Adaptive Metric Learning For Zero-Shot Recognition
Adaptive Metric Learning For Zero-Shot Recognition
复制标题
用于零样本识别的自适应度量学习
DOI：
10.1109/lsp.2019.2917148
复制
发表时间：
2019-09-01
影响因子：
3.9
通讯作者：
Chen, Xilin
中科院分区：
文献类型：
--
作者：
Jiang, Huajie;Wang, Ruiping;Chen, Xilin
近几年来，零镜头学习(ZSL)因其识别新对象的能力而广受欢迎，该方法利用语义信息来建立不同类别之间的关系。传统的ZSL方法通常侧重于在可见类之间学习更健壮的视觉语义嵌入，并将其直接应用于不可见类，而不考虑它们是否合适。众所周知，在可见类和不可见类之间存在域间隙。为了解决这一问题，我们提出了一种新的自适应度量学习方法来度量视觉样本和类语义之间的兼容性，其中利用类的相似性来适应视觉语义嵌入到不可见类。在四个基准ZSL数据集上的大量实验表明了该方法的有效性。
Zero-shot learning (ZSL) has enjoyed great popularity in recent years due to its ability to recognize novel objects, where semantic information is exploited to build up relations among different categories. Traditional ZSL approaches usually focus on learning more robust visual-semantic embeddings among seen classes and directly apply them to the unseen classes without considering whether they are suitable. It is well known that domain gap exists between seen and unseen classes. In order to tackle such problem, we propose a novel adaptive metric learning approach to measure the compatibility between visual samples and class semantics, where class similarities are utilized to adapt the visual-semantic embedding to the unseen classes. Extensive experiments on four benchmark ZSL datasets show the effectiveness of the proposed approach.