Integrated generalized zero-shot learning for fine-grained classification

Embedding learning (EL) and feature synthesizing (FS) are two of the popular categories fine-grained GZSL methods. EL or FS using global features cannot discriminate fine details in absence local features. On other hand, methods exploiting either neglect direct attribute guidance information. Consequently, neither method performs well. In this paper, we propose to explore attribute-supervised visual for both an integrated manner GZSL. The proposed network has sub-network a sub-network. can be tested ways. We novel two-step dense attention mechanism discover attribute-guided introduce new mutual between sub-networks exploit mutually beneficial information optimization. Moreover, compute source-target class similarity based on transfer-learn target classes reduce bias towards source domain during testing. demonstrate that our outperforms contemporary benchmark datasets.