Inspired by strategies like Active Learning, it is intuitive that intelligently selecting the training classes from a dataset for Zero-Shot Learning (ZSL) can improve the performance of existing ZSL methods. In this work, we propose a framework called Diverse and Rare Class Identifier (DiRaC-I) which, given an attribute-based dataset, can intelligently yield the most suitable "seen classes" for training ZSL models. DiRaC-I has two main goals - constructing a diversified set of seed classes, followed by a visual-semantic mining algorithm initialized by these seed classes that acquires the classes capturing both diversity and rarity in the object domain adequately. These classes can then be used as "seen classes" to train ZSL models for image classification. We adopt a real-world scenario where novel object classes are available to neither DiRaC-I nor the ZSL models during training and conducted extensive experiments on two benchmark data sets for zero-shot image classification - CUB and SUN. Our results demonstrate DiRaC-I helps ZSL models to achieve significant classification accuracy improvements.
翻译:在积极学习等战略的启发下,明智地从零热学习(ZSL)的数据集中选择培训课程可以提高现有ZSL方法的性能,这是直觉的。在这个工作中,我们提议了一个称为多样性和累分级识别器(DiRaC-I)的框架,根据一个基于属性的数据集,该框架可以明智地产生用于培训ZSL模型的最合适的“见习”课程。DiRaC-I有两个主要目标:建立一套多样化的种子类,然后由这些种子类开始的视觉-语义采掘算法,这些种子类能够充分获得在目标领域捕捉到多样性和罕见性的课程。然后这些课程可以作为“见习”课程用于培训ZSL模型进行图像分类。我们采用了一种现实世界情景,在培训期间,既没有DRAC-I,也没有ZSL模型提供新的对象课程。我们还对两套零光图像分类基准数据集(CUB和SUN)进行了广泛的实验。我们的成果展示了DRAC-I帮助ZSL模型实现重大分类精确性改进。