Relation-based Discriminative Cooperation Network for Zero-Shot Classification

Highlights：

• The discriminative visual embedding preserves the discriminative information of the image features by separating the inter-classes and clustering the intra-classes with a margin.

• The discriminative semantic embedding acts as a pivot regularization to ensure the cooperated structures representative by utilizing semantic relations between classes.

• Extensive experimental evaluation on multiple datasets, including the large scale ImageNet shows that the proposed model performs favorably against state-of-the-art ZSL methods.