Learning Prototype via Placeholder for Zero-shot Recognition

TL;DR

This paper introduces a novel zero-shot learning method that uses placeholder prototypes to better align visual and semantic spaces, significantly improving recognition of unseen classes.

Contribution

It proposes learning prototypes via placeholders to mitigate domain shift, combining seen classes to hallucinate new classes as placeholders, and employs semantic-oriented fine-tuning for reliability.

Findings

Significant performance improvements on five benchmark datasets.

Effective mitigation of domain shift in zero-shot learning.

Enhanced semantic reliability of class prototypes.

Abstract

Zero-shot learning (ZSL) aims to recognize unseen classes by exploiting semantic descriptions shared between seen classes and unseen classes. Current methods show that it is effective to learn visual-semantic alignment by projecting semantic embeddings into the visual space as class prototypes. However, such a projection function is only concerned with seen classes. When applied to unseen classes, the prototypes often perform suboptimally due to domain shift. In this paper, we propose to learn prototypes via placeholders, termed LPL, to eliminate the domain shift between seen and unseen classes. Specifically, we combine seen classes to hallucinate new classes which play as placeholders of the unseen classes in the visual and semantic space. Placed between seen classes, the placeholders encourage prototypes of seen classes to be highly dispersed. And more space is spared for the insertion of well-separated unseen ones. Empirically, well-separated prototypes help counteract visual-semantic misalignment caused by domain shift. Furthermore, we exploit a novel semantic-oriented fine-tuning to guarantee the semantic reliability of placeholders. Extensive experiments on five benchmark datasets demonstrate the significant performance gain of LPL over the state-of-the-art methods. Code is available at https://github.com/zaiquanyang/LPL.