Bidirectional Mapping Coupled GAN for Generalized Zero-Shot Learning

TL;DR

This paper introduces BMCoGAN, a bidirectional mapping coupled GAN that leverages both seen and unseen class semantics with Wasserstein optimization to improve generalized zero-shot learning by better modeling joint distributions and maintaining domain distinctions.

Contribution

The paper proposes a novel bidirectional coupled GAN with Wasserstein optimization that effectively learns joint distributions using both seen and unseen class semantics for GZSL.

Findings

Superior performance on benchmark datasets

Effective preservation of domain distinctions

Reduced bias towards seen classes

Abstract

Bidirectional mapping-based generalized zero-shot learning (GZSL) methods rely on the quality of synthesized features to recognize seen and unseen data. Therefore, learning a joint distribution of seen-unseen domains and preserving domain distinction is crucial for these methods. However, existing methods only learn the underlying distribution of seen data, although unseen class semantics are available in the GZSL problem setting. Most methods neglect retaining domain distinction and use the learned distribution to recognize seen and unseen data. Consequently, they do not perform well. In this work, we utilize the available unseen class semantics alongside seen class semantics and learn joint distribution through a strong visual-semantic coupling. We propose a bidirectional mapping coupled generative adversarial network (BMCoGAN) by extending the coupled generative adversarial network into a dual-domain learning bidirectional mapping model. We further integrate a Wasserstein generative adversarial optimization to supervise the joint distribution learning. We design a loss optimization for retaining domain distinctive information in the synthesized features and reducing bias towards seen classes, which pushes synthesized seen features towards real seen features and pulls synthesized unseen features away from real seen features. We evaluate BMCoGAN on benchmark datasets and demonstrate its superior performance against contemporary methods.