Relation-based Discriminative Cooperation Network for Zero-Shot Classification

•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. Zero-shot learning (ZSL) aims to assign the category corresponding to the relevant semantic as the label of the unseen sample based on the relationship between the learned visual and semantic features. However, most typical ZSL models faced with the domain bias problem, which leads to unseen or test samples being easily misclassified into seen or training categories. To handle this problem, we propose a relation-based discriminative cooperation network (RDCN) model for ZSL in this work. The proposed model effectively utilize the robust metric space spanned by the cooperated semantics with the help of a set of relations. On the other hand, we devise the relation network to measure the relationship between the visual features and embedded semantics, and the validation information will guide the embedding module to learn more discriminative information. At last, the proposed RDCN model is validated on six benchmarks, and extensive experiments demonstrate the superiority of proposed method over most existing ZSL models on the traditional zero-shot setting and the more realistic generalized zero-shot setting.