DiRaC-I: Identifying Diverse and Rare Training Classes for Zero-Shot Learning
This work addresses the challenge of training class selection in zero-shot learning for image classification, offering an incremental improvement over existing methods.
The paper tackles the problem of selecting training classes for zero-shot learning by proposing DiRaC-I, a framework that identifies diverse and rare classes to improve ZSL model performance, achieving significant accuracy improvements on CUB and SUN datasets.
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.