DFS: A Diverse Feature Synthesis Model for Generalized Zero-Shot Learning

TL;DR

This paper introduces DFS, a novel model that enhances generalized zero-shot learning by synthesizing diverse, class-specific features using both semantic and visual knowledge, leading to improved classifier robustness.

Contribution

DFS uniquely combines semantic and visual knowledge in an aligned space to generate diverse features for unseen classes, improving GZSL performance.

Findings

DFS produces more diverse features for unseen classes.

DFS achieves superior results on multiple benchmarks.

The model is low-complexity and easy to implement.

Abstract

Generative based strategy has shown great potential in the Generalized Zero-Shot Learning task. However, it suffers severe generalization problem due to lacking of feature diversity for unseen classes to train a good classifier. In this paper, we propose to enhance the generalizability of GZSL models via improving feature diversity of unseen classes. For this purpose, we present a novel Diverse Feature Synthesis (DFS) model. Different from prior works that solely utilize semantic knowledge in the generation process, DFS leverages visual knowledge with semantic one in a unified way, thus deriving class-specific diverse feature samples and leading to robust classifier for recognizing both seen and unseen classes in the testing phase. To simplify the learning, DFS represents visual and semantic knowledge in the aligned space, making it able to produce good feature samples with a low-complexity implementation. Accordingly, DFS is composed of two consecutive generators: an aligned feature generator, transferring semantic and visual representations into aligned features; a synthesized feature generator, producing diverse feature samples of unseen classes in the aligned space. We conduct comprehensive experiments to verify the efficacy of DFS. Results demonstrate its effectiveness to generate diverse features for unseen classes, leading to superior performance on multiple benchmarks. Code will be released upon acceptance.