摘要
Collecting training images for all visual categories is not only expensive but also impractical. Zero-shot learning (ZSL), especially using attributes, offers a pragmatic solution to this problem. However, at test time most attribute-based methods require a full description of attribute associations for each unseen class. Providing these associations is time consuming and often requires domain specific knowledge. In this work, we aim to carry out attribute-based zero-shot classification in an unsupervised manner. We propose an approach to learn relations that couples class embeddings with their corresponding attributes. Given only the name of an unseen class, the learned relationship model is used to automatically predict the class-attribute associations. Furthermore, our model facilitates transferring attributes across data sets without additional effort. Integrating knowledge from multiple sources results in a significant additional improvement in performance. We evaluate on two public data sets: Animals with Attributes and aPascal/aYahoo. Our approach outperforms state-of the-art methods in both predicting class-attribute associations and unsupervised ZSL by a large margin.
摘要译文
收集所有视觉类别的培训图像不仅昂贵，而且不切实际的Zero（ZSL）特别是使用属性，为此问题提供了务实的解决方案然而，在测试时，大多数基于属性的方法都需要对每个不可见类别的属性关联进行全面描述提供这些关联是耗时的，通常需要领域特定的知识。在这项工作中，我们的目标是以无监督的方式进行基于属性的零点分类我们提出一种方法来学习将类嵌入与他们相应的属性相结合的关系。只给出一个看不见的类的名字，学习关系模型用于自动预测类属性关联。此外，我们的模型有助于跨数据集传输属性，而无需额外的努力整合来自多个来源的知识可以显着提高性能。我们对两个公共数据集进行评估：动物与属性和aPascal /aYahoo 我们的方法在预测类属性关联和无监督的ZSL中大大提高了最先进的方法
Ziad Al-Halah[1];Makarand Tapaswi[1];Rainer Stiefelhagen[1]. Recovering the Missing Link: Predicting Class-Attribute Associations for Unsupervised Zero-Shot Learning[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 27-30 June 2016, IEEE, 2016: -