Data driven recurrent generative adversarial network for generalized zero shot image classification

Traditional Generative Adversarial Network (GAN) based Generalized Zero Shot Learning (GZSL) methods usually suffer from a problem that these methods ignore the differences between classes when using the standard normal distribution to fit the true distribution of each category, and the incompleteness of a single adversarial training makes the model unable to capture all the characteristics of the samples. To address this problem, a data-driven recurrent adversarial generative network is proposed in this paper. We first synthe-size visual prototypes for unseen classes using the transformation from semantic attributes to visual prototypes learned on seen classes. Then, some noise is generated from these pro-totypes to synthesize the unseen samples according to the corresponding semantic attri-butes. During the sample generation process, a recurrent generative adversarial network is designed to facilitate the generated visual features to be more representative. Extensive experiments on five popular datasets as well as detailed ablation studies demon-strate the effectiveness and superiority of the proposed method.(c) 2023 Elsevier Inc. All rights reserved.