Imagination Based Sample Construction for Zero-Shot Learning

TL;DR

This paper introduces IBSC, a novel zero-shot learning approach that constructs synthetic image samples in feature space by mimicking human cognition, transforming ZSL into a supervised learning problem.

Contribution

It proposes the first sample construction method for ZSL, leveraging attribute-feature association and dissimilarity selection to generate training data for unseen classes.

Findings

Outperforms existing ZSL methods on four benchmark datasets.

Transforms ZSL into a supervised learning problem with constructed samples.

Establishes a baseline for future sample construction approaches.

Abstract

Zero-shot learning (ZSL) which aims to recognize unseen classes with no labeled training sample, efficiently tackles the problem of missing labeled data in image retrieval. Nowadays there are mainly two types of popular methods for ZSL to recognize images of unseen classes: probabilistic reasoning and feature projection. Different from these existing types of methods, we propose a new method: sample construction to deal with the problem of ZSL. Our proposed method, called Imagination Based Sample Construction (IBSC), innovatively constructs image samples of target classes in feature space by mimicking human associative cognition process. Based on an association between attribute and feature, target samples are constructed from different parts of various samples. Furthermore, dissimilarity representation is employed to select high-quality constructed samples which are used as labeled data to train a specific classifier for those unseen classes. In this way, zero-shot learning is turned into a supervised learning problem. As far as we know, it is the first work to construct samples for ZSL thus, our work is viewed as a baseline for future sample construction methods. Experiments on four benchmark datasets show the superiority of our proposed method.