Dual Feature Augmentation Network for Generalized Zero-shot Learning

TL;DR

This paper introduces a Dual Feature Augmentation Network (DFAN) for generalized zero-shot learning, enhancing attribute and semantic feature representations to improve classification of unseen classes.

Contribution

The paper proposes a novel dual augmentation framework with explicit attribute learning and bias correction, addressing entanglement and diversity issues in ZSL.

Findings

Significant improvement over state-of-the-art on three benchmarks

Effective attribute separation using cosine distance

Bias learner reduces attribute prediction gap

Abstract

Zero-shot learning (ZSL) aims to infer novel classes without training samples by transferring knowledge from seen classes. Existing embedding-based approaches for ZSL typically employ attention mechanisms to locate attributes on an image. However, these methods often ignore the complex entanglement among different attributes' visual features in the embedding space. Additionally, these methods employ a direct attribute prediction scheme for classification, which does not account for the diversity of attributes in images of the same category. To address these issues, we propose a novel Dual Feature Augmentation Network (DFAN), which comprises two feature augmentation modules, one for visual features and the other for semantic features. The visual feature augmentation module explicitly learns attribute features and employs cosine distance to separate them, thus enhancing attribute representation. In the semantic feature augmentation module, we propose a bias learner to capture the offset that bridges the gap between actual and predicted attribute values from a dataset's perspective. Furthermore, we introduce two predictors to reconcile the conflicts between local and global features. Experimental results on three benchmarks demonstrate the marked advancement of our method compared to state-of-the-art approaches. Our code is available at https://github.com/Sion1/DFAN.