategory-Aware Object Classification2013
- Tabula rasa: Model transfer for object category detection2011
- Ensemble of exemplar-SVMs for object detection and beyond2011
- Learning to share visual appearance for multiclass object detection2011
- Shared parts for deformable part-based models2011
- Object Detection with Discriminatively Trained Part-Based ModelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- MapReduceCommunications of the ACM, 2008
- Sharing Visual Features for Multiclass and Multiview Object DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007
- Family resemblances: Studies in the internal structure of categoriesCognitive Psychology, 1975