Transductive Unbiased Embedding for Zero-Shot Learning
Transductive Unbiased Embedding for Zero-Shot Learning
复制标题
DOI：
10.1109/cvpr.2018.00113
复制
发表时间：
2018-03
期刊：
影响因子：
--
通讯作者：
Jie Song;Chengchao Shen;Yezhou Yang;Yang Liu;Mingli Song
中科院分区：
文献类型：
--
作者：
Jie Song;Chengchao Shen;Yezhou Yang;Yang Liu;Mingli Song
大多数现有的零次学习（Zero-Shot Learning，简称ZRL）方法都存在强偏差问题，即看不见（目标）类的实例往往被归类为可见（源）类之一。因此，它们在部署到广义的CNOL设置中后性能很差。在本文中，我们提出了一种简单而有效的方法，称为准完全监督学习（QFSL），以减轻偏见问题。我们的方法遵循的方式，即假设标记的源图像和未标记的目标图像都可用于训练的转导学习。在语义嵌入空间中，将已标记的源图像映射到源类别指定的几个固定点上，将未标记的目标图像强制映射到目标类别指定的其他点上。在AwA 2、CUB和SUN数据集上进行的实验表明，在广义的BNL设置下，我们的方法比现有的最先进的方法性能高出9.3%~ 24.5%，在传统的BNL设置下，我们的方法比现有的最先进的方法性能高出0.2%~ 16.2%。
Most existing Zero-Shot Learning (ZSL) methods have the strong bias problem, in which instances of unseen (target) classes tend to be categorized as one of the seen (source) classes. So they yield poor performance after being deployed in the generalized ZSL settings. In this paper, we propose a straightforward yet effective method named Quasi-Fully Supervised Learning (QFSL) to alleviate the bias problem. Our method follows the way of transductive learning, which assumes that both the labeled source images and unlabeled target images are available for training. In the semantic embedding space, the labeled source images are mapped to several fixed points specified by the source categories, and the unlabeled target images are forced to be mapped to other points specified by the target categories. Experiments conducted on AwA2, CUB and SUN datasets demonstrate that our method outperforms existing state-of-the-art approaches by a huge margin of 9.3 ~ 24.5% following generalized ZSL settings, and by a large margin of 0.2 ~ 16.2% following conventional ZSL settings.