Semantic Feature Extraction for Generalized Zero-Shot Learning

Generalized zero-shot learning (GZSL) is a technique to train deep model identify unseen classes using the attribute. In this paper, we put forth new GZSL that improves classification performance greatly. Key idea of proposed approach, henceforth referred as semantic feature extraction-based (SE-GZSL), use containing only attribute-related information in relationship between image and doing so, can remove interference, if any, caused by attribute-irrelevant contained feature. To network extracting feature, present two novel loss functions, 1) mutual information-based capture all 2) similarity-based unwanted information. From extensive experiments various datasets, show SE-GZSL outperforms conventional approaches large margin.