Zero-Shot Learning in the Presence of Hierarchically Coarsened Labels

Colin Samplawski, Erik G. Learned-Miller, Heesung Kwon, Benjamin M. Marlin

CVPRW 2020 pp. 4015-4019

doi:10.1109/CVPRW50498.2020.00471 /cvprw/2020/samplawski2020cvprw-zeroshot/

Abstract

Zero-shot image classification leverages side information including label attributes and semantic class hierarchies to transfer knowledge about fine-grained training classes to fine-grained zero-shot classes. In this paper, we consider the problem of zero-shot learning of fine-grained classes given a mixture of images with fine-grained and coarsened labels. We show how probabilistic hierarchical classification models can be used to simultaneously accommodate fine and coarse-grained labels in the zero-shot learning setting. We show that this approach is robust even to significant levels of coarsening.

CVPRW Semantic Scholar

Cite

Text

Samplawski et al. "Zero-Shot Learning in the Presence of Hierarchically Coarsened Labels." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020. doi:10.1109/CVPRW50498.2020.00471

Markdown

[Samplawski et al. "Zero-Shot Learning in the Presence of Hierarchically Coarsened Labels." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020.](https://mlanthology.org/cvprw/2020/samplawski2020cvprw-zeroshot/) doi:10.1109/CVPRW50498.2020.00471

BibTeX

@inproceedings{samplawski2020cvprw-zeroshot,
  title     = {{Zero-Shot Learning in the Presence of Hierarchically Coarsened Labels}},
  author    = {Samplawski, Colin and Learned-Miller, Erik G. and Kwon, Heesung and Marlin, Benjamin M.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2020},
  pages     = {4015-4019},
  doi       = {10.1109/CVPRW50498.2020.00471},
  url       = {https://mlanthology.org/cvprw/2020/samplawski2020cvprw-zeroshot/}
}