# Generalised Zero-Shot Learning with Domain Classification in a Joint Semantic and Visual Space

## TL;DR

This paper introduces a novel generalized zero-shot learning approach that combines semantic and visual data in a joint space with domain classification, significantly improving classification accuracy for unseen classes.

## Contribution

It proposes a joint latent space representation and domain classification to better distinguish seen and unseen classes, reducing bias and enhancing GZSL performance.

## Key findings

- Achieves state-of-the-art results on benchmark datasets.
- Improves harmonic mean and unseen class accuracy.
- Reduces bias towards seen classes in GZSL.

## Abstract

Generalised zero-shot learning (GZSL) is a classification problem where the learning stage relies on a set of seen visual classes and the inference stage aims to identify both the seen visual classes and a new set of unseen visual classes. Critically, both the learning and inference stages can leverage a semantic representation that is available for the seen and unseen classes. Most state-of-the-art GZSL approaches rely on a mapping between latent visual and semantic spaces without considering if a particular sample belongs to the set of seen or unseen classes. In this paper, we propose a novel GZSL method that learns a joint latent representation that combines both visual and semantic information. This mitigates the need for learning a mapping between the two spaces. Our method also introduces a domain classification that estimates whether a sample belongs to a seen or an unseen class. Our classifier then combines a class discriminator with this domain classifier with the goal of reducing the natural bias that GZSL approaches have toward the seen classes. Experiments show that our method achieves state-of-the-art results in terms of harmonic mean, the area under the seen and unseen curve and unseen classification accuracy on public GZSL benchmark data sets. Our code will be available upon acceptance of this paper.