arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.00236cs.CV
收藏

DiRaC-I:为零样本学习识别多样化和稀有的训练类

DiRaC-I: Identifying Diverse and Rare Training Classes for Zero-Shot Learning

Indian Institute of Technology Guwahati(印度理工学院古瓦哈蒂分校)

Sandipan Sarma, Arijit Sur

摘要:

受主动学习等策略的启发,从零样本学习(Zero-Shot Learning,简称ZRL)的数据集中智能地选择训练类可以提高现有Zero-Shot学习方法的性能。在这项工作中,我们提出了一个称为多样和稀有类标识符(DiRaC-I)的框架,给定基于属性的数据集,可以智能地产生最合适的“可见类”来训练BML模型。DiRaC-I有两个主要目标-构建一组多样化的种子类,其次是由这些种子类初始化的视觉语义挖掘算法,获得在对象域中充分捕获多样性和稀有性的类。然后,这些类可以被用作“看到的类”,以训练用于图像分类的RML模型。我们采用了一个现实世界的情况下,新的对象类是既不适用于DiRaC-I,也不适用于在训练过程中的ARML模型,并进行了广泛的实验上的两个基准数据集的zero-shot图像分类- CUB和SUN。我们的研究结果表明,DiRaC-I有助于BML模型实现显着的分类准确性提高。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑