Class Knowledge Overlay to Visual Feature Learning for Zero-Shot Image Classification

Abstract

New categories can be discovered by transforming semantic features into synthesized visual features without corresponding training samples in zero-shot image classification. Although significant progress has been made in generating high-quality synthesized visual features using generative adversarial networks, guaranteeing semantic consistency between the semantic features and visual features remains very challenging. In this paper, we propose a novel zero-shot learning approach, GAN-CST, based on class knowledge to visual feature learning to tackle the problem. The approach consists of three parts, class knowledge overlay, semi-supervised learning and triplet loss. It applies class knowledge overlay (CKO) to obtain knowledge not only from the corresponding class but also from other classes that have the knowledge overlay. It ensures that the knowledge-to-visual learning process has adequate information to generate synthesized visual features. The approach also applies a semi-supervised learning process to re-train knowledge-to-visual model. It contributes to reinforcing synthesized visual features generation as well as new category prediction. We tabulate results on a number of benchmark datasets demonstrating that the proposed model delivers superior performance over state-of-the-art approaches.

References in corpus (9)

• Semi-Supervised Classification with Graph Convolutional Networks
• Zero-Shot Learning Through Cross-Modal Transfer
• Transductive Multi-view Zero-Shot Learning
• AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks
• A Unified Perspective on Multi-Domain and Multi-Task Learning
• Zero-Shot Learning via Class-Conditioned Deep Generative Models
• Recent Advances in Zero-shot Recognition
• A Unified Semantic Embedding: Relating Taxonomies and Attributes
• Unified Generator-Classifier for Efficient Zero-Shot Learning