论文标题
通过语义歧视者改善广义零射门学习
Improving Generalized Zero-Shot Learning by Semantic Discriminator
论文作者
论文摘要
公认的事实是，在广义零局学习（GZSL）的设置中，看不见的类的分类准确性远低于传统的零射倾斜（ZSL）。原因之一是一个实例总是错误地分类为错误的域。在这里，我们将看到和看不见的类别称为两个领域。我们提出了一种新的方法，以区分这些实例是来自可见的还是看不见的班级。首先，实例的视觉功能将投影到语义空间中。然后，投影的语义向量与类语义嵌入向量之间的绝对规范差，以及投影的语义向量与所见类的语义嵌入向量之间的最小距离被用作歧视基础。该方法称为SD（语义歧视器），因为实例的域判断是在语义空间中执行的。我们的方法可以与任何现有的ZSL方法和完全监督分类模型结合使用，以形成一种新的GZSL方法。此外，我们的方法非常简单，不需要任何固定参数。
It is a recognized fact that the classification accuracy of unseen classes in the setting of Generalized Zero-Shot Learning (GZSL) is much lower than that of traditional Zero-Shot Leaning (ZSL). One of the reasons is that an instance is always misclassified to the wrong domain. Here we refer to the seen and unseen classes as two domains respectively. We propose a new approach to distinguish whether the instances come from the seen or unseen classes. First the visual feature of instance is projected into the semantic space. Then the absolute norm difference between the projected semantic vector and the class semantic embedding vector, and the minimum distance between the projected semantic vectors and the semantic embedding vectors of the seen classes are used as discrimination basis. This approach is termed as SD (Semantic Discriminator) because domain judgement of instance is performed in the semantic space. Our approach can be combined with any existing ZSL method and fully supervision classification model to form a new GZSL method. Furthermore, our approach is very simple and does not need any fixed parameters.
