Learning Class Prototypes via Structure Alignment for Zero-Shot Recognition

TL;DR

This paper introduces a coupled dictionary learning method that aligns visual and semantic structures using class prototypes to enhance zero-shot recognition by leveraging discriminative visual information.

Contribution

It proposes a novel structure alignment approach that improves semantic space discriminability for zero-shot learning by utilizing visual space information.

Findings

Effective on four benchmark datasets.

Improves zero-shot recognition accuracy.

Aligns visual and semantic structures successfully.

Abstract

Zero-shot learning (ZSL) aims to recognize objects of novel classes without any training samples of specific classes, which is achieved by exploiting the semantic information and auxiliary datasets. Recently most ZSL approaches focus on learning visual-semantic embeddings to transfer knowledge from the auxiliary datasets to the novel classes. However, few works study whether the semantic information is discriminative or not for the recognition task. To tackle such problem, we propose a coupled dictionary learning approach to align the visual-semantic structures using the class prototypes, where the discriminative information lying in the visual space is utilized to improve the less discriminative semantic space. Then, zero-shot recognition can be performed in different spaces by the simple nearest neighbor approach using the learned class prototypes. Extensive experiments on four benchmark datasets show the effectiveness of the proposed approach.