Probabilistic Label Trees for Efficient Large Scale Image Classification

Baoyuan Liu, Fereshteh Sadeghi, Marshall Tappen, Ohad Shamir, Ce Liu

CVPR 2013

doi:10.1109/CVPR.2013.114 /cvpr/2013/liu2013cvpr-probabilistic/

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.

PDF CVPR Semantic Scholar

Cite

Text

Liu et al. "Probabilistic Label Trees for Efficient Large Scale Image Classification." Conference on Computer Vision and Pattern Recognition, 2013. doi:10.1109/CVPR.2013.114

Markdown

[Liu et al. "Probabilistic Label Trees for Efficient Large Scale Image Classification." Conference on Computer Vision and Pattern Recognition, 2013.](https://mlanthology.org/cvpr/2013/liu2013cvpr-probabilistic/) doi:10.1109/CVPR.2013.114

BibTeX

@inproceedings{liu2013cvpr-probabilistic,
  title     = {{Probabilistic Label Trees for Efficient Large Scale Image Classification}},
  author    = {Liu, Baoyuan and Sadeghi, Fereshteh and Tappen, Marshall and Shamir, Ohad and Liu, Ce},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2013},
  doi       = {10.1109/CVPR.2013.114},
  url       = {https://mlanthology.org/cvpr/2013/liu2013cvpr-probabilistic/}
}