Joint Hierarchical Learning for Efficient Multi-Class Object Detection

Abstract

In addition to multi-class classification, the multi-class object detection task consists further in classifying a dominating background label. In this work, we present a novel approach where relevant classes are ranked higher and background labels are rejected. To this end, we arrange the classes into a tree structure where the classifiers are trained in a joint framework combining ranking and classification constraints. Our convex problem formulation naturally allows to apply a tree traversal algorithm that searches for the best class label and progressively rejects background labels. We evaluate our approach on the PASCAL VOC 2007 dataset and show a considerable speed-up of the detection time with increased detection performance.

Cite

Text

Fard et al. "Joint Hierarchical Learning for Efficient Multi-Class Object Detection." IEEE/CVF Winter Conference on Applications of Computer Vision, 2014. doi:10.1109/WACV.2014.6836090

Markdown

[Fard et al. "Joint Hierarchical Learning for Efficient Multi-Class Object Detection." IEEE/CVF Winter Conference on Applications of Computer Vision, 2014.](https://mlanthology.org/wacv/2014/fard2014wacv-joint/) doi:10.1109/WACV.2014.6836090

BibTeX

@inproceedings{fard2014wacv-joint,
  title     = {{Joint Hierarchical Learning for Efficient Multi-Class Object Detection}},
  author    = {Fard, Hamidreza Odabai and Chaouch, Mohamed and Pham, Quoc Cuong and Vacavant, Antoine and Chateau, Thierry},
  booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
  year      = {2014},
  pages     = {261-268},
  doi       = {10.1109/WACV.2014.6836090},
  url       = {https://mlanthology.org/wacv/2014/fard2014wacv-joint/}
}