ML Anthology

Learning to Share Visual Appearance for Multiclass Object Detection

Ruslan Salakhutdinov, Antonio Torralba, Joshua B. Tenenbaum
CVPR 2011 pp. 1481-1488
doi:10.1109/CVPR.2011.5995720 /cvpr/2011/salakhutdinov2011cvpr-learning/

Abstract

We present a hierarchical classification model that allows rare objects to borrow statistical strength from related objects that have many training examples. Unlike many of the existing object detection and recognition systems that treat different classes as unrelated entities, our model learns both a hierarchy for sharing visual appearance across 200 object categories and hierarchical parameters. Our experimental results on the challenging object localization and detection task demonstrate that the proposed model substantially improves the accuracy of the standard single object detectors that ignore hierarchical structure altogether.

CVPR Semantic Scholar

Cite

Text

Salakhutdinov et al. "Learning to Share Visual Appearance for Multiclass Object Detection." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011. doi:10.1109/CVPR.2011.5995720

Markdown

[Salakhutdinov et al. "Learning to Share Visual Appearance for Multiclass Object Detection." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011.](https://mlanthology.org/cvpr/2011/salakhutdinov2011cvpr-learning/) doi:10.1109/CVPR.2011.5995720

BibTeX

@inproceedings{salakhutdinov2011cvpr-learning,
  title     = {{Learning to Share Visual Appearance for Multiclass Object Detection}},
  author    = {Salakhutdinov, Ruslan and Torralba, Antonio and Tenenbaum, Joshua B.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2011},
  pages     = {1481-1488},
  doi       = {10.1109/CVPR.2011.5995720},
  url       = {https://mlanthology.org/cvpr/2011/salakhutdinov2011cvpr-learning/}
}