Zero-Shot Learning in the Presence of Hierarchically Coarsened Labels

Colin Samplawski, Erik Learned-Miller, Heesung Kwon, Benjamin M. Marlin; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2020, pp. 926-927

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.

Related Material


[pdf]
[bibtex]
@InProceedings{Samplawski_2020_CVPR_Workshops,
author = {Samplawski, Colin and Learned-Miller, Erik and Kwon, Heesung and Marlin, Benjamin M.},
title = {Zero-Shot Learning in the Presence of Hierarchically Coarsened Labels},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2020}
}