Hard Negative Mining for Metric Learning Based Zero-Shot Classification

Autor:	Bucher, Maxime, Herbin, Stéphane, Jurie, Frédéric
Rok vydání:	2016
Předmět:	Computer Science - Learning Computer Science - Artificial Intelligence Computer Science - Computer Vision and Pattern Recognition Statistics - Machine Learning
Zdroj:	ECCV 16 WS TASK-CV: Transferring and Adapting Source Knowledge in Computer Vision, Oct 2016, Amsterdam, Netherlands. ECCV 16 WS TASK-CV: Transferring and Adapting Source Knowledge in Computer Vision
Druh dokumentu:	Working Paper
Popis:	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.
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1608.07441 Zobrazit plný text záznamu View this record from Arxiv