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

TL;DR

This paper introduces DiRaC-I, a framework that intelligently selects diverse and rare classes from datasets to enhance zero-shot learning models' performance in image classification tasks.

Contribution

DiRaC-I is a novel framework that constructs diverse seed classes and mines classes capturing both diversity and rarity for improved ZSL training.

Findings

DiRaC-I significantly improves ZSL classification accuracy.

Effective selection of diverse and rare classes enhances model performance.

Experiments on CUB and SUN datasets validate the approach.

Abstract

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.