arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1608.07441cs.LGcs.AIcs.CVstat.ML
收藏

基于度量学习的Zero-Shot分类中的硬否定挖掘

Hard Negative Mining for Metric Learning Based Zero-Shot Classification

Normandie Univ, UNICAEN, ENSICAEN, CNRS(诺曼底大学,卡昂大学,卡昂国立高等工程师学校,国家科学研究中心);ONERA - The French Aerospace Lab(法国国家航空航天研究院)

Maxime Bucher, Stéphane Herbin, Frédéric Jurie

摘要:

零样本学习已被证明是领域自适应的有效策略。在这种情况下,本文建立在Bucher等人的最新工作基础上。[1],该工作提出了一种通过引入新的基于度量学习的目标函数来解决Zero-Shot分类问题(ZSC)的方法。该目标函数允许学习属性的最佳嵌入,并结合图像和属性之间的相似性度量。本文扩展了他们的方法,提出了几种方案来控制负对的生成,从而显着提高了性能,并在三个具有挑战性的ZSC数据集上给出了上述最先进的结果。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑