Title
Probabilistic Label Trees For Efficient Large Scale Image Classification
Keywords
image classification; label tree; large-scale recognition; maximum likelihood estimation
Abstract
Large-scale recognition problems with thousands of classes pose a particular challenge because applying the classifier requires more computation as the number of classes grows. The label tree model integrates classification with the traversal of the tree so that complexity grows logarithmically. In this paper, we show how the parameters of the label tree can be found using maximum likelihood estimation. This new probabilistic learning technique produces a label tree with significantly improved recognition accuracy. © 2013 IEEE.
Publication Date
11-15-2013
Publication Title
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Number of Pages
843-850
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/CVPR.2013.114
Copyright Status
Unknown
Socpus ID
84887356989 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/84887356989
STARS Citation
Liu, Baoyuan; Sadeghi, Fereshteh; Tappen, Marshall; Shamir, Ohad; and Liu, Ce, "Probabilistic Label Trees For Efficient Large Scale Image Classification" (2013). Scopus Export 2010-2014. 6466.
https://stars.library.ucf.edu/scopus2010/6466