Hard Negative Mining for Metric Learning Based Zero-Shot Classification
Machine Learning
2016-08-29 v1 Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Abstract
Zero-Shot learning has been shown to be an efficient strategy for domain adaptation. In this context, this paper builds on the recent work of Bucher et al. [1], which proposed an approach to solve Zero-Shot classification problems (ZSC) by introducing a novel metric learning based objective function. This objective function allows to learn an optimal embedding of the attributes jointly with a measure of similarity between images and attributes. This paper extends their approach by proposing several schemes to control the generation of the negative pairs, resulting in a significant improvement of the performance and giving above state-of-the-art results on three challenging ZSC datasets.
Cite
@article{arxiv.1608.07441,
title = {Hard Negative Mining for Metric Learning Based Zero-Shot Classification},
author = {Maxime Bucher and Stéphane Herbin and Frédéric Jurie},
journal= {arXiv preprint arXiv:1608.07441},
year = {2016}
}